Instructions to use halame/chatdoctor-llama3-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use halame/chatdoctor-llama3-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("./models/llama3-8b")
model = PeftModel.from_pretrained(base_model, "halame/chatdoctor-llama3-lora")

Transformers

How to use halame/chatdoctor-llama3-lora with Transformers:

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

pipe = pipeline("text-generation", model="halame/chatdoctor-llama3-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("halame/chatdoctor-llama3-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use halame/chatdoctor-llama3-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "halame/chatdoctor-llama3-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "halame/chatdoctor-llama3-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/halame/chatdoctor-llama3-lora

SGLang

How to use halame/chatdoctor-llama3-lora 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 "halame/chatdoctor-llama3-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "halame/chatdoctor-llama3-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "halame/chatdoctor-llama3-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "halame/chatdoctor-llama3-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use halame/chatdoctor-llama3-lora with Docker Model Runner:
```
docker model run hf.co/halame/chatdoctor-llama3-lora
```

ChatDoctor LLaMA-3 8B LoRA

A fine-tuned LoRA adapter for medical question answering, achieving BERTScore F1 = 0.845 (best result, exceeds original ChatDoctor paper).

Model Details

Base Model: NousResearch/Meta-Llama-3-8B-Instruct
Training Data: HealthCareMagic-100k (111,665 samples)
Training Time: 7h 46m on 2x A100 80GB
Final Loss: 1.886
Method: QLoRA (4-bit quantization)

Performance

Model	BERTScore P	BERTScore R	BERTScore F1
ChatDoctor (Paper)	0.844	0.845	0.841
Mistral + LoRA	0.845	0.843	0.844
LLaMA-3 + LoRA	0.844	0.846	0.845

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "NousResearch/Meta-Llama-3-8B-Instruct",
    torch_dtype=torch.float16,
    device_map="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "halame/chatdoctor-llama3-lora")
tokenizer = AutoTokenizer.from_pretrained("halame/chatdoctor-llama3-lora")

# Generate
prompt = "I have headache and fever for 2 days. What should I do?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Configuration

LoRA r: 16
LoRA alpha: 32
LoRA dropout: 0.05
Learning rate: 2e-4
Batch size: 64
Epochs: 1
Quantization: 4-bit (nf4)

License

Apache 2.0

Disclaimer

This model is for research purposes only. Do not use for actual medical diagnosis.

Downloads last month: 3

Model tree for halame/chatdoctor-llama3-lora

Base model

NousResearch/Meta-Llama-3-8B-Instruct

Adapter

(103)

this model

halame
/

chatdoctor-llama3-lora