Phi-2 是一个小型语言模型，能够进行常识推理和语言理解。它在参数少于 130 亿的语言模型中 демонстрирует “最先进的性能”。

示例提示

默认情况下，phi 包含一个为多轮对话设计的聊天提示模板

% ollama run phi
>>> Hello, can you help me find my way to Toronto?
 Certainly! What is the exact location in Toronto that you are looking for?

>>> Yonge & Bloor
 Sure, Yonge and Bloor is a busy intersection in downtown Toronto. Would you like to take public transportation or drive there?

>>> Public transportation
 Great! The easiest way to get there is by taking the TTC subway. You can take Line 1, which runs along Yonge Street and passes through downtown Toronto.

使用 Ollama API

curl http://127.0.0.1:11434/api/chat -d '{
  "model": "phi",
  "messages": [
    { "role": "user", "content": "why is the sky blue?" }
  ]
}'

示例提示（原始模式）

当在 Ollama API 中使用 原始模式 时，Phi 也能很好地响应各种提示格式，这会绕过所有默认提示模板

指令

curl http://127.0.0.1:11434/api/generate -d '{
  "model": "phi",
  "prompt": "Instruct: Write a detailed analogy between mathematics and a lighthouse.\nOutput:",
  "options": {
    "stop": ["Instruct:", "Output:"]
  },
  "raw": true,
  "stream": false
}'

代码补全

curl http://127.0.0.1:11434/api/generate -d '{
  "model": "phi",
  "prompt": "def print_prime(n):\n  ",
  "raw": true,
  "stream": false
}'

文本补全

curl http://127.0.0.1:11434/api/generate -d '{
  "model": "phi",
  "prompt": "There once was a mouse named",
  "raw": true,
  "stream": false
}'

参考

HuggingFace

博客文章