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

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))