Delete FL2VA

FL2VA/audio_vae/config.json

@@ -1,81 +0,0 @@
-{
-  "_class_name": "MiniMaxH3AudioVAE",
-  "_diffusers_version": "0.32.2",
-  "auto_map": {
-    "AutoModel": "minimax_h3_audio_vae.MiniMaxH3AudioVAE"
-  },
-  "output_channel": 2,
-  "sample_rate": 32000,
-  "source_config_path": "config.yaml",
-  "source_safetensors_path": "model.safetensors",
-  "source_metadata_path": "metadata.json",
-  "latent_channels": 32,
-  "latents_mean": [
-    -0.020211687488382354,
-    0.3876466479950502,
-    -0.04398279799186767,
-    -0.28591514936373,
-    0.08179686214561671,
-    -0.35782641352446604,
-    0.040623809960919084,
-    -0.01552534501956604,
-    -0.223362481667332,
-    0.1821006842509091,
-    0.2941778783780663,
-    -0.07901167601970885,
-    -0.056815072777201,
-    -0.3699028221860095,
-    -0.31616315591624855,
-    0.5905951377425391,
-    -0.052139568068853864,
-    0.013673160263486295,
-    -0.03691647864630577,
-    0.09732660653298163,
-    -0.3394662328788498,
-    -0.30685677538541667,
-    -0.24504598907458763,
-    -0.034698524462007344,
-    0.02868032184767538,
-    -0.21217779266454084,
-    -0.1678263169941987,
-    0.3221287889040614,
-    -0.1223055851554907,
-    0.4356604928128464,
-    -0.0502599202236253,
-    0.3979258376211797
-  ],
-  "latents_std": [
-    1.6895524230479284,
-    2.76263727217653,
-    1.7945344281264435,
-    1.6801681847309828,
-    1.6390226546605453,
-    2.7788298348882177,
-    1.7659090095747236,
-    1.6199757612137327,
-    2.6336525640336896,
-    1.8539356672817833,
-    2.5056497896915633,
-    1.811019237886178,
-    1.9579657790720237,
-    1.6685498243529284,
-    1.4922469314453364,
-    3.298670198067373,
-    1.9491804496832168,
-    1.8720003270431442,
-    1.8334080103291832,
-    1.6488070416529093,
-    1.6176957696319716,
-    1.9131449234774398,
-    1.5695245398428617,
-    1.6943659940415912,
-    1.8318420762504692,
-    1.5540637421583379,
-    1.9344930328968526,
-    1.599198216109855,
-    1.718045989838149,
-    1.6307219190837705,
-    1.8661226051202384,
-    1.5613768203168363
-  ]
-}

FL2VA/audio_vae/config.yaml

@@ -1,5 +0,0 @@
-model_config:
-  sr: 32000
-  decoder_dim: 1024
-  audio_channel: 1
-  vae_latent_channels: 32

FL2VA/audio_vae/dac_activations.py

@@ -1,60 +0,0 @@
-# SPDX-License-Identifier: MIT
-# Implementation adapted from https://github.com/EdwardDixon/snake under the MIT license.
-
-import torch
-from torch import nn
-from torch.nn import Parameter
-
-
-@torch.jit.script
-def snakebeta(x, alpha, beta):
-    shape = x.shape
-    x = x.reshape(shape[0], shape[1], -1)
-    x = x + (beta + 1e-9).reciprocal() * torch.sin(alpha * x).pow(2)
-    x = x.reshape(shape)
-    return x
-
-
-class SnakeBeta(nn.Module):
-    def __init__(self, in_features, alpha=1.0, alpha_trainable=True, alpha_logscale=False):
-        """
-        Initialization.
-        INPUT:
-            - in_features: shape of the input
-            - alpha - trainable parameter that controls frequency
-            - beta - trainable parameter that controls magnitude
-            alpha is initialized to 1 by default, higher values = higher-frequency.
-            beta is initialized to 1 by default, higher values = higher-magnitude.
-            alpha will be trained along with the rest of your model.
-        """
-        super(SnakeBeta, self).__init__()
-        self.in_features = in_features
-
-        # Initialize alpha
-        self.alpha_logscale = alpha_logscale
-        if self.alpha_logscale:  # Log scale alphas initialized to zeros
-            self.alpha = Parameter(torch.zeros(in_features) * alpha)
-            self.beta = Parameter(torch.zeros(in_features) * alpha)
-        else:  # Linear scale alphas initialized to ones
-            self.alpha = Parameter(torch.ones(in_features) * alpha)
-            self.beta = Parameter(torch.ones(in_features) * alpha)
-
-        self.alpha.requires_grad = alpha_trainable
-        self.beta.requires_grad = alpha_trainable
-
-        self.no_div_by_zero = 0.000000001
-
-    def forward(self, x):
-        """
-        Forward pass of the function.
-        Applies the function to the input elementwise.
-        SnakeBeta := x + 1/b * sin^2 (xa)
-        """
-        alpha = self.alpha.unsqueeze(0).unsqueeze(-1)  # Line up with x to [B, C, T]
-        beta = self.beta.unsqueeze(0).unsqueeze(-1)
-        if self.alpha_logscale:
-            alpha = torch.exp(alpha)
-            beta = torch.exp(beta)
-        x = snakebeta(x, alpha, beta)
-
-        return x

FL2VA/audio_vae/dac_alias_free_act.py

@@ -1,30 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
-
-import torch.nn as nn
-from .dac_alias_free_resample import UpSample1d, DownSample1d
-
-
-class Activation1d(nn.Module):
-    def __init__(
-        self,
-        activation,
-        up_ratio: int = 2,
-        down_ratio: int = 2,
-        up_kernel_size: int = 12,
-        down_kernel_size: int = 12,
-    ):
-        super().__init__()
-        self.up_ratio = up_ratio
-        self.down_ratio = down_ratio
-        self.act = activation
-        self.upsample = UpSample1d(up_ratio, up_kernel_size)
-        self.downsample = DownSample1d(down_ratio, down_kernel_size)
-
-    # x: [B,C,T]
-    def forward(self, x):
-        x = self.upsample(x)
-        x = self.act(x)
-        x = self.downsample(x)
-
-        return x

