qwen-math-gpt4o-imitation

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

base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-1.5B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "v-vasi/qwen-math-gpt4o-imitation")

question = "Janet's ducks lay 16 eggs per day. She eats three for breakfast and bakes muffins with four. She sells the rest for $2 each. How much does she make daily?"

messages = [{"role": "user", "content": f"Solve step by step. End with the answer after '####'.\n\n{question}"}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

@article{cobbe2021gsm8k,
  title={Training Verifiers to Solve Math Word Problems},
  author={Cobbe, Karl and others},
  journal={arXiv preprint arXiv:2110.14168},
  year={2021}
}