Instructions to use malhajar/meditron-70b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use malhajar/meditron-70b-chat with Transformers:

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

pipe = pipeline("text-generation", model="malhajar/meditron-70b-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("malhajar/meditron-70b-chat")
model = AutoModelForCausalLM.from_pretrained("malhajar/meditron-70b-chat")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use malhajar/meditron-70b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "malhajar/meditron-70b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "malhajar/meditron-70b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/malhajar/meditron-70b-chat

SGLang

How to use malhajar/meditron-70b-chat 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 "malhajar/meditron-70b-chat" \
    --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": "malhajar/meditron-70b-chat",
		"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 "malhajar/meditron-70b-chat" \
        --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": "malhajar/meditron-70b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use malhajar/meditron-70b-chat with Docker Model Runner:
```
docker model run hf.co/malhajar/meditron-70b-chat
```

Model Card for Model ID

meditron-7b-chat is a finetuned version of epfl-llm/meditron-70b using SFT Training on the Alpaca Dataset. This model can answer information about different excplicit ideas in medicine (see epfl-llm/meditron-70b for more info)

Model Description

Finetuned by: Mohamad Alhajar
Language(s) (NLP): English
Finetuned from model: epfl-llm/meditron-70b

Prompt Template

### Instruction:

<prompt> (without the <>)

### Response:

How to Get Started with the Model

Use the code sample provided in the original post to interact with the model.

from transformers import AutoTokenizer,AutoModelForCausalLM
 
model_id = "malhajar/meditron-70b-chat"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             torch_dtype=torch.float16,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_id)

question: "what is tract infection?"
# For generating a response
prompt = '''
### Instruction:
{question} 

### Response:'''
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
output = model.generate(inputs=input_ids,max_new_tokens=512,pad_token_id=tokenizer.eos_token_id,top_k=50, do_sample=True,
        top_p=0.95)
response = tokenizer.decode(output[0])

print(response)