| --- |
| tags: |
| - uv-script |
| - text-classification |
| - hf-jobs |
| base_model: LiquidAI/LFM2.5-Encoder-350M |
| datasets: |
| - davanstrien/dataset-rows16-with-task-categories |
| pipeline_tag: text-classification |
| library_name: transformers |
| --- |
| |
| # dataset-rows16-task-classifier-4096 |
|
|
| [LiquidAI/LFM2.5-Encoder-350M](https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M) fine-tuned for |
| multi-label text classification on |
| [davanstrien/dataset-rows16-with-task-categories](https://huggingface.co/datasets/davanstrien/dataset-rows16-with-task-categories). |
|
|
| - **Labels (35)**: `audio-classification`, `audio-to-audio`, `automatic-speech-recognition`, `feature-extraction`, `fill-mask`, `image-classification`, `image-feature-extraction`, `image-segmentation`, `image-text-to-text`, `image-to-3d`, `image-to-image`, `image-to-text`, `multiple-choice`, `object-detection`, `question-answering`, `reinforcement-learning`, `robotics`, `sentence-similarity`, `summarization`, `table-question-answering`, `tabular-classification`, `tabular-regression`, `text-classification`, `text-generation`, `text-retrieval`, `text-to-image`, `text-to-speech`, `text-to-video`, `time-series-forecasting`, `token-classification`, … (35 total) |
| - **Date**: 2026-07-30 09:39 UTC |
|
|
| > [!NOTE] |
| > This model uses a custom classification head (mean pooling over a backbone without a native sequence-classification class), so loading requires `trust_remote_code=True`. vLLM serving requires a standard architecture. |
|
|
| ## Evaluation |
|
|
| | Metric | Value | |
| |--------|-------| |
| | f1_micro @ 0.5 | 0.6343 | |
| | f1_macro @ 0.5 | 0.4691 | |
| | f1_micro @ tuned | 0.6464 | |
| | f1_macro @ tuned | 0.5545 | |
|
|
| Per-label decision thresholds tuned on the eval split are stored in |
| `config.classifier_thresholds`. |
|
|
| **Choosing an operating point**: the stored thresholds maximise per-label F1. For |
| precision-first use (e.g. auto-applying labels), act only on predictions well above |
| their threshold — sigmoid probabilities are a usable confidence signal, and filtering |
| to high-confidence predictions trades coverage for precision. Route the rest to review. |
|
|
| ## Usage |
|
|
| ```python |
| import torch |
| from transformers import AutoModelForSequenceClassification, AutoTokenizer |
| |
| model = AutoModelForSequenceClassification.from_pretrained("davanstrien/dataset-rows16-task-classifier-4096", trust_remote_code=True) |
| tokenizer = AutoTokenizer.from_pretrained("davanstrien/dataset-rows16-task-classifier-4096", trust_remote_code=True) |
| |
| inputs = tokenizer("your text here", return_tensors="pt", truncation=True) |
| probs = torch.sigmoid(model(**inputs).logits)[0] |
| thresholds = torch.tensor(model.config.classifier_thresholds) # tuned on validation |
| labels = [model.config.id2label[i] for i in (probs >= thresholds).nonzero().flatten().tolist()] |
| print(labels) |
| ``` |
|
|
| ## Reproduction |
|
|
| Produced on [Hugging Face Jobs](https://huggingface.co/docs/huggingface_hub/guides/jobs) (`gpu`) with the [`train-classifier.py`](https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-classifier.py) recipe from [uv-scripts](https://huggingface.co/uv-scripts). Run it yourself: |
|
|
| ```bash |
| hf jobs uv run --flavor gpu --secrets HF_TOKEN \ |
| https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-classifier.py \ |
| davanstrien/dataset-rows16-with-task-categories davanstrien/dataset-rows16-task-classifier-4096 --label-column labels |
| ``` |
|
|
