Instructions to use hicai-zju/InstructProtein with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hicai-zju/InstructProtein with Transformers:

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

pipe = pipeline("text-generation", model="hicai-zju/InstructProtein")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hicai-zju/InstructProtein")
model = AutoModelForCausalLM.from_pretrained("hicai-zju/InstructProtein")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hicai-zju/InstructProtein with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hicai-zju/InstructProtein"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hicai-zju/InstructProtein",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hicai-zju/InstructProtein

SGLang

How to use hicai-zju/InstructProtein 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 "hicai-zju/InstructProtein" \
    --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": "hicai-zju/InstructProtein",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "hicai-zju/InstructProtein" \
        --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": "hicai-zju/InstructProtein",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hicai-zju/InstructProtein with Docker Model Runner:
```
docker model run hf.co/hicai-zju/InstructProtein
```

InstructProtein

InstructProtein is the first large generative language model exploring the feasibility of bidirectional generation between human and protein language. It is based on OPT-1.3B architecture with two-step training approach: It initiates with pre-training on protein and natural language corpora, followed by fine-tuning with the established protein knowledge instruction dataset. Through further instruction tuning, InstructProtein outperforms larger general-purpose foundation models on protein understanding and design tasks.

Limitations

The current model, developed through instruction tuning using knowledge instruction dataset, serves as a preliminary example. Despite its initial success in controlled environments, it lacks the robustness to manage complex, real-world, production-level tasks.

Reference

For more information, please take a look at our paper and repository.

Downloads last month: 11

Safetensors

Model size

1B params

Tensor type

F32

Paper for hicai-zju/InstructProtein

InstructProtein: Aligning Human and Protein Language via Knowledge Instruction

Paper • 2310.03269 • Published Oct 5, 2023