Instructions to use DUTIR-BioNLP/RexDrug-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DUTIR-BioNLP/RexDrug-base with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DUTIR-BioNLP/RexDrug-base")
model = AutoModelForCausalLM.from_pretrained("DUTIR-BioNLP/RexDrug-base")
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 DUTIR-BioNLP/RexDrug-base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DUTIR-BioNLP/RexDrug-base

SGLang

How to use DUTIR-BioNLP/RexDrug-base 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 "DUTIR-BioNLP/RexDrug-base" \
    --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": "DUTIR-BioNLP/RexDrug-base",
		"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 "DUTIR-BioNLP/RexDrug-base" \
        --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": "DUTIR-BioNLP/RexDrug-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DUTIR-BioNLP/RexDrug-base with Docker Model Runner:
```
docker model run hf.co/DUTIR-BioNLP/RexDrug-base
```

Add paper link and improve model card metadata

by nielsr HF Staff - opened Mar 10

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+12

-7

nielsr

Mar 10

This PR improves the model card for RexDrug-base by:

Adding the pipeline_tag: text-generation metadata.
Linking the model to the original research paper: RexDrug: Reliable Multi-Drug Combination Extraction through Reasoning-Enhanced LLMs.
Including a link to the official GitHub repository for source code and data.

These changes help improve the discoverability of the model and provide users with the necessary context for its research application.

Add paper link and improve model card metadata8b717f7e

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment