orca2

Orca 2 由 Microsoft research 建構，並且是 Meta 的 Llama 2 模型的微調版本。此模型旨在於推理方面表現出色。

7b 13b

61.2K Pulls Updated 14 個月前

33 個標籤

更新於 14 個月前

14 個月前

ea98cc422de3 · 3.8GB

{ "num_ctx": 4096, "stop": [ "<|im_start", "<|im_end", "|im_start",

82B

模板

<|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assi

106B

系統

您是 Orca，一個由 Microsoft 創建的 AI 語言模型。您是一個謹慎的助手。您仔細地

215B

許可證

MICROSOFT RESEARCH LICENSE TERMS IF YOU LIVE IN THE UNITED STATES, PLEASE READ THE “BINDING ARBIT

11kB

說明文件

Orca 2 模型由 Microsoft Research 建構。它們在 Meta 的 Llama 2 上進行微調，使用合成資料集，該資料集旨在增強小型模型的推理能力。所有合成訓練資料均使用 Microsoft Azure 內容篩選器進行審核。

使用案例

Orca 2 是一個有用的助手，可在諸如推理給定資料、閱讀理解、數學問題解決和文本摘要等任務中提供答案。

此模型旨在於推理方面表現特別出色。

Microsoft Research 對此模型的預期目的是鼓勵進一步研究小型語言模型的開發、評估和對齊。

CLI

70 億參數模型

ollama run orca2

130 億參數模型

ollama run orca2:13b

API

範例

curl -X POST https://127.0.0.1:11434/api/generate -d '{
  "model": "orca2",
  "prompt":"Why is the sky blue?"
 }'

參考文獻

Microsoft Research 公告部落格
Microsoft Research 發表的論文，Orca 2: Teaching Small Language Models How to Reason

Orca 2 models are built by Microsoft Research. They are fine-tuned on Meta's Llama 2 using a synthetic dataset that was created to enhance the small model's reasoning abilities. All synthetic training data was moderated using Microsoft Azure content filters.

### Use case

Orca 2 is a helpful assistant, and provides an answer in tasks such as reasoning over your given data, reading comprehension, math problem solving and text summarization.

The model is designed to excel particularly in reasoning.

Microsoft Research's intended purpose for this model is to encourage further research on the development, evaluation, and alignment of smaller language models.

### CLI

7 billion parameter model:

```
ollama run orca2
```

13 billion parameter model:

```
ollama run orca2:13b
```

### API

Example:

```bash
curl -X POST https://127.0.0.1:11434/api/generate -d '{
  "model": "orca2",
  "prompt":"Why is the sky blue?"
 }'
```

### References

- [Microsoft Research announcement blog](https://www.microsoft.com/en-us/research/blog/orca-2-teaching-small-language-models-how-to-reason/)

- Microsoft Research published paper, [Orca 2: Teaching Small Language Models How to Reason](https://arxiv.org/pdf/2311.11045.pdf)

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