Phi-2 是一個小型語言模型，具備常識推理和語言理解能力。它展現了參數少於 130 億的語言模型中「最先進的效能」。

範例提示

預設情況下，phi 包含一個專為多回合對話設計的聊天提示範本

% 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 的 API

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

範例提示（原始模式）

當在 Ollama 的 API 中使用 原始模式 時，Phi 對於各種提示格式也有良好的回應，這會繞過所有預設提示範本

指示

curl http://localhost: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
}'

程式碼完成

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

文字完成

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

參考文獻

HuggingFace

部落格文章