Instructions to use StanfordAIMI/RadLLaMA-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use StanfordAIMI/RadLLaMA-7b with Transformers:

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

pipe = pipeline("text-generation", model="StanfordAIMI/RadLLaMA-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("StanfordAIMI/RadLLaMA-7b")
model = AutoModelForMultimodalLM.from_pretrained("StanfordAIMI/RadLLaMA-7b")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use StanfordAIMI/RadLLaMA-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "StanfordAIMI/RadLLaMA-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "StanfordAIMI/RadLLaMA-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/StanfordAIMI/RadLLaMA-7b

SGLang

How to use StanfordAIMI/RadLLaMA-7b 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 "StanfordAIMI/RadLLaMA-7b" \
    --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": "StanfordAIMI/RadLLaMA-7b",
		"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 "StanfordAIMI/RadLLaMA-7b" \
        --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": "StanfordAIMI/RadLLaMA-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use StanfordAIMI/RadLLaMA-7b with Docker Model Runner:
```
docker model run hf.co/StanfordAIMI/RadLLaMA-7b
```

AIMI FMs: A Collection of Foundation Models in Radiology

📝 Paper • 🤗 Hugging Face • 🧩 Github • 🪄 Project

✨ Latest News

[01/20/2023]: Model released in Hugging Face.

🎬 Get Started

from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("StanfordAIMI/RadLLaMA-7b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("StanfordAIMI/RadLLaMA-7b")

prompt = "Hi"
conv = [{"from": "human", "value": prompt}]
input_ids = tokenizer.apply_chat_template(conv, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(input_ids)
response = tokenizer.decode(outputs[0])
print(response)

✏️ Citation

@article{aimifms-2024,
  title={},
  author={},
  journal={arXiv preprint arXiv:xxxx.xxxxx},
  url={https://arxiv.org/abs/xxxx.xxxxx},
  year={2024}
}

Downloads last month: 2,136

Safetensors

Model size

7B params

Tensor type

F32

Model tree for StanfordAIMI/RadLLaMA-7b

Finetunes

1 model