FL2VA/audio_vae/dac_alias_free_filter.py

@@ -1,97 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-import math
-
-if "sinc" in dir(torch):
-    sinc = torch.sinc
-else:
-    # This code is adopted from adefossez's julius.core.sinc under the MIT License
-    # https://adefossez.github.io/julius/julius/core.html
-    def sinc(x: torch.Tensor):
-        """
-        Implementation of sinc, i.e. sin(pi * x) / (pi * x)
-        __Warning__: Different to julius.sinc, the input is multiplied by `pi`!
-        """
-        return torch.where(
-            x == 0,
-            torch.tensor(1.0, device=x.device, dtype=x.dtype),
-            torch.sin(math.pi * x) / math.pi / x,
-        )
-
-
-# This code is adopted from adefossez's julius.lowpass.LowPassFilters under the MIT License
-# https://adefossez.github.io/julius/julius/lowpass.html
-def kaiser_sinc_filter1d(cutoff, half_width, kernel_size):  # return filter [1,1,kernel_size]
-    even = kernel_size % 2 == 0
-    half_size = kernel_size // 2
-
-    # For kaiser window
-    delta_f = 4 * half_width
-    A = 2.285 * (half_size - 1) * math.pi * delta_f + 7.95
-    if A > 50.0:
-        beta = 0.1102 * (A - 8.7)
-    elif A >= 21.0:
-        beta = 0.5842 * (A - 21) ** 0.4 + 0.07886 * (A - 21.0)
-    else:
-        beta = 0.0
-    window = torch.kaiser_window(kernel_size, beta=beta, periodic=False)
-
-    # ratio = 0.5/cutoff -> 2 * cutoff = 1 / ratio
-    if even:
-        time = torch.arange(-half_size, half_size) + 0.5
-    else:
-        time = torch.arange(kernel_size) - half_size
-    if cutoff == 0:
-        filter_ = torch.zeros_like(time)
-    else:
-        filter_ = 2 * cutoff * window * sinc(2 * cutoff * time)
-        """
-        Normalize filter to have sum = 1, otherwise we will have a small leakage of the constant component in the input signal.
-        """
-        filter_ /= filter_.sum()
-        filter = filter_.view(1, 1, kernel_size)
-
-    return filter
-
-
-class LowPassFilter1d(nn.Module):
-    def __init__(
-        self,
-        cutoff=0.5,
-        half_width=0.6,
-        stride: int = 1,
-        padding: bool = True,
-        padding_mode: str = "replicate",
-        kernel_size: int = 12,
-    ):
-        """
-        kernel_size should be even number for stylegan3 setup, in this implementation, odd number is also possible.
-        """
-        super().__init__()
-        if cutoff < -0.0:
-            raise ValueError("Minimum cutoff must be larger than zero.")
-        if cutoff > 0.5:
-            raise ValueError("A cutoff above 0.5 does not make sense.")
-        self.kernel_size = kernel_size
-        self.even = kernel_size % 2 == 0
-        self.pad_left = kernel_size // 2 - int(self.even)
-        self.pad_right = kernel_size // 2
-        self.stride = stride
-        self.padding = padding
-        self.padding_mode = padding_mode
-        filter = kaiser_sinc_filter1d(cutoff, half_width, kernel_size)
-        self.register_buffer("filter", filter)
-
-    # Input [B, C, T]
-    def forward(self, x):
-        _, C, _ = x.shape
-
-        if self.padding:
-            x = F.pad(x, (self.pad_left, self.pad_right), mode=self.padding_mode)
-        out = F.conv1d(x, self.filter.expand(C, -1, -1), stride=self.stride, groups=C)
-
-        return out

FL2VA/audio_vae/dac_alias_free_resample.py

@@ -1,48 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
-
-import torch.nn as nn
-from torch.nn import functional as F
-from .dac_alias_free_filter import LowPassFilter1d
-from .dac_alias_free_filter import kaiser_sinc_filter1d
-
-
-class UpSample1d(nn.Module):
-    def __init__(self, ratio=2, kernel_size=None):
-        super().__init__()
-        self.ratio = ratio
-        self.kernel_size = int(6 * ratio // 2) * 2 if kernel_size is None else kernel_size
-        self.stride = ratio
-        self.pad = self.kernel_size // ratio - 1
-        self.pad_left = self.pad * self.stride + (self.kernel_size - self.stride) // 2
-        self.pad_right = self.pad * self.stride + (self.kernel_size - self.stride + 1) // 2
-        filter = kaiser_sinc_filter1d(cutoff=0.5 / ratio, half_width=0.6 / ratio, kernel_size=self.kernel_size)
-        self.register_buffer("filter", filter)
-
-    # x: [B, C, T]
-    def forward(self, x):
-        _, C, _ = x.shape
-
-        x = F.pad(x, (self.pad, self.pad), mode="replicate")
-        x = self.ratio * F.conv_transpose1d(x, self.filter.expand(C, -1, -1), stride=self.stride, groups=C)
-        x = x[..., self.pad_left : -self.pad_right]
-
-        return x
-
-
-class DownSample1d(nn.Module):
-    def __init__(self, ratio=2, kernel_size=None):
-        super().__init__()
-        self.ratio = ratio
-        self.kernel_size = int(6 * ratio // 2) * 2 if kernel_size is None else kernel_size
-        self.lowpass = LowPassFilter1d(
-            cutoff=0.5 / ratio,
-            half_width=0.6 / ratio,
-            stride=ratio,
-            kernel_size=self.kernel_size,
-        )
-
-    def forward(self, x):
-        xx = self.lowpass(x)
-
-        return xx

