Instructions to use PharMolix/BioMedGPT-LM-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PharMolix/BioMedGPT-LM-7B with Transformers:

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

pipe = pipeline("text-generation", model="PharMolix/BioMedGPT-LM-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PharMolix/BioMedGPT-LM-7B")
model = AutoModelForCausalLM.from_pretrained("PharMolix/BioMedGPT-LM-7B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PharMolix/BioMedGPT-LM-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PharMolix/BioMedGPT-LM-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PharMolix/BioMedGPT-LM-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PharMolix/BioMedGPT-LM-7B

SGLang

How to use PharMolix/BioMedGPT-LM-7B 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 "PharMolix/BioMedGPT-LM-7B" \
    --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": "PharMolix/BioMedGPT-LM-7B",
		"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 "PharMolix/BioMedGPT-LM-7B" \
        --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": "PharMolix/BioMedGPT-LM-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PharMolix/BioMedGPT-LM-7B with Docker Model Runner:
```
docker model run hf.co/PharMolix/BioMedGPT-LM-7B
```

youngking0727 commited on Aug 12, 2023

Commit

3e29d41

1 Parent(s): 722991b

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -45,7 +45,7 @@ ical data modalities via a single GPT model. BioMedGPT aligns different biologic
 |------------------------|----------------|-----------|-------------|--------------|
 | Human (pass)*          |        -       |  Manual   | -           | 60.0         |
 | Human (expert)*        |        -       |  Manual   | 90          | 78.0         |
-|------------------------|:---------------|-----------|-------------|--------------|
 | InstructGPT*           | 175            | zero-shot | 44.0        | 73.2         |
 | ChatGPT*               | -              | zero-shot | 44.7        | 63.9         |
 | Llama*                 | 7              | zero-shot | 24.3        | 5.2          |

 |------------------------|----------------|-----------|-------------|--------------|
 | Human (pass)*          |        -       |  Manual   | -           | 60.0         |
 | Human (expert)*        |        -       |  Manual   | 90          | 78.0         |
+|------------------------|----------------|-----------|-------------|--------------|
 | InstructGPT*           | 175            | zero-shot | 44.0        | 73.2         |
 | ChatGPT*               | -              | zero-shot | 44.7        | 63.9         |
 | Llama*                 | 7              | zero-shot | 24.3        | 5.2          |