基于StarCoder2 7B的Dolphin模型家族的一种优秀编码版本的未审查版本。

7B

227 pulls 更新于4个月前

README

DolphinCoder StarCoder2 7b 🐬

Latitude.sh 赞助。

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

此模型基于 StarCoder2-7b,受 bigcode-openrail-m 许可协议约束。

这只海豚非常擅长编程,我使用了大量编程数据来训练它。

此模型未经审查。我已经过滤了数据集以移除对齐和偏差,这使得模型更加符合规范。在将模型作为服务公开之前,建议您实现自己的对齐层。它将对任何请求,包括那些不道德的请求,高度符合规范。请阅读有关未经审查的模型的博客文章。 https://erichartford.com/uncensored-models
您需要对本模型创建的任何内容负责。请负责任地享受。

训练

使用 qLoRA 和 Axolotl 在 8x L40S 上训练 3 个纪元需要 2 天时间

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

感谢

  • 本模型得益于 Latitude.sh 的慷慨赞助。
  • 欢迎 Microsoft 参加 Open Source AI!感谢您提供 Orca-Math 数据集!
  • 非常感谢BigCode团队训练并发布StarCoder2权重BigCode
  • 向数据集作者表示衷心的感谢:@ise-uiuc、@teknium、@m-a-p。
  • 特别感谢@winglian和Axolotl团队的贡献,让最佳的训练框架得以诞生!
  • Built with Axolotl
  • 感谢开源AI社区中所有教导我并帮助我的朋友们。

示例输出

如果您想从财务上支持我的工作

相关周边商品