# 安裝 Ollama
curl -fsSL <https://ollama.com/install.sh> | sh

# 拉取 Qwen2.5-Coder 模型
ollama pull qwen2.5-coder

# 創(chuàng)建自定義 Modelfile 用于特定配置
cat << EOF > Modelfile
FROM qwen2.5-coder

# 配置模型參數(shù)
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER repeat_penalty 1.1
PARAMETER context_length 32768

# 設(shè)置系統(tǒng)消息
SYSTEM "You are an expert programming assistant."
EOF

# 創(chuàng)建自定義模型
ollama create qwen2.5-coder-custom -f Modelfile

import requests
import json

class Qwen25Coder:
    def __init__(self, base_url="<http://localhost:11434>"):
        self.base_url = base_url
        self.api_generate = f"{base_url}/api/generate"

    def generate_code(self, prompt, model="qwen2.5-coder-custom"):
        payload = {
            "model": model,
            "prompt": prompt,
            "stream": False,
            "options": {
                "temperature": 0.7,
                "top_p": 0.9,
                "repeat_penalty": 1.1
            }
        }

        response = requests.post(self.api_generate, jsnotallow=payload)
        return response.json()["response"]

    def code_review(self, code):
        prompt = f"""審查以下代碼并提供詳細(xì)反饋：

        ```
        {code}
        ```

        請分析：
        1. 代碼質(zhì)量
        2. 潛在錯(cuò)誤
        3. 性能影響
        4. 安全考慮
        """

        return self.generate_code(prompt)

# 使用示例
coder = Qwen25Coder()

# 代碼補(bǔ)全示例
code_snippet = """
def calculate_fibonacci(n):
    if n <= 0:
        return []
    elif n == 1:
        return [0]
"""

completion = coder.generate_code(f"完成這個(gè)斐波那契數(shù)列函數(shù): {code_snippet}")

models:
  qwen2.5-coder:
    type: llama
    parameters:
      context_length: 32768
      num_gpu: 1
      num_thread: 8
      batch_size: 32
    quantization:
      mode: 'int8'
    cache:
      type: 'redis'
      capacity: '10gb'
    runtime:
      compute_type: 'float16'
      tensor_parallel: true

import time
import psutil
import logging
from dataclasses import dataclass
from typing import Optional

@dataclass
class PerformanceMetrics:
    inference_time: float
    memory_usage: float
    token_count: int
    success: bool
    error: Optional[str] = None

class Qwen25CoderMonitored(Qwen25Coder):
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.logger = logging.getLogger("qwen2.5-coder")

    def generate_code_with_metrics(self, prompt: str) -> tuple[str, PerformanceMetrics]:
        start_time = time.time()
        initial_memory = psutil.Process().memory_info().rss / 1024 / 1024

        try:
            response = self.generate_code(prompt)
            success = True
            error = None
        except Exception as e:
            response = ""
            success = False
            error = str(e)

        end_time = time.time()
        final_memory = psutil.Process().memory_info().rss / 1024 / 1024

        metrics = PerformanceMetrics(
            inference_time=end_time - start_time,
            memory_usage=final_memory - initial_memory,
            token_count=len(response.split()),
            success=success,
            error=error
        )

        self.logger.info(f"Performance metrics: {metrics}")
        return response, metrics