FL2VA/audio_vae/dac_attn_proj.py

@@ -1,88 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from torch.nn.functional import scaled_dot_product_attention
-
-
-class GeGluMlp(nn.Module):
-    def __init__(
-        self,
-        in_features,
-        hidden_features,
-    ):
-        super().__init__()
-        self.norm = nn.LayerNorm(in_features)
-        self.act = nn.GELU(approximate="tanh")
-        self.w0 = nn.Linear(in_features, hidden_features)
-        self.w1 = nn.Linear(in_features, hidden_features)
-        self.w2 = nn.Linear(hidden_features, in_features)
-
-    def forward(self, x):
-        x = self.norm(x)
-        x = self.act(self.w0(x)) * self.w1(x)
-        x = self.w2(x)
-        return x
-
-
-class CausalAttention(nn.Module):
-    def __init__(self, in_dim, out_dim, num_heads):
-        super().__init__()
-        if in_dim > out_dim:
-            # assert in_dim // num_heads == out_dim
-            self.head_dim = in_dim // num_heads
-            self.qkv = nn.Linear(in_dim, in_dim * 3, bias=False)
-            self.q_bias = nn.Parameter(torch.zeros(in_dim))
-            self.v_bias = nn.Parameter(torch.zeros(in_dim))
-            self.register_buffer("zero_k_bias", torch.zeros(in_dim))
-        else:
-            # assert out_dim // num_heads == in_dim
-            self.head_dim = out_dim // num_heads
-            self.qkv = nn.Linear(in_dim, out_dim * 3, bias=False)
-            self.q_bias = nn.Parameter(torch.zeros(out_dim))
-            self.v_bias = nn.Parameter(torch.zeros(out_dim))
-            self.register_buffer("zero_k_bias", torch.zeros(out_dim))
-
-        self.in_dim = in_dim
-        self.out_dim = out_dim
-        self.num_heads = num_heads
-        self.scale = self.head_dim**-0.5
-        self.proj = nn.Linear(out_dim, out_dim)
-
-    def forward(self, x: torch.Tensor) -> torch.Tensor:
-        B, N, C = x.shape
-        qkv = F.linear(input=x, weight=self.qkv.weight, bias=torch.cat((self.q_bias, self.zero_k_bias, self.v_bias)))
-        q, k, v = qkv.reshape(B, N, 3, self.num_heads, self.head_dim).permute(2, 0, 3, 1, 4).unbind(0)
-
-        x = scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=True)
-
-        if self.in_dim > self.out_dim:
-            x = torch.mean(x, dim=1)
-            if self.in_dim // self.num_heads != self.out_dim:
-                x = nn.functional.adaptive_avg_pool1d(x, self.out_dim)
-        else:
-            x = x.transpose(1, 2).reshape(B, N, -1)
-        x = self.proj(x)
-        return x
-
-
-class AttnProjection(nn.Module):
-    def __init__(self, in_dim, out_dim, num_heads, norm_layer=nn.LayerNorm, mlp_ratio=2):
-        super().__init__()
-        assert out_dim % in_dim == 0 or in_dim % out_dim == 0
-        self.in_dim = in_dim
-        self.out_dim = out_dim
-        self.norm1 = norm_layer(in_dim)
-        self.attn = CausalAttention(in_dim, out_dim, num_heads)
-        self.proj = nn.Linear(in_dim, out_dim)
-        self.norm3 = norm_layer(in_dim)
-
-        self.norm2 = norm_layer(out_dim)
-        hidden_dim = int(out_dim * mlp_ratio)
-        self.mlp = GeGluMlp(in_features=out_dim, hidden_features=hidden_dim)
-        # self.mlp = FeedForward(out_dim, out_dim)
-
-    def forward(self, x):
-        x = self.proj(self.norm3(x)) + self.attn(self.norm1(x))
-        x = x + self.mlp(self.norm2(x))
-        return x

