Instructions to use QizhiPei/BioMatrix-4B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QizhiPei/BioMatrix-4B-Base with Transformers:

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

pipe = pipeline("text-generation", model="QizhiPei/BioMatrix-4B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QizhiPei/BioMatrix-4B-Base")
model = AutoModelForCausalLM.from_pretrained("QizhiPei/BioMatrix-4B-Base", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QizhiPei/BioMatrix-4B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QizhiPei/BioMatrix-4B-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": "QizhiPei/BioMatrix-4B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QizhiPei/BioMatrix-4B-Base

SGLang

How to use QizhiPei/BioMatrix-4B-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 "QizhiPei/BioMatrix-4B-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": "QizhiPei/BioMatrix-4B-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 "QizhiPei/BioMatrix-4B-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": "QizhiPei/BioMatrix-4B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QizhiPei/BioMatrix-4B-Base with Docker Model Runner:
```
docker model run hf.co/QizhiPei/BioMatrix-4B-Base
```

QizhiPei commited on Apr 28

Commit

128fcba

verified ·

1 Parent(s): cd73a83

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ tags:
 - foundation-model
 - pretrained
 pipeline_tag: text-generation
-base_model: Qwen/Qwen3-4B
 library_name: transformers
 ---
@@ -19,7 +19,7 @@ library_name: transformers
 **BioMatrix** is a multimodal biological foundation model that natively integrates **1D sequences**, **3D structures**, and **natural language** for both **molecules** and **proteins** within a single decoder-only architecture.
-This is the **4B-parameter Base model**, obtained via **multimodal continual pretraining** of Qwen3-4B on 304.4 billion tokens spanning text, molecular and protein 1D/3D data, and cross-modal corpora. This base checkpoint is intended for further fine-tuning on downstream tasks. For an instruction-tuned model ready for inference, see [BioMatrix-4B-SFT](https://huggingface.co/QizhiPei/BioMatrix-4B-SFT).
 - 📄 **Paper**: [BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language](https://arxiv.org/abs/xxxx.xxxxx)
 - 💻 **Code**: [https://github.com/QizhiPei/biomatrix](https://github.com/QizhiPei/biomatrix)
@@ -48,7 +48,7 @@ All modalities are consumed and produced uniformly under a **single next-token p
 ## Model Details
-- **Base Architecture**: Qwen3-4B
 - **Parameters**: 4B
 - **Training Stage**: Multimodal Continual Pretraining only (not instruction-tuned)
 - **Training Tokens**: 304.4B
@@ -158,4 +158,4 @@ If you find BioMatrix useful, please cite:
 ## License
-This model is released under the Apache 2.0 license. The base model (Qwen3-4B) is subject to its own license terms.

 - foundation-model
 - pretrained
 pipeline_tag: text-generation
+base_model: Qwen/Qwen3-4B-Base
 library_name: transformers
 ---
 **BioMatrix** is a multimodal biological foundation model that natively integrates **1D sequences**, **3D structures**, and **natural language** for both **molecules** and **proteins** within a single decoder-only architecture.
+This is the **4B-parameter Base model**, obtained via **multimodal continual pretraining** of Qwen3-4B-Base on 304.4 billion tokens spanning text, molecular and protein 1D/3D data, and cross-modal corpora. This base checkpoint is intended for further fine-tuning on downstream tasks. For an instruction-tuned model ready for inference, see [BioMatrix-4B-SFT](https://huggingface.co/QizhiPei/BioMatrix-4B-SFT).
 - 📄 **Paper**: [BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language](https://arxiv.org/abs/xxxx.xxxxx)
 - 💻 **Code**: [https://github.com/QizhiPei/biomatrix](https://github.com/QizhiPei/biomatrix)
 ## Model Details
+- **Base Architecture**: Qwen3-4B-Base
 - **Parameters**: 4B
 - **Training Stage**: Multimodal Continual Pretraining only (not instruction-tuned)
 - **Training Tokens**: 304.4B
 ## License
+This model is released under the Apache 2.0 license. The base model (Qwen3-4B-Base) is subject to its own license terms.