DeepSeek MedQuAD LoRA Adapter

This repository contains a LoRA (PEFT) adapter fine-tuned for medical Q&A on the MedQuAD-style dataset.

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Usage

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

base_id = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
adapter_id = "prithvi1029/deepseek-medquad-lora"

tok = AutoTokenizer.from_pretrained(base_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base_id, device_map='auto', torch_dtype=torch.float16, trust_remote_code=True
)
model = PeftModel.from_pretrained(model, adapter_id)

prompt = "Question: What is diabetic retinopathy?\nAnswer:"
inputs = tok(prompt, return_tensors='pt').to(model.device)
out = model.generate(**inputs, max_new_tokens=128)
print(tok.decode(out[0], skip_special_tokens=True))

Disclaimer

This model is for research and educational purposes only and not medical advice.

Downloads last month: -; Downloads are not tracked for this model. How to track