FL2VA/audio_vae/dac_audio_vae.py

@@ -1,225 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# DAC-lineage audio VAE: waveform encoder + BigVGAN decoder (inference-only bundle).
-import math
-from typing import List
-
-import numpy as np
-import torch
-from torch import nn
-from torch.nn.utils.parametrizations import weight_norm
-
-from .dac_bigvgan import BigVGAN
-from .dac_attn_proj import AttnProjection
-
-
-class AttrDict(dict):
-    def __init__(self, *args, **kwargs):
-        super(AttrDict, self).__init__(*args, **kwargs)
-        self.__dict__ = self
-
-
-def WNConv1d(*args, **kwargs):
-    return weight_norm(nn.Conv1d(*args, **kwargs))
-
-
-@torch.jit.script
-def snake(x, alpha):
-    shape = x.shape
-    x = x.reshape(shape[0], shape[1], -1)
-    x = x + (alpha + 1e-9).reciprocal() * torch.sin(alpha * x).pow(2)
-    x = x.reshape(shape)
-    return x
-
-
-class Snake1d(nn.Module):
-    def __init__(self, channels):
-        super().__init__()
-        self.alpha = nn.Parameter(torch.ones(1, channels, 1))
-
-    def forward(self, x):
-        return snake(x, self.alpha)
-
-
-def init_weights(m):
-    if isinstance(m, nn.Conv1d):
-        nn.init.trunc_normal_(m.weight, std=0.02)
-        if m.bias is not None:
-            nn.init.constant_(m.bias, 0)
-
-
-class ResidualUnit(nn.Module):
-    def __init__(self, dim: int = 16, dilation: int = 1):
-        super().__init__()
-        pad = ((7 - 1) * dilation) // 2
-        self.block = nn.Sequential(
-            Snake1d(dim),
-            WNConv1d(dim, dim, kernel_size=7, dilation=dilation, padding=pad),
-            Snake1d(dim),
-            WNConv1d(dim, dim, kernel_size=1),
-        )
-
-    def forward(self, x):
-        y = self.block(x)
-        pad = (x.shape[-1] - y.shape[-1]) // 2
-        if pad > 0:
-            x = x[..., pad:-pad]
-        return x + y
-
-
-class EncoderBlock(nn.Module):
-    def __init__(self, dim: int = 16, stride: int = 1):
-        super().__init__()
-        self.block = nn.Sequential(
-            ResidualUnit(dim // 2, dilation=1),
-            ResidualUnit(dim // 2, dilation=3),
-            ResidualUnit(dim // 2, dilation=9),
-            Snake1d(dim // 2),
-            WNConv1d(
-                dim // 2,
-                dim,
-                kernel_size=2 * stride,
-                stride=stride,
-                padding=math.ceil(stride / 2),
-            ),
-        )
-
-    def forward(self, x):
-        return self.block(x)
-
-
-class Encoder(nn.Module):
-    def __init__(
-        self,
-        d_model: int = 64,
-        strides: list = [2, 4, 8, 8],
-        d_latent: int = 64,
-    ):
-        super().__init__()
-        # Create first convolution
-        self.block = [WNConv1d(1, d_model, kernel_size=7, padding=3)]
-
-        # Create EncoderBlocks that double channels as they downsample by `stride`
-        for stride in strides:
-            d_model *= 2
-            self.block += [EncoderBlock(d_model, stride=stride)]
-
-        # Create last convolution
-        self.block += [
-            Snake1d(d_model),
-            WNConv1d(d_model, d_latent, kernel_size=3, padding=1),
-        ]
-
-        # Wrap black into nn.Sequential
-        self.block = nn.Sequential(*self.block)
-        self.enc_dim = d_model
-
-    def forward(self, x):
-        return self.block(x)
-
-
-class DacAudioVAE(nn.Module):
-    def __init__(
-        self,
-        encoder_dim: int = 64,
-        encoder_rates: List[int] = [2, 4, 8, 8],
-        latent_dim: int = None,
-        decoder_dim: int = 1536,
-        decoder_rates: List[int] = [8, 8, 4, 2],
-        sample_rate: int = 44100,
-        vae_latent_channels: int = 64,
-        attn_proj: bool = False,
-        decoder_type: str = "bigvgan",
-    ):
-        super().__init__()
-
-        self.encoder_dim = encoder_dim
-        self.encoder_rates = encoder_rates
-        self.decoder_dim = decoder_dim
-        self.decoder_rates = decoder_rates
-        self.sample_rate = sample_rate
-        self.attn_proj = attn_proj
-        self.decoder_type = decoder_type
-
-        if latent_dim is None:
-            latent_dim = encoder_dim * (2 ** len(encoder_rates))
-
-        self.latent_dim = latent_dim
-
-        self.hop_length = np.prod(encoder_rates)
-        self.encoder = Encoder(encoder_dim, encoder_rates, latent_dim)
-
-        if latent_dim % vae_latent_channels == 0:
-            self.attn_proj_dim = vae_latent_channels
-        else:
-            # smallest power of two >= vae_latent_channels
-            self.attn_proj_dim = 2 ** int(np.ceil(np.log2(vae_latent_channels)))
-
-        self.mean_proj = nn.Conv1d(self.attn_proj_dim, vae_latent_channels, 1)
-        self.logs_proj = nn.Conv1d(self.attn_proj_dim, vae_latent_channels, 1)
-
-        self.dec_in_proj = nn.Conv1d(vae_latent_channels, latent_dim, 1)
-
-        if self.decoder_type == "bigvgan":
-            if sample_rate == 16000:
-                bigvgan_conf = {"resblock": "1",
-                            "num_mels": latent_dim,
-                            "upsample_rates": [5,5,2,2,2,2],
-                            "upsample_kernel_sizes": [9,9,4,4,4,4],
-                            "upsample_initial_channel": decoder_dim,
-                            "resblock_kernel_sizes": [3,7,11],
-                            "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-                            "use_tanh_at_final": False,
-                            "use_bias_at_final": False,
-                            "activation": "snakebeta",
-                            "snake_logscale": True}
-            elif sample_rate == 32000:
-                bigvgan_conf = {"resblock": "1",
-                            "num_mels": latent_dim,
-                            "upsample_rates": [5,5,2,2,2,2,2],
-                            "upsample_kernel_sizes": [9,9,4,4,4,4,4],
-                            "upsample_initial_channel": decoder_dim,
-                            "resblock_kernel_sizes": [3,7,11],
-                            "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-                            "use_tanh_at_final": False,
-                            "use_bias_at_final": False,
-                            "activation": "snakebeta",
-                            "snake_logscale": True}
-            else:
-                raise ValueError(f"Invalid sample_rate: {sample_rate}")
-
-            h = AttrDict(**bigvgan_conf)
-            self.decoder = BigVGAN(h)
-        else:
-            raise ValueError(f"Invalid decoder type: {self.decoder_type}")
-
-        if self.attn_proj:
-            self.pre_block = AttnProjection(latent_dim, self.attn_proj_dim, num_heads=8)
-
-        self.sample_rate = sample_rate
-        self.apply(init_weights)
-
-    def preprocess(self, audio_data, sample_rate):
-        if sample_rate is None:
-            sample_rate = self.sample_rate
-
-        length = audio_data.shape[-1]
-        right_pad = math.ceil(length / self.hop_length) * self.hop_length - length
-        audio_data = nn.functional.pad(audio_data, (0, right_pad))
-
-        return audio_data
-
-    def decode(self, z: torch.Tensor):
-        """Decode given latent codes and return audio data
-
-        Parameters
-        ----------
-        z : Tensor[B x D x T]
-            Continuous latent representation
-
-        Returns
-        -------
-        Tensor[B x 1 x length]
-            Decoded audio data.
-        """
-        z = self.dec_in_proj(z)
-        return self.decoder(z)

