Instructions to use StanfordAIMI/CheXagent-2-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use StanfordAIMI/CheXagent-2-3b with Transformers:

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

pipe = pipeline("text-generation", model="StanfordAIMI/CheXagent-2-3b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("StanfordAIMI/CheXagent-2-3b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("StanfordAIMI/CheXagent-2-3b", trust_remote_code=True)
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 StanfordAIMI/CheXagent-2-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "StanfordAIMI/CheXagent-2-3b"
# 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/CheXagent-2-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/StanfordAIMI/CheXagent-2-3b

SGLang

How to use StanfordAIMI/CheXagent-2-3b 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/CheXagent-2-3b" \
    --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/CheXagent-2-3b",
		"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/CheXagent-2-3b" \
        --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/CheXagent-2-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use StanfordAIMI/CheXagent-2-3b with Docker Model Runner:
```
docker model run hf.co/StanfordAIMI/CheXagent-2-3b
```

Differences to 8b?

by dscarmo - opened Mar 14, 2025

Discussion

dscarmo

Mar 14, 2025

Hello!

Could you clarify the differences between this weight and the 8B version?
The model cards suggest a Chat template while the original 8B version is a pure image text prompt.

Thank you for the great work in CheXagent.

IAMJB

Stanford AIMI org Mar 14, 2025

The two models use different visual and textual backbone. You can check those configurations in their respective config.json files.
Chexagent-2-3b does in fact perform equally if not better than the 8b on some tasks. Chexagent-2-3b is also the model used and evaluated in our latest manuscript: https://arxiv.org/abs/2401.12208

IAMJB changed discussion status to closed Mar 14, 2025

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