ProtGPT3 Family
Collection
7 items • Updated • 5
Text Generation
Transformers
Safetensors
mixtral
biology
protein-language-model
protein-generation
causal-lm
mixture-of-experts
text-generation-inference
How to use from
SGLangUse 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 "AI4PD/ProtGPT3-10B" \
--host 0.0.0.0 \
--port 30000# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "AI4PD/ProtGPT3-10B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Model Card for ProtGPT3-1OB
Model Description
ProtGPT3-10B is a single-sequence autoregressive protein language model for protein sequence generation. It is the largest model in the ProtGPT3 family, an open-source suite of promptable and aligned protein language models ranging from 112M to 10B parameters. ProtGPT3 models use a causal Mixtral-style Mixture-of-Experts architecture and are trained for causal language modeling on protein sequences.
For more info and guidance on how to generate sequences with ProtGPT3-10B check out the extensive description provided in ProtGPT3-1.3B, just replacing the model name (i.e., model_name=AI4PD/ProtGPT3-10B).
Also consider using the ProtGPT3-10B-dpo version for an equivalent model size, but with improved sequence generation.
Out-of-Scope Use
The model should not be used as the sole basis for experimental, clinical, environmental, or safety-critical decisions. Generated proteins require downstream computational and experimental validation. The model is not guaranteed to generate functional, soluble, safe, or synthesizable proteins.
Bias, Risks, and Limitations
ProtGPT3-1OB learns from public protein sequence datasets and may reproduce biases present in those datasets. Generated sequences may be low-complexity, nonfunctional, unstable, insoluble, or biologically implausible. Protein generation models may also present dual-use risks if used irresponsibly.
Citation
BibTeX:
@article{garibbo2026protgpt3,
title={ProtGPT3: an Open-source family of Promptable and Aligned Protein Language Models},
author={Garibbo, Michele and Boxo Corominas, Gerard and Stocco, Filippo and Illanes Vicioso, Ramiro and Middendorf, Lasse and Ferruz, Noelia},
journal={bioRxiv},
pages={2026--06},
year={2026},
publisher={Cold Spring Harbor Laboratory}
}
More Information
For guidance on how to generate sequences with ProtGPT3-10B check out the extensive description provided in ProtGPT3-1.3B. All models and code are released through the Hugging Face ecosystem and accompanying code repository.
- Downloads last month
- 130
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "AI4PD/ProtGPT3-10B" \ --host 0.0.0.0 \ --port 30000# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AI4PD/ProtGPT3-10B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'