Instructions to use Danielbrdz/Barcenas-8b-Juridico-Mexicano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Danielbrdz/Barcenas-8b-Juridico-Mexicano with Transformers:

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

pipe = pipeline("text-generation", model="Danielbrdz/Barcenas-8b-Juridico-Mexicano")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Danielbrdz/Barcenas-8b-Juridico-Mexicano")
model = AutoModelForCausalLM.from_pretrained("Danielbrdz/Barcenas-8b-Juridico-Mexicano")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Danielbrdz/Barcenas-8b-Juridico-Mexicano with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Danielbrdz/Barcenas-8b-Juridico-Mexicano"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Danielbrdz/Barcenas-8b-Juridico-Mexicano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Danielbrdz/Barcenas-8b-Juridico-Mexicano

SGLang

How to use Danielbrdz/Barcenas-8b-Juridico-Mexicano 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 "Danielbrdz/Barcenas-8b-Juridico-Mexicano" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Danielbrdz/Barcenas-8b-Juridico-Mexicano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Danielbrdz/Barcenas-8b-Juridico-Mexicano" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Danielbrdz/Barcenas-8b-Juridico-Mexicano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Danielbrdz/Barcenas-8b-Juridico-Mexicano with Docker Model Runner:
```
docker model run hf.co/Danielbrdz/Barcenas-8b-Juridico-Mexicano
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Barcenas 8b Juridico Mexicano

Modelo basado en el NousResearch/Meta-Llama-3.1-8B-Instruct y entrenado con datos de Danielbrdz/Barcenas-Juridico-Mexicano-Dataset

El objetivo de este LLM es promover el conocimiento jurídico mexicano y leyes de la SCJN.

El LLM puede responder cualquier duda de las leyes mexicanas, gracias que su dataset de entrenamiento contiene 50 documentos de la SCJN en forma QA.

Barcenas 8b Juridico Mexicano

Model based on the NousResearch/Meta-Llama-3.1-8B-Instruct and trained with data from Danielbrdz/Barcenas-Juridico-Mexicano-Dataset

The objective of this LLM is to promote Mexican legal knowledge and SCJN laws.

The LLM can answer any questions about Mexican law, thanks to its training dataset containing 50 SCJN documents in QA form.

Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

F16

Model tree for Danielbrdz/Barcenas-8b-Juridico-Mexicano

Adapters

1 model

Quantizations

1 model

Dataset used to train Danielbrdz/Barcenas-8b-Juridico-Mexicano

Collection including Danielbrdz/Barcenas-8b-Juridico-Mexicano

Barcenas Jurídico Mexicano

Collection

3 items • Updated Aug 8, 2024 • 1