impulse2000 / dolphincoder-starcoder2-7b

基于StarCoder2 7B的优秀编码性能，Dolphin模型家族的无审查版本。

227 拉取更新于4个月前

4个月前更新

4个月前

7c430080facc · 4.6GB

Readme

DolphinCoder StarCoder2 7b 🐬

由 latitude.sh 赞助。

加入我们的Discord！ https://discord.gg/cognitivecomputations

此模型基于StarCoder2-7b并遵循bigcode-openrail-m许可证。

这只海豚真的擅长编程，我使用了大量编程数据进行训练。

此模型未经审查。我已经过滤了数据集以去除对齐和偏差，这使得模型更加合规。建议在将模型作为服务公开之前实现自己的对齐层。它将对任何请求高度合规，甚至不道德的请求。请阅读我的关于未经审查模型的博客文章。 https://erichartford.com/uncensored-models
您应对使用此模型创建的任何内容负责。负责任地享受。

训练

使用qLoRA和Axolotl在8x L40S上训练3个时期花费了2天。

提示格式
此模型使用ChatML提示格式。

<|im_start|>system
You are DolphinCoder, a helpful AI programming assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

示例

<|im_start|>system
You are DolphinCoder, a master at software engineering and coding in any programming language.
<|im_start|>user
Please write me a program in golang that parses all the lines in a file, and reverses them character-wise, and saves it to a new file.
<|im_start|>assistant

量化模型

dagbs/-GGUF

感恩

这个模型的创建得益于 latitude.sh 的慷慨赞助。
欢迎微软回归开源AI！感谢你们提供的Orca-Math数据集！
对于训练和发布StarCoder2的权重表示衷心的感谢 BigCode！
对于数据集作者的深深感谢：@ise-uiuc, @teknium, @m-a-p
对@winglian和Axolotl贡献者制作最佳训练框架表示深深的感谢！
感谢开源AI社区中的所有人，他们在过程中教导了我，并帮助了我。

示例输出

如果您想经济上支持我的工作

周边产品

DolphinCoder StarCoder2 7b 🐬

sponsored by [latitude.sh](https://www.latitude.sh/).

Join our Discord! https://discord.gg/cognitivecomputations

This model is based on StarCoder2-7b and is subject to bigcode-openrail-m license.

This Dolphin is *really good* at coding, I trained with a lot of coding data.

This model is uncensored.  I have filtered the dataset to remove alignment and bias.  This makes the model more compliant.  You are advised to implement your own alignment layer before exposing the model as a service.  It will be highly compliant to any requests, even unethical ones.  Please read my blog post about uncensored models.  https://erichartford.com/uncensored-models
You are responsible for any content you create using this model.  Enjoy responsibly.

## Training
It took 2 days to train 3 epochs on 8x L40S's using qLoRA and Axolotl

Prompt format:
This model uses ChatML prompt format.
```
<|im_start|>system
You are DolphinCoder, a helpful AI programming assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

```

Example:
```
<|im_start|>system
You are DolphinCoder, a master at software engineering and coding in any programming language.
<|im_start|>user
Please write me a program in golang that parses all the lines in a file, and reverses them character-wise, and saves it to a new file.
<|im_start|>assistant
```

## Quantized models

- [dagbs/-GGUF](https://hugging-face.cn/dagbs/dolphincoder-starcoder2-7b-GGUF)

## Gratitude
- This model was made possible by the generous sponsorship of [latitude.sh](https://www.latitude.sh/).
- Welcome Microsoft to Open Source AI!  Thank you for the Orca-Math Dataset!
- Huge thank you to [BigCode](https://www.bigcode-project.org/) for training and publishing the weights of StarCoder2
- HUGE Thank you to the dataset authors: @ise-uiuc, @teknium, @m-a-p
- And HUGE thanks to @winglian and the Axolotl contributors for making the best training framework!
- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.

## Example Output

[If you would like to financially support my efforts](https://ko-fi.com/erichartford)

[swag](https://fa7113.myshopify.com/)

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)