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

Libraries

How to use delimi/Mistral_Legal with Transformers:

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

pipe = pipeline("text-generation", model="delimi/Mistral_Legal")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("delimi/Mistral_Legal")
model = AutoModelForMultimodalLM.from_pretrained("delimi/Mistral_Legal")
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 delimi/Mistral_Legal with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/delimi/Mistral_Legal

SGLang

How to use delimi/Mistral_Legal 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 "delimi/Mistral_Legal" \
    --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": "delimi/Mistral_Legal",
		"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 "delimi/Mistral_Legal" \
        --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": "delimi/Mistral_Legal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Mistral Legal - French Legal Document Generator

A specialized French legal document generation model based on Mistral-7B-Instruct-v0.3.

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load model
model = AutoModelForCausalLM.from_pretrained(
    "delimi/Mistral_Legal",
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("delimi/Mistral_Legal")

# Generate legal document
prompt = \"\"\"Génère une mise en demeure pour:
**Situation**: Loyer impayé
**Montant**: 1,500 euros
**Locataire**: M. Martin
**Délai**: 15 jours

Mise en demeure:\"\"\"

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(
    **inputs, 
    max_new_tokens=400, 
    temperature=0.7,
    do_sample=True,
    top_p=0.9
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Capabilities

Mise en demeure (formal demands)
Contracts (sales, rental, service agreements)
Legal clauses (confidentiality, liability, etc.)
Legal correspondence
Template generation

Performance

Training Loss: 1.142
Validation Loss: 1.082
Dataset: 541 French legal examples
Method: LoRA fine-tuning + merge

Legal Disclaimer

This model is for assistance purposes only. All generated content should be reviewed by qualified legal professionals before use.

Technical Details

Base: mistralai/Mistral-7B-Instruct-v0.3
Parameters: 7B
Language: French
Domain: Legal documents
License: Apache 2.0

Usage Examples

Mise en demeure

Génère une mise en demeure pour un loyer impayé de 2,400 euros depuis 3 mois.

Contract Generation

Rédige un contrat de vente pour une voiture Peugeot 208 au prix de 15,000 euros.

Legal Clauses

Crée une clause de confidentialité pour un accord commercial d'une durée de 2 ans.

Model created by AIAJ team - {datetime.now().strftime('%B %Y')}

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

F16

Model tree for delimi/Mistral_Legal

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3

Finetuned

(505)

this model

Evaluation results

ROUGE-1
self-reported

0.350