justjuu/qwen2.5-0.5b-chatdoctor-qlora-adapters

qwen2.5-0.5b-chatdoctor-qlora

This is a QLoRA fine-tuned adapter for Qwen/Qwen2.5-0.5B-Instruct trained on the ChatDoctor-HealthCareMagic-100k medical Q&A dataset.

Model Details

• Base Model: Qwen/Qwen2.5-0.5B-Instruct
• Fine-tuning Method: QLoRA (4-bit quantization + LoRA)
• Dataset: ChatDoctor-HealthCareMagic-100k
• Training Samples: 39,500
• Evaluation Samples: 500

LoRA Configuration

• Rank (r): 16
• Alpha: 32
• Dropout: 0.05
• Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Training Configuration

• Epochs: 1
• Batch Size: 4
• Gradient Accumulation Steps: 4
• Learning Rate: 0.0002
• Max Sequence Length: 512

Evaluation Results (ROUGE Metrics)

Metric	Score
ROUGE-1	0.2646
ROUGE-2	0.0485
ROUGE-L	0.1493

Usage

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

# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-0.5B-Instruct",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "justjuu/qwen2.5-0.5b-chatdoctor-qlora-adapters")

# Generate response
messages = [
    {"role": "system", "content": "You are a helpful medical assistant."},
    {"role": "user", "content": "What are the symptoms of diabetes?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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 Framework

• transformers: HuggingFace Transformers
• peft: Parameter-Efficient Fine-Tuning
• trl: Transformer Reinforcement Learning (SFTTrainer)
• bitsandbytes: 4-bit quantization

Disclaimer

This model is for educational and research purposes only. It should not be used as a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of a qualified healthcare provider.