FL2VA/audio_vae/dac_bigvgan.py

@@ -1,206 +0,0 @@
-# SPDX-License-Identifier: MIT
-# Copyright (c) 2024 NVIDIA CORPORATION.
-#   Licensed under the MIT license.
-
-# Adapted from https://github.com/jik876/hifi-gan under the MIT license.
-
-from .dac_activations import SnakeBeta
-
-import torch
-import torch.nn as nn
-from torch.nn import Conv1d, ConvTranspose1d
-from torch.nn.utils.parametrizations import weight_norm
-
-from .dac_utils import init_weights, get_padding
-from .dac_alias_free_act import Activation1d
-
-
-class AttrDict(dict):
-    def __init__(self, *args, **kwargs):
-        super(AttrDict, self).__init__(*args, **kwargs)
-        self.__dict__ = self
-
-
-class AMPBlock1(torch.nn.Module):
-    """
-    AMPBlock applies SnakeBeta activation functions with trainable parameters that control periodicity, defined for each layer.
-    AMPBlock1 has additional self.convs2 that contains additional Conv1d layers with a fixed dilation=1 followed by each layer in self.convs1
-
-    Args:
-        h (AttrDict): Hyperparameters.
-        channels (int): Number of convolution channels.
-        kernel_size (int): Size of the convolution kernel. Default is 3.
-        dilation (tuple): Dilation rates for the convolutions. Each dilation layer has two convolutions. Default is (1, 3, 5).
-        activation (str): Activation function type. Must be 'snakebeta'.
-    """
-
-    def __init__(
-        self,
-        h: AttrDict,
-        channels: int,
-        kernel_size: int = 3,
-        dilation: tuple = (1, 3, 5),
-        activation: str = None,
-    ):
-        super().__init__()
-
-        self.h = h
-
-        self.convs1 = nn.ModuleList(
-            [
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        stride=1,
-                        dilation=d,
-                        padding=get_padding(kernel_size, d),
-                    )
-                )
-                for d in dilation
-            ]
-        )
-        self.convs1.apply(init_weights)
-
-        self.convs2 = nn.ModuleList(
-            [
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        stride=1,
-                        dilation=1,
-                        padding=get_padding(kernel_size, 1),
-                    )
-                )
-                for _ in range(len(dilation))
-            ]
-        )
-        self.convs2.apply(init_weights)
-
-        self.num_layers = len(self.convs1) + len(self.convs2)  # Total number of conv layers
-
-        if activation == "snakebeta":
-            self.activations = nn.ModuleList(
-                [
-                    Activation1d(activation=SnakeBeta(channels, alpha_logscale=h.snake_logscale))
-                    for _ in range(self.num_layers)
-                ]
-            )
-        else:
-            raise NotImplementedError(
-                "activation incorrectly specified. check the config file and look for 'activation'."
-            )
-
-    def forward(self, x):
-        acts1, acts2 = self.activations[::2], self.activations[1::2]
-        for c1, c2, a1, a2 in zip(self.convs1, self.convs2, acts1, acts2):
-            xt = a1(x)
-            xt = c1(xt)
-            xt = a2(xt)
-            xt = c2(xt)
-            x = xt + x
-
-        return x
-
-
-class BigVGAN(torch.nn.Module):
-    """
-    BigVGAN is a neural vocoder model that applies anti-aliased periodic activation for residual blocks (resblocks).
-
-    Args:
-        h (AttrDict): Hyperparameters.
-    """
-
-    def __init__(self, h: AttrDict):
-        super().__init__()
-        self.h = h
-
-        self.num_kernels = len(h.resblock_kernel_sizes)
-        self.num_upsamples = len(h.upsample_rates)
-
-        # Pre-conv
-        self.conv_pre = weight_norm(Conv1d(h.num_mels, h.upsample_initial_channel, 7, 1, padding=3))
-
-        # Define which AMPBlock to use. BigVGAN uses AMPBlock1 as default
-        if h.resblock == "1":
-            resblock_class = AMPBlock1
-        else:
-            raise ValueError(f"Incorrect resblock class specified in hyperparameters. Got {h.resblock}")
-
-        # Transposed conv-based upsamplers. does not apply anti-aliasing
-        self.ups = nn.ModuleList()
-        for i, (u, k) in enumerate(zip(h.upsample_rates, h.upsample_kernel_sizes)):
-            self.ups.append(
-                nn.ModuleList(
-                    [
-                        weight_norm(
-                            ConvTranspose1d(
-                                h.upsample_initial_channel // (2**i),
-                                h.upsample_initial_channel // (2 ** (i + 1)),
-                                k,
-                                u,
-                                padding=(k - u) // 2,
-                            )
-                        )
-                    ]
-                )
-            )
-
-        # Residual blocks using anti-aliased multi-periodicity composition modules (AMP)
-        self.resblocks = nn.ModuleList()
-        for i in range(len(self.ups)):
-            ch = h.upsample_initial_channel // (2 ** (i + 1))
-            for j, (k, d) in enumerate(zip(h.resblock_kernel_sizes, h.resblock_dilation_sizes)):
-                self.resblocks.append(resblock_class(h, ch, k, d, activation=h.activation))
-
-        # Post-conv
-        if h.activation != "snakebeta":
-            raise NotImplementedError(
-                "activation incorrectly specified. check the config file and look for 'activation'."
-            )
-        activation_post = SnakeBeta(ch, alpha_logscale=h.snake_logscale)
-
-        self.activation_post = Activation1d(activation=activation_post)
-
-        # Whether to use bias for the final conv_post. Default to True for backward compatibility
-        self.use_bias_at_final = h.get("use_bias_at_final", True)
-        self.conv_post = weight_norm(Conv1d(ch, 1, 7, 1, padding=3, bias=self.use_bias_at_final))
-
-        # Weight initialization
-        for i in range(len(self.ups)):
-            self.ups[i].apply(init_weights)
-        self.conv_post.apply(init_weights)
-
-        # Final tanh activation. Defaults to True for backward compatibility
-        self.use_tanh_at_final = h.get("use_tanh_at_final", True)
-
-    def forward(self, x):
-        # Pre-conv
-        x = self.conv_pre(x)
-
-        for i in range(self.num_upsamples):
-            # Upsampling
-            for i_up in range(len(self.ups[i])):
-                x = self.ups[i][i_up](x)
-            # AMP blocks
-            xs = None
-            for j in range(self.num_kernels):
-                if xs is None:
-                    xs = self.resblocks[i * self.num_kernels + j](x)
-                else:
-                    xs += self.resblocks[i * self.num_kernels + j](x)
-            x = xs / self.num_kernels
-
-        # Post-conv
-        x = self.activation_post(x)
-        x = self.conv_post(x)
-        # Final tanh activation
-        if self.use_tanh_at_final:
-            x = torch.tanh(x)
-        else:
-            x = torch.clamp(x, min=-1.0, max=1.0)  # Bound the output to [-1, 1]
-
-        return x

FL2VA/audio_vae/dac_utils.py

@@ -1,12 +0,0 @@
-# SPDX-License-Identifier: MIT
-# Adapted from https://github.com/jik876/hifi-gan under the MIT license.
-
-
-def init_weights(m, mean=0.0, std=0.01):
-    classname = m.__class__.__name__
-    if classname.find("Conv") != -1:
-        m.weight.data.normal_(mean, std)
-
-
-def get_padding(kernel_size, dilation=1):
-    return int((kernel_size * dilation - dilation) / 2)

FL2VA/audio_vae/metadata.json

@@ -1,29 +0,0 @@
-{
-  "metadata": {
-    "kwargs": {
-      "attn_proj": true,
-      "decoder_dim": 1024,
-      "decoder_rates": [
-        5,
-        5,
-        2,
-        2,
-        2,
-        2,
-        2
-      ],
-      "decoder_type": "bigvgan",
-      "encoder_dim": 64,
-      "encoder_rates": [
-        2,
-        4,
-        4,
-        5,
-        5
-      ],
-      "latent_dim": 2048,
-      "sample_rate": 32000,
-      "vae_latent_channels": 32
-    }
-  }
-}

FL2VA/audio_vae/minimax_h3_audio_vae.py

@@ -1,86 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# Remote entry: self-contained MiniMax H3 audio VAE (DAC-lineage encoder + BigVGAN decoder).
-# Loaded via config.json:auto_map with trust_remote_code; weights are safetensors-only.
-from __future__ import annotations
-
-import json
-from pathlib import Path
-
-import torch.nn as nn
-
-# --- dependency manifest ---
-# diffusers' dynamic-module loader only copies ONE level of relative
-# imports into its cache; list every bundle module here so all files
-# are copied, letting their own second-level imports resolve.
-from .dac_activations import SnakeBeta as _dep_dac_activations  # noqa: F401
-from .dac_alias_free_act import Activation1d as _dep_dac_alias_free_act  # noqa: F401
-from .dac_alias_free_filter import kaiser_sinc_filter1d as _dep_dac_alias_free_filter  # noqa: F401
-from .dac_alias_free_resample import UpSample1d as _dep_dac_alias_free_resample  # noqa: F401
-from .dac_attn_proj import GeGluMlp as _dep_dac_attn_proj  # noqa: F401
-from .dac_bigvgan import AttrDict as _dep_dac_bigvgan  # noqa: F401
-from .dac_audio_vae import AttrDict as _dep_dac_audio_vae  # noqa: F401
-from .dac_utils import init_weights as _dep_dac_utils  # noqa: F401
-# --- end dependency manifest ---
-from safetensors.torch import load_file
-
-from .dac_audio_vae import DacAudioVAE
-
-
-def _load_yaml(path: Path) -> dict:
-    try:
-        import yaml
-    except ImportError as exc:
-        raise ImportError("MiniMax H3 audio VAE requires PyYAML.") from exc
-    with path.open("r", encoding="utf-8") as f:
-        return yaml.safe_load(f)
-
-
-class MiniMaxH3AudioVAE(nn.Module):
-    def __init__(self, model: nn.Module) -> None:
-        super().__init__()
-        self.model = model
-
-    @classmethod
-    def from_pretrained(cls, pretrained_model_name_or_path: str, **kwargs):
-        component_dir = Path(pretrained_model_name_or_path)
-        with (component_dir / "config.json").open("r", encoding="utf-8") as f:
-            config = json.load(f)
-
-        audio_config = _load_yaml(component_dir / config["source_config_path"])
-        if "source_safetensors_path" not in config:
-            raise KeyError(
-                "source_safetensors_path is required; pickle checkpoints are not supported"
-            )
-        if "source_metadata_path" not in config:
-            raise KeyError(
-                "source_metadata_path is required when source_safetensors_path is set"
-            )
-        state_dict = load_file(
-            component_dir / config["source_safetensors_path"], device="cpu"
-        )
-        with (component_dir / config["source_metadata_path"]).open(
-            "r", encoding="utf-8"
-        ) as f:
-            metadata_doc = json.load(f)
-        metadata = metadata_doc["metadata"]["kwargs"]
-
-        model = DacAudioVAE(
-            encoder_rates=metadata["encoder_rates"],
-            decoder_rates=metadata["decoder_rates"],
-            attn_proj=metadata["attn_proj"],
-            decoder_type=metadata["decoder_type"],
-            decoder_dim=audio_config["model_config"]["decoder_dim"],
-            vae_latent_channels=audio_config["model_config"]["vae_latent_channels"],
-            sample_rate=metadata["sample_rate"],
-        )
-        model.load_state_dict(state_dict, strict=True)
-        return cls(model.eval())
-
-    def decode(self, *args, **kwargs):
-        return self.model.decode(*args, **kwargs)
-
-    def __getattr__(self, name: str):
-        try:
-            return super().__getattr__(name)
-        except AttributeError:
-            return getattr(self.model, name)

FL2VA/audio_vae/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:37dddc2f3e6d5d5139d823d5ea283bbf304dadcb885b1ccda818aa13dade5ea2
-size 605429308

