nicholas-ugbala-hf/llama-3.2-3b-medical-finetuned

Llama 3.2 3B Medical Fine-Tuned

Llama 3.2 3B Instruct fine-tuned on a cleaned subset of ChatDoctor HealthCareMagic 100k for medical question answering.

Training Details

• Base model: meta-llama/Llama-3.2-3B-Instruct
• Fine-tuning method: LoRA (r=16, alpha=32)
• Dataset: nicholas-ugbala-hf/chatdoctor-cleaned-10k (4,937 train samples)
• Training: 1 epoch, 309 steps, ~73 minutes on T4 GPU
• Final eval loss: 2.495

How to Use

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

base = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.2-3B-Instruct",
    quantization_config=BitsAndBytesConfig(load_in_4bit=True),
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(
    "nicholas-ugbala-hf/llama-3.2-3b-medical-finetuned"
)
model = PeftModel.from_pretrained(
    base,
    "nicholas-ugbala-hf/llama-3.2-3b-medical-finetuned"
)

Part of

healthcare-llm-finetune