Instructions to use AdaptLLM/medicine-LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdaptLLM/medicine-LLM with Transformers:

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

pipe = pipeline("text-generation", model="AdaptLLM/medicine-LLM")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/medicine-LLM")
model = AutoModelForCausalLM.from_pretrained("AdaptLLM/medicine-LLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AdaptLLM/medicine-LLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AdaptLLM/medicine-LLM

SGLang

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

Docker Model Runner
How to use AdaptLLM/medicine-LLM with Docker Model Runner:
```
docker model run hf.co/AdaptLLM/medicine-LLM
```

AdaptLLM commited on Jan 2, 2024

Commit

5564758

1 Parent(s): 849c7c9

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -45,8 +45,8 @@ For example, to chat with the biomedicine model:
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained("AdaptLLM/medicine-LLM-13B")
-tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/medicine-LLm-13B", use_fast=False)
 # Put your input here:
 user_input = '''Question: Which of the following is an example of monosomy?
@@ -58,8 +58,8 @@ Options:
 Please provide your choice first and then provide explanations if possible.'''
-# Simply use your input as the prompt
-prompt = user_input
 inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
 outputs = model.generate(input_ids=inputs, max_length=4096)[0]

 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("AdaptLLM/medicine-chat")
+tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/medicine-chat", use_fast=False)
 # Put your input here:
 user_input = '''Question: Which of the following is an example of monosomy?
 Please provide your choice first and then provide explanations if possible.'''
+# We use the prompt template of LLaMA-2-Chat demo
+prompt = f"<s>[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n{user_input} [/INST]"
 inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
 outputs = model.generate(input_ids=inputs, max_length=4096)[0]