Instructions to use somosnlp/LLM_SQL_BaseDatosEspanol_Mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use somosnlp/LLM_SQL_BaseDatosEspanol_Mistral with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="somosnlp/LLM_SQL_BaseDatosEspanol_Mistral")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("somosnlp/LLM_SQL_BaseDatosEspanol_Mistral")
model = AutoModelForCausalLM.from_pretrained("somosnlp/LLM_SQL_BaseDatosEspanol_Mistral", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use somosnlp/LLM_SQL_BaseDatosEspanol_Mistral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "somosnlp/LLM_SQL_BaseDatosEspanol_Mistral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "somosnlp/LLM_SQL_BaseDatosEspanol_Mistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/somosnlp/LLM_SQL_BaseDatosEspanol_Mistral

SGLang

How to use somosnlp/LLM_SQL_BaseDatosEspanol_Mistral with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "somosnlp/LLM_SQL_BaseDatosEspanol_Mistral" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "somosnlp/LLM_SQL_BaseDatosEspanol_Mistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "somosnlp/LLM_SQL_BaseDatosEspanol_Mistral" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "somosnlp/LLM_SQL_BaseDatosEspanol_Mistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use somosnlp/LLM_SQL_BaseDatosEspanol_Mistral with Docker Model Runner:
```
docker model run hf.co/somosnlp/LLM_SQL_BaseDatosEspanol_Mistral
```

Asis41 commited on Apr 11, 2024

Commit

06fab6d

verified ·

1 Parent(s): a070d7f

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -16,7 +16,12 @@ diseñado específicamente para asistir en consultas de bases de datos utilizand
 En este proyecto se busco hacer fine-tuning a 2 modelos diferentes:
 - Mistral 7B
 - Code Llama
-Para ver cual arrojaba mejores resultados como base
 ## Uso

 En este proyecto se busco hacer fine-tuning a 2 modelos diferentes:
 - Mistral 7B
 - Code Llama
+Para ver cual arrojaba mejores resultados como base
+Esto con el fin de crear un modelo el cual una persona sin ningun conocimiento en base de datos pueda hacer consultas a una base de datos y que esta responda
+con el dato a pedir
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6529beddd78452c474eacc37/IKuxLT3JFnZyaPd1Hqccz.png)
 ## Uso