phi - Ollama 框架

% 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 https://127.0.0.1:11434/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能良好回應，這會繞過所有預設的提示範本

指示

curl https://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
}'

程式碼完成

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

文字完成

curl https://127.0.0.1:11434/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

Phi-2 is a small language model capable of common-sense reasoning and language understanding. It showcases "state-of-the-art performance" among language models with less than 13 billion parameters.

### Example prompt

By default, `phi` includes a chat prompt template designed for multi-turn conversations:

```
% 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.
```

Using Ollama's API:

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

### Example prompts (raw mode)

Phi also responds well to a wide variety of prompt formats when using [raw mode](https://github.com/jmorganca/ollama/blob/main/docs/api.md#request-raw-mode) in Ollama's API, which bypasses all default prompt templating:

#### Instruct

```
curl https://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
}'
```

#### Code Completion

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

#### Text completion

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

## References

[HuggingFace](https://huggingface.co/microsoft/phi-2)

[Blog Post](https://www.microsoft.com/en-us/research/blog/phi-2-the-surprising-power-of-small-language-models/)

貼上、拖放或點擊以上傳圖片 (.png, .jpeg, .jpg, .svg, .gif)