Instructions to use pucpr-br/Clinical-BR-Mistral-7B-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pucpr-br/Clinical-BR-Mistral-7B-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="pucpr-br/Clinical-BR-Mistral-7B-v0.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pucpr-br/Clinical-BR-Mistral-7B-v0.2")
model = AutoModelForCausalLM.from_pretrained("pucpr-br/Clinical-BR-Mistral-7B-v0.2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pucpr-br/Clinical-BR-Mistral-7B-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pucpr-br/Clinical-BR-Mistral-7B-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pucpr-br/Clinical-BR-Mistral-7B-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pucpr-br/Clinical-BR-Mistral-7B-v0.2

SGLang

How to use pucpr-br/Clinical-BR-Mistral-7B-v0.2 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 "pucpr-br/Clinical-BR-Mistral-7B-v0.2" \
    --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": "pucpr-br/Clinical-BR-Mistral-7B-v0.2",
		"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 "pucpr-br/Clinical-BR-Mistral-7B-v0.2" \
        --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": "pucpr-br/Clinical-BR-Mistral-7B-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pucpr-br/Clinical-BR-Mistral-7B-v0.2 with Docker Model Runner:
```
docker model run hf.co/pucpr-br/Clinical-BR-Mistral-7B-v0.2
```

Technical question: Lineage of pucpr-br/Clinical-BR-Mistral-7B-v0.2

by dqdw - opened Mar 8

Discussion

dqdw

Mar 8

Dear [Developer/Team],

I really appreciate your work on pucpr-br/Clinical-BR-Mistral-7B-v0.2. I've been using it recently and it's been very helpful.

Since I plan to extend this model, I want to confirm how it relates to mistralai/Mistral-7B-v0.3 according to Hugging Face:

Direct Fine-tuning: Is pucpr-br/Clinical-BR-Mistral-7B-v0.2 a direct fine-tuned version of mistralai/Mistral-7B-v0.3, or were there intermediate models/checkpoints involved?

Inheritance: Is it fully compatible with the mistralai/Mistral-7B-v0.3 architecture?

I just want to make sure I'm using it the right way.

Appreciate your support!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment