Instructions to use GreatCaptainNemo/ProLLaMA_Stage_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GreatCaptainNemo/ProLLaMA_Stage_1 with Transformers:

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

pipe = pipeline("text-generation", model="GreatCaptainNemo/ProLLaMA_Stage_1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GreatCaptainNemo/ProLLaMA_Stage_1")
model = AutoModelForCausalLM.from_pretrained("GreatCaptainNemo/ProLLaMA_Stage_1")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GreatCaptainNemo/ProLLaMA_Stage_1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GreatCaptainNemo/ProLLaMA_Stage_1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GreatCaptainNemo/ProLLaMA_Stage_1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GreatCaptainNemo/ProLLaMA_Stage_1

SGLang

How to use GreatCaptainNemo/ProLLaMA_Stage_1 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 "GreatCaptainNemo/ProLLaMA_Stage_1" \
    --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": "GreatCaptainNemo/ProLLaMA_Stage_1",
		"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 "GreatCaptainNemo/ProLLaMA_Stage_1" \
        --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": "GreatCaptainNemo/ProLLaMA_Stage_1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GreatCaptainNemo/ProLLaMA_Stage_1 with Docker Model Runner:
```
docker model run hf.co/GreatCaptainNemo/ProLLaMA_Stage_1
```

GreatCaptainNemo commited on May 14, 2024

Commit

1d7e28c

verified ·

1 Parent(s): f8407d3

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -3

README.md CHANGED Viewed

@@ -12,9 +12,6 @@ ProLLaMA_Stage_1 is based on Llama-2-7b, so please follow the license of Llama2.
 ```bash
 # you can replace the model_path with your local path
 CUDA_VISIBLE_DEVICES=0 python main.py --model "GreatCaptainNemo/ProLLaMA_Stage_1" --interactive
-# For example:
-# Input:Seq=
-# Then the model outputs:Seq=<xxxxxxxxxxxx>
 # main.py is as follows 👇:
 ```
@@ -110,4 +107,11 @@ if __name__ == '__main__':
             with open(args.output_file,'w') as f:
                 f.write("\n".join(outputs))
             print("All the outputs have been saved in",args.output_file)
 ```

 ```bash
 # you can replace the model_path with your local path
 CUDA_VISIBLE_DEVICES=0 python main.py --model "GreatCaptainNemo/ProLLaMA_Stage_1" --interactive
 # main.py is as follows 👇:
 ```
             with open(args.output_file,'w') as f:
                 f.write("\n".join(outputs))
             print("All the outputs have been saved in",args.output_file)
+```
+# Input format:
+```text
+Seq=
+#You can also specify the first few amino acids of the protein sequence:
+Seq=<MAPGGMPRE
 ```