morvinp/medical-llama-lora-adapter

Medical Assistant LoRA Adapter

This is a LoRA (Low-Rank Adaptation) adapter for medical conversations, trained on the LLaMA-7B model.

Model Details

• Base Model: baffo32/decapoda-research-llama-7B-hf
• Adapter Type: LoRA
• LoRA Rank: 2
• LoRA Alpha: 4
• Target Modules: q_proj, v_proj
• Task: Medical Conversation Generation

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained("baffo32/decapoda-research-llama-7B-hf")
tokenizer = AutoTokenizer.from_pretrained("baffo32/decapoda-research-llama-7B-hf")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "morvinp/medical-llama-lora-adapter")

# Generate response
prompt = "What are the symptoms of flu?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Details

This adapter was trained using the following configuration:

• LoRA rank: 2
• LoRA alpha: 4
• LoRA dropout: 0.05
• Target modules: ["q_proj", "v_proj"]
• Training data: Medical dialogue dataset

Intended Use

• Medical conversation assistance
• Healthcare information queries
• Educational purposes in medical domain

Limitations

⚠️ Important Disclaimers:

• This model is for informational purposes only
• Should not replace professional medical advice
• Always consult healthcare professionals for medical decisions
• Not validated for clinical use

License

Apache 2.0

Citation

If you use this model, please cite:

@misc{medical-lora-adapter,
  title={Medical Assistant LoRA Adapter},
  author={Morvin},
  year={2025},
  url={https://huggingface.co/morvinp/medical-llama-lora-adapter}
}