open-orca-platypus2:13b-q4_K_S

open-orca-platypus2

Open Orca OpenChat 模型和 Garage-bAInd Platypus 2 模型的合并版本。专为聊天和代码生成而设计。

13b

23.2K 下载量 Updated 15 个月前更新

17 个标签

15 个月前更新

15 个月前

f4de4beb0df0 · 7.4GB

{ "stop": [ "### Instruction:", "### Response:" ] }

45B

template

{{ .System }} ### Instruction: {{ .Prompt }} ### Response:

63B

Readme

OpenOrca Platypus2 模型是一个 130 亿参数的模型，它是 OpenOrca OpenChat 模型和 Garage-bAInd Platypus2-13B 模型的合并版本，这两个模型都是 Llama 2 模型的微调版本。它被设计为一个通用模型，可用于聊天、文本生成和代码生成。

开始使用 OpenOrca Platypus 2

下面示例中使用的模型是 OpenOrca Platypus 2 模型，具有 13b 参数，它是一个通用模型。

API

启动 Ollama 服务器 (运行 ollama serve)
运行模型

curl -X POST http://127.0.0.1:11434/api/generate -d '{
  "model": "open-orca-platypus2",
  "prompt":"Tell me a joke about ropes."
 }'

CLI

安装 Ollama
打开终端并运行 ollama run open-orca-platypus2

注意：如果模型尚未下载，ollama run 命令会执行 ollama pull。要在不运行模型的情况下下载模型，请使用 ollama pull open-orca-platypus2

内存要求

13b 模型通常至少需要 16GB 的 RAM

如果您在使用更高的量化级别时遇到问题，请尝试使用 q4 模型或关闭任何其他占用大量内存的程序。

模型变体

默认情况下，Ollama 使用 4 位量化。要尝试其他量化级别，请尝试其他标签。q 后面的数字表示用于量化的位数（即 q4 表示 4 位量化）。数字越高，模型越准确，但运行速度越慢，并且需要更多内存。

别名
latest, 13b, 13b-q4_0

模型来源

Ollama 上的 OpenOrca Platypus 2 来源

13b 参数来源: OpenOrca

参考

Platypus: Quick, Cheap, and Powerful Refinement of LLMs

The OpenOrca Platypus2 model is a 13 billion parameter model which is a merge of the OpenOrca OpenChat model and the Garage-bAInd Platypus2-13B model which are both fine tunings of the Llama 2 model. It is designed to be a general-use model that can be used for chat, text generation, and code generation.

## Get started with OpenOrca Platypus 2

The model used in the example below is the OpenOrca Platypus 2 model, with 13b parameters, which is a general-use model.

### API

1. Start Ollama server (Run `ollama serve`)
2. Run the model

```bash
curl -X POST http://127.0.0.1:11434/api/generate -d '{
  "model": "open-orca-platypus2",
  "prompt":"Tell me a joke about ropes."
 }'
  ```

### CLI

1. Install Ollama
2. Open the terminal and run `ollama run open-orca-platypus2`

Note: The `ollama run` command performs an `ollama pull` if the model is not already downloaded. To download the model without running it, use `ollama pull open-orca-platypus2`

## Memory requirements

- 13b models generally require at least 16GB of RAM

If you run into issues with higher quantization levels, try using the q4 model or shut down any other programs that are using a lot of memory.

## Model variants

By default, Ollama uses 4-bit quantization. To try other quantization levels, please try the other tags. The number after the q represents the number of bits used for quantization (i.e. q4 means 4-bit quantization). The higher the number, the more accurate the model is, but the slower it runs, and the more memory it requires.

| **Aliases** |
| --- |
| latest, 13b, 13b-q4_0 |

## Model source

**OpenOrca Platypus 2 source on Ollama**

13b parameters source:
 [OpenOrca](http://hugging-face.cn/Open-Orca/OpenOrca-Platypus2-13B)

## References

[Platypus: Quick, Cheap, and Powerful Refinement of LLMs](https://arxiv.org/abs/2308.07317 )

粘贴、拖放或点击上传图片 (.png, .jpeg, .jpg, .svg, .gif)