orca-mini

Orca Mini 是一個基於 Llama 和 Llama 2 模型訓練的模型，其訓練資料集 Orca Style 採用論文《Orca: Progressive Learning from Complex Explanation Traces of GPT-4》中定義的方法建立。目前有兩種版本。原始 Orca Mini 基於 Llama，提供 30 億、70 億和 130 億參數規模；v3 版本基於 Llama 2，提供 70 億、130 億和 700 億參數規模。

使用方式

CLI

開啟終端機並執行 ollama run orca-mini

API

範例

  curl -X POST https://127.0.0.1:11434/api/generate -d '{
    "model": "orca-mini",
    "prompt":"Why is the sky blue?"
   }'

記憶體需求

7b 模型通常至少需要 8GB RAM
13b 模型通常至少需要 16GB RAM
70b 模型通常至少需要 64GB RAM

參考資料

3b 參數原始來源：Pankaj Mathur

7b 參數原始來源：Pankaj Mathur

13b 參數原始來源：Pankaj Mathur

Ollama 上的 Orca Mini v3 來源

13b 參數原始來源：Pankaj Mathur

70b 參數來源：Pankaj Mathur

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Orca Mini is a Llama and Llama 2 model trained on Orca Style datasets created using the approaches defined in the paper, Orca: Progressive Learning from Complex Explanation Traces of GPT-4. There are two variations available. The original Orca Mini based on Llama in 3, 7, and 13 billion parameter sizes, and v3 based on Llama 2 in 7, 13, and 70 billion parameter sizes.

## Usage

### CLI

Open the terminal and run `ollama run orca-mini`

### API

Example:

```bash
  curl -X POST https://127.0.0.1:11434/api/generate -d '{
    "model": "orca-mini",
    "prompt":"Why is the sky blue?"
   }'
  ```

## Memory requirements

- 7b models generally require at least 8GB of RAM
- 13b models generally require at least 16GB of RAM
- 70b models generally require at least 64GB of RAM

## Reference

3b parameters original source:
 [Pankaj Mathur](https://huggingface.co/psmathur/orca_mini_3b)

7b parameters original source:
 [Pankaj Mathur](https://huggingface.co/psmathur/orca_mini_7b)

13b parameters original source:
 [Pankaj Mathur](https://huggingface.co/psmathur/orca_mini_13b)

**Orca Mini v3 source on Ollama**

13b parameters original source:
 [Pankaj Mathur](https://huggingface.co/psmathur/orca_mini_v3_13b)

70b parameters source:
 [Pankaj Mathur](https://huggingface.co/psmathur/orca_mini_v3_70b)

[Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://arxiv.org/abs/2306.02707 )

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