Instructions to use EdwardYu/llama-2-7b-MedQuAD-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EdwardYu/llama-2-7b-MedQuAD-merged with Transformers:

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

pipe = pipeline("text-generation", model="EdwardYu/llama-2-7b-MedQuAD-merged")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EdwardYu/llama-2-7b-MedQuAD-merged")
model = AutoModelForCausalLM.from_pretrained("EdwardYu/llama-2-7b-MedQuAD-merged")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EdwardYu/llama-2-7b-MedQuAD-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EdwardYu/llama-2-7b-MedQuAD-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EdwardYu/llama-2-7b-MedQuAD-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EdwardYu/llama-2-7b-MedQuAD-merged

SGLang

How to use EdwardYu/llama-2-7b-MedQuAD-merged 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 "EdwardYu/llama-2-7b-MedQuAD-merged" \
    --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": "EdwardYu/llama-2-7b-MedQuAD-merged",
		"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 "EdwardYu/llama-2-7b-MedQuAD-merged" \
        --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": "EdwardYu/llama-2-7b-MedQuAD-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EdwardYu/llama-2-7b-MedQuAD-merged with Docker Model Runner:
```
docker model run hf.co/EdwardYu/llama-2-7b-MedQuAD-merged
```

This model is a merged model of meta Llama2 and EdwardYu/llama-2-7b-MedQuAD.

Usage

model_name = "EdwardYu/llama-2-7b-MedQuAD-merged"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    load_in_4bit=True,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    quantization_config=BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_compute_dtype=torch.bfloat16,
        bnb_4bit_use_double_quant=True,
        bnb_4bit_quant_type='nf4'
    ),
)

question = 'What are the side effects or risks of Glucagon?'
inputs = tokenizer(question, return_tensors="pt").to("cuda")
outputs = model.generate(inputs=inputs.input_ids, max_length=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

To run model inference faster, you can load in 16-bits without 4-bit quantization.

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter)

Downloads last month: 23

Safetensors

Model size

7B params

Tensor type

F32

BF16