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

Files changed (1) hide show

README.md +12 -7

README.md CHANGED Viewed

@@ -1,19 +1,24 @@
 ---
-license: llama3.1
 base_model: meta-llama/Llama-3.1-8B-Instruct
 library_name: transformers
 tags:
-  - drug-combination
-  - relation-extraction
-  - biomedical
-  - llama
-  - chain-of-thought
 ---
 # RexDrug-Base
 This is the SFT (Supervised Fine-Tuning) base model for **RexDrug**, a chain-of-thought reasoning model for biomedical drug combination relation extraction.
 ## Model Details
 - **Base architecture**: [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
@@ -40,4 +45,4 @@ model = PeftModel.from_pretrained(model, "dlutIR/RexDrug-adapter")
 ## License
-This model is built upon Llama 3.1 and is subject to the [Llama 3.1 Community License Agreement](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE).

 ---
 base_model: meta-llama/Llama-3.1-8B-Instruct
 library_name: transformers
+license: llama3.1
+pipeline_tag: text-generation
 tags:
+- drug-combination
+- relation-extraction
+- biomedical
+- llama
+- chain-of-thought
 ---
 # RexDrug-Base
 This is the SFT (Supervised Fine-Tuning) base model for **RexDrug**, a chain-of-thought reasoning model for biomedical drug combination relation extraction.
+For more details, please refer to the paper: [RexDrug: Reliable Multi-Drug Combination Extraction through Reasoning-Enhanced LLMs](https://huggingface.co/papers/2603.08166).
+**Official Code:** [DUTIR-BioNLP/RexDrug](https://github.com/DUTIR-BioNLP/RexDrug)
 ## Model Details
 - **Base architecture**: [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
 ## License
+This model is built upon Llama 3.1 and is subject to the [Llama 3.1 Community License Agreement](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE).