llama-SFT-GRPO

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# 加载模型和分词器
model_name = "zhman/llama-SFT-GRPO"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# 推理示例
def solve_math_problem(question):
    prompt = f"问题：{question}\n答案："
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    
    outputs = model.generate(
        **inputs,
        max_length=512,
        temperature=0.7,
        top_p=0.9,
        do_sample=True
    )
    
    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return answer

# 测试
result = solve_math_problem("2+2等于多少？")
print(result)

import requests

API_URL = "https://api-inference.huggingface.co/models/zhman/llama-SFT-GRPO"
headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

output = query({
    "inputs": "问题：3×5等于多少？",
    "parameters": {"max_length": 200, "temperature": 0.7}
})
print(output)

@misc{llama-math-tuned,
  author = {Your Name},
  title = {Llama Math Fine-tuned Model},
  year = {2026},
  publisher = {HuggingFace},
  url = {https://huggingface.co/zhman/llama-SFT-GRPO}
}