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

Libraries

How to use adriata/med_mistral with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adriata/med_mistral")
model = AutoModelForCausalLM.from_pretrained("adriata/med_mistral")
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

vLLM

How to use adriata/med_mistral with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/adriata/med_mistral

SGLang

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

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

Model Card for med_mistral

Model Details

Model Description

Model Mistral-7B-Instruct-v0.2 finetuned with QLoRA on multiple medical datasets.

4-bit version: med_mistral_4bit

License: apache-2.0
Finetuned from model : mistralai/Mistral-7B-Instruct-v0.2

Model Sources [optional]

Repository: https://github.com/atadria/med_llm

Uses

The model is finetuned on medical data and is intended only for research. It should not be used as a substitute for professional medical advice, diagnosis, or treatment.

Bias, Risks, and Limitations

The model's predictions are based on the information available in the finetuned medical dataset. It may not generalize well to all medical conditions or diverse patient populations.

Sensitivity to variations in input data and potential biases present in the training data may impact the model's performance.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

# !pip install -q transformers accelerate bitsandbytes

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adriata/med_mistral")
model = AutoModelForCausalLM.from_pretrained("adriata/med_mistral")

prompt_template = """<s>[INST] {prompt} [/INST]"""

prompt = "What is influenza?"

model_inputs = tokenizer.encode(prompt_template.format(prompt=prompt),
                                return_tensors="pt").to("cuda")

generated_ids = model.generate(model_inputs, max_new_tokens=512, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Training Details

~13h - 20k examples x 1 epoch

GPU: OVH - 1 × NVIDIA TESLA V100S (32 GiB RAM)

Training Data

Training data included 20k examples randomly selected from datasets:

pubmed
bigbio/czi_drsm
bigbio/bc5cdr
bigbio/distemist
pubmed_qa
medmcqa

Downloads last month: 7

Safetensors

Model size

7B params

Tensor type

F32

Datasets used to train adriata/med_mistral

Collection including adriata/med_mistral

med-mistral-v0.1

Collection

4 items • Updated Mar 2