FL2VA/model_index.json

@@ -1,42 +0,0 @@
-{
-  "_class_name": "MiniMaxH3Pipeline",
-  "_diffusers_version": "0.32.2",
-  "text_encoder": [
-    "transformers",
-    "MiniMaxH3Qwen3VLHFEncoder"
-  ],
-  "tokenizer": [
-    "transformers",
-    "Qwen2TokenizerFast"
-  ],
-  "video_vae": [
-    "diffusers",
-    "MiniMaxH3VideoVAE"
-  ],
-  "audio_vae": [
-    "diffusers",
-    "MiniMaxH3AudioVAE"
-  ],
-  "scheduler": null,
-  "transformer": [
-    "diffusers",
-    "MiniMaxH3DiTModel"
-  ],
-  "processor": [
-    "transformers",
-    "Qwen3VLProcessor"
-  ],
-  "_minimax_h3": {
-    "schema_version": 1,
-    "partition": "fl2va",
-    "tasks": [
-      "t2va",
-      "fl2va"
-    ],
-    "task_aliases": {},
-    "sigma_shift_scales": {
-      "video": 12.0,
-      "audio": 3.0
-    }
-  }
-}

FL2VA/processor/chat_template.json

@@ -1,3 +0,0 @@
-{
-    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
-}

FL2VA/processor/preprocessor_config.json

@@ -1,21 +0,0 @@
-{
-    "size": {
-        "longest_edge": 16777216,
-        "shortest_edge": 65536
-    },
-    "patch_size": 16,
-    "temporal_patch_size": 2,
-    "merge_size": 2,
-    "image_mean": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "image_std": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "processor_class": "Qwen3VLProcessor",
-    "image_processor_type": "Qwen2VLImageProcessorFast"
-}

FL2VA/processor/tokenizer_config.json

@@ -1,246 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>",
-    "<d>",
-    "</d>",
-    "<|cutoff|>",
-    "<|lyrics_start|>",
-    "<|lyrics_end|>",
-    "<|caption_start|>",
-    "<|caption_end|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "model_max_length": 262144,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

FL2VA/processor/video_preprocessor_config.json

@@ -1,21 +0,0 @@
-{
-    "size": {
-        "longest_edge": 25165824,
-        "shortest_edge": 4096
-    },
-    "patch_size": 16,
-    "temporal_patch_size": 2,
-    "merge_size": 2,
-    "image_mean": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "image_std": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "processor_class": "Qwen3VLProcessor",
-    "video_processor_type": "Qwen3VLVideoProcessor"
-}

FL2VA/text_encoder/chat_template.json

@@ -1,3 +0,0 @@
-{
-    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
-}

FL2VA/text_encoder/config.json

@@ -1,62 +0,0 @@
-{
-  "architectures": [
-    "Qwen3VLForConditionalGeneration"
-  ],
-  "image_token_id": 151655,
-  "model_type": "qwen3_vl",
-  "text_config": {
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bos_token_id": 151643,
-    "dtype": "bfloat16",
-    "eos_token_id": 151645,
-    "head_dim": 128,
-    "hidden_act": "silu",
-    "hidden_size": 5120,
-    "initializer_range": 0.02,
-    "intermediate_size": 25600,
-    "max_position_embeddings": 262144,
-    "model_type": "qwen3_vl_text",
-    "num_attention_heads": 64,
-    "num_hidden_layers": 64,
-    "num_key_value_heads": 8,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": {
-      "mrope_interleaved": true,
-      "mrope_section": [
-        24,
-        20,
-        20
-      ],
-      "rope_type": "default"
-    },
-    "rope_theta": 5000000,
-    "use_cache": true,
-    "vocab_size": 151936
-  },
-  "tie_word_embeddings": false,
-  "transformers_version": "4.57.0.dev0",
-  "video_token_id": 151656,
-  "vision_config": {
-    "deepstack_visual_indexes": [
-      8,
-      16,
-      24
-    ],
-    "depth": 27,
-    "hidden_act": "gelu_pytorch_tanh",
-    "hidden_size": 1152,
-    "in_channels": 3,
-    "initializer_range": 0.02,
-    "intermediate_size": 4304,
-    "model_type": "qwen3_vl",
-    "num_heads": 16,
-    "num_position_embeddings": 2304,
-    "out_hidden_size": 5120,
-    "patch_size": 16,
-    "spatial_merge_size": 2,
-    "temporal_patch_size": 2
-  },
-  "vision_end_token_id": 151653,
-  "vision_start_token_id": 151652
-}

FL2VA/text_encoder/model-00001-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6b9dfbc930e505402ae9d7e5091a9d7d656cda5f34614f01cfe70bfb0cca27cb
-size 4932328944

FL2VA/text_encoder/model-00002-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d8bb44b4ff303fe76fe9e894022fb3dc71b15a2e716592790fe0e3c3e60478fa
-size 4875990528

FL2VA/text_encoder/model-00003-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:54f22e8b3168f8dc962fac0d313607ebf52a12b433d4cf3098a0d82d9f042940
-size 4875990552

FL2VA/text_encoder/model-00004-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad09c74d3c13ee29b5d0d84548fd8a3424a651564eaccd519946c296e59c557f
-size 4875990584

FL2VA/text_encoder/model-00005-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fc993c8a0e2a5b0570f383e1a95dc3a1281d1b224b6f3ee908f4827941e1dfc2
-size 4875990584

FL2VA/text_encoder/model-00006-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:82f05620d1f718a90c362b221d6a184ff1a0f53301d706882d3df49695fa1974
-size 4875990584

FL2VA/text_encoder/model-00007-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fb91da8cb01ff4de3eef0eab1c3e769a734b3a1aafc61734068638a0d6c86934
-size 4875990584

FL2VA/text_encoder/model-00008-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:431ca56535c8781944ce3801f5eb61c45531e853ecc5846d936ebaf4761b764f
-size 4875990584

FL2VA/text_encoder/model-00009-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3825e3f4302f4d2f7d76aa7430d2ce0864fde6b9e540a5806bf0d8e38e4d9f47
-size 4875990584

FL2VA/text_encoder/model-00010-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aded5a4d1d5e22dbd8b6f79266b6eb88c840411b09527c53917a1419ace22e2f
-size 4875990584

FL2VA/text_encoder/model-00011-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3820ffe8d8d6477f6fe8d614ef3c87abb264ee39accebf43a1507b970d80946f
-size 4875990584

FL2VA/text_encoder/model-00012-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:05ad2d08ce71963121c9b03f1d9ec5d7641052f4b23c6c12b80d71065eb8e98e
-size 4875990584

FL2VA/text_encoder/model-00013-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b64f2289871261fdd1abbd3b78bcd66011b341de3dc8eeb2ed1a473ee7c8d95c
-size 4875990584

FL2VA/text_encoder/model-00014-of-00014.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e45b6c9998c77ee5a6577f9f47bc76416c1d4d387169e50c4c9d3134ea51b13b
-size 3270697008

FL2VA/text_encoder/model.safetensors.index.json

@@ -1,1065 +0,0 @@
-{
-  "metadata": {
-    "total_size": 66714780128
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00014-of-00014.safetensors",
-    "model.language_model.embed_tokens.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.18.input_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
-    "model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.23.input_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
-    "model.language_model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
-    "model.language_model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
-    "model.language_model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.33.input_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
-    "model.language_model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.38.input_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
-    "model.language_model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
-    "model.language_model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
-    "model.language_model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.53.input_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.53.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
-    "model.language_model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.58.input_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.58.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
-    "model.language_model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.63.input_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
-    "model.language_model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
-    "model.language_model.layers.63.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
-    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
-    "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
-    "model.language_model.norm.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.0.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.1.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.10.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.11.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.12.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.13.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.14.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.15.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.16.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.17.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.18.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.19.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.2.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.20.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.21.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.22.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.23.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.24.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.25.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.26.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.3.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.4.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.5.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.6.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.7.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.8.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.attn.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.attn.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.attn.qkv.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.attn.qkv.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.norm1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.norm1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.norm2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.blocks.9.norm2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.0.norm.bias": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.0.norm.weight": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.1.norm.bias": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.1.norm.weight": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.2.norm.bias": "model-00014-of-00014.safetensors",
-    "model.visual.deepstack_merger_list.2.norm.weight": "model-00014-of-00014.safetensors",
-    "model.visual.merger.linear_fc1.bias": "model-00014-of-00014.safetensors",
-    "model.visual.merger.linear_fc1.weight": "model-00014-of-00014.safetensors",
-    "model.visual.merger.linear_fc2.bias": "model-00014-of-00014.safetensors",
-    "model.visual.merger.linear_fc2.weight": "model-00014-of-00014.safetensors",
-    "model.visual.merger.norm.bias": "model-00014-of-00014.safetensors",
-    "model.visual.merger.norm.weight": "model-00014-of-00014.safetensors",
-    "model.visual.patch_embed.proj.bias": "model-00014-of-00014.safetensors",
-    "model.visual.patch_embed.proj.weight": "model-00014-of-00014.safetensors",
-    "model.visual.pos_embed.weight": "model-00014-of-00014.safetensors"
-  }
-}

FL2VA/text_encoder/preprocessor_config.json

@@ -1,21 +0,0 @@
-{
-    "size": {
-        "longest_edge": 16777216,
-        "shortest_edge": 65536
-    },
-    "patch_size": 16,
-    "temporal_patch_size": 2,
-    "merge_size": 2,
-    "image_mean": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "image_std": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "processor_class": "Qwen3VLProcessor",
-    "image_processor_type": "Qwen2VLImageProcessorFast"
-}

FL2VA/text_encoder/tokenizer_config.json

@@ -1,246 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>",
-    "<d>",
-    "</d>",
-    "<|cutoff|>",
-    "<|lyrics_start|>",
-    "<|lyrics_end|>",
-    "<|caption_start|>",
-    "<|caption_end|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "model_max_length": 262144,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

FL2VA/text_encoder/video_preprocessor_config.json

@@ -1,21 +0,0 @@
-{
-    "size": {
-        "longest_edge": 25165824,
-        "shortest_edge": 4096
-    },
-    "patch_size": 16,
-    "temporal_patch_size": 2,
-    "merge_size": 2,
-    "image_mean": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "image_std": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "processor_class": "Qwen3VLProcessor",
-    "video_processor_type": "Qwen3VLVideoProcessor"
-}

FL2VA/tokenizer/tokenizer_config.json

@@ -1,246 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>",
-    "<d>",
-    "</d>",
-    "<|cutoff|>",
-    "<|lyrics_start|>",
-    "<|lyrics_end|>",
-    "<|caption_start|>",
-    "<|caption_end|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "model_max_length": 262144,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

FL2VA/transformer/config.json

@@ -1,27 +0,0 @@
-{
-  "_class_name": "MiniMaxH3DiTModel",
-  "_diffusers_version": "0.32.2",
-  "hidden_size": 5376,
-  "num_layers": 50,
-  "token_refiner_num_layers": 2,
-  "num_attention_heads": 56,
-  "attention_head_dim": 128,
-  "ffn_hidden_size": 14336,
-  "latents_dim": 24,
-  "audio_latents_dim": 32,
-  "patch_size": [
-    1,
-    2,
-    2
-  ],
-  "text_dim": 5120,
-  "timestep_input_dim": 256,
-  "time_embed_hidden_size": 5376,
-  "time_embed_dim": 2688,
-  "adaln_out_features": 96768,
-  "final_adaln_out_features": 10752,
-  "rope_inv_freq_len": 16,
-  "norm_eps": 1e-05,
-  "qk_norm_eps": 1e-05,
-  "final_norm_eps": 1e-05
-}

FL2VA/transformer/model-00001-of-00013.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0b3386565e476bfdea287e9ea9f269d036e5c649ed14bb9b4afac1dc4661bd2a
-size 5227812968