Instructions to use deep-div/MediLlama-3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deep-div/MediLlama-3.2 with Transformers:

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

pipe = pipeline("text-generation", model="deep-div/MediLlama-3.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deep-div/MediLlama-3.2")
model = AutoModelForCausalLM.from_pretrained("deep-div/MediLlama-3.2", device_map="auto")
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 deep-div/MediLlama-3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deep-div/MediLlama-3.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deep-div/MediLlama-3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deep-div/MediLlama-3.2

SGLang

How to use deep-div/MediLlama-3.2 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 "deep-div/MediLlama-3.2" \
    --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": "deep-div/MediLlama-3.2",
		"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 "deep-div/MediLlama-3.2" \
        --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": "deep-div/MediLlama-3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use deep-div/MediLlama-3.2 with Docker Model Runner:
```
docker model run hf.co/deep-div/MediLlama-3.2
```

MediLlama-3.2

Commit History

Adding `safetensors` variant of this model

4403e43
verified

SFconvertbot commited on May 16, 2025

Update README.md

e2bda88
verified

InferenceLab commited on May 16, 2025

Update README.md

01236ab
verified

InferenceLab commited on May 16, 2025

Update README.md

fa2af79
verified

InferenceLab commited on May 16, 2025

Update README.md

789c811
verified

InferenceLab commited on May 16, 2025

Trained with Unsloth

19e4b54
verified

InferenceLab commited on May 16, 2025

Upload tokenizer

084e2eb
verified

InferenceLab commited on May 16, 2025

initial commit

f9aae1c
verified

InferenceLab commited on May 16, 2025

Commit History

Adding `safetensors` variant of this model 4403e43 verified

Update README.md e2bda88 verified

Update README.md 01236ab verified

Update README.md fa2af79 verified

Update README.md 789c811 verified

Trained with Unsloth 19e4b54 verified

Upload tokenizer 084e2eb verified

initial commit f9aae1c verified

Adding `safetensors` variant of this model

4403e43
verified

Update README.md

e2bda88
verified

Update README.md

01236ab
verified

Update README.md

fa2af79
verified

Update README.md

789c811
verified

Trained with Unsloth

19e4b54
verified

Upload tokenizer

084e2eb
verified

initial commit

f9aae1c
verified