Skip to content

Issues: deepseek-ai/DeepSeek-Coder

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

80 Open 80 Closed
80 Open 80 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

对DeepSeek-Coder-V2-LIte sft之后输出会带上<|EOT|>然后一直打满
#183 opened Oct 24, 2024 by SamuelScc
is it still under development?
#182 opened Oct 17, 2024 by nikhil-swamix
多卡执行微调脚本报错The server socket has failed to bind to [::]:29500 (errno: 98 - Address already in use)
#180 opened Sep 5, 2024 by zhangyaoyue01
6.7B模型量化失败，但是33B模型能够正常量化
#179 opened Aug 30, 2024 by Soulscb
Function call sample code 需要更新下
#177 opened Aug 30, 2024 by markshao
Problem in Math Evaluation
#175 opened Aug 5, 2024 by chang-github-00
1
dependency parsing code and deduplication script
#174 opened Jul 31, 2024 by wentinghome
What is the correct padding side for train/eval of base model for FIM?
#173 opened Jul 6, 2024 by zhzhangcc
deepseek-coder-6.7b-base vuejs代码补全上存在一些问题
#171 opened Jul 2, 2024 by godkun
Long Code Arena
#170 opened Jun 20, 2024 by DifferentialityDevelopment
为什么在进行一次训练加载后，会出现找不到显卡no slot的报错呢？
#167 opened Jun 14, 2024 by ZhiyuYUE
Deepseekcoder 6 spitting out corrupt output for code generation question
#166 opened Jun 11, 2024 by kodergeek
疑惑：为什么 base 模型的 tokenizer 词表中也有类似 <|Assistant|> 这样多用于 chat 模型的 special tokens？
#165 opened Jun 6, 2024 by yucc-leon
训练数据切分问题
#164 opened May 30, 2024 by sm307
1
Are EOS tokens masked during pre-training? If so, how does FIM mode know how to connect to the text_after?
#163 opened May 29, 2024 by zhzhangcc
用vllm加速推理框架 推理速度还是很慢
#161 opened May 20, 2024 by zhuzhiwei88
1
并发数目
#160 opened May 9, 2024 by ChenVadder
使用vllm加载33b-base或33b-instruct后，使用DS-1000、Program-Aided Math Reasoning (PAL)评估集进行评估，得分很低，与论文上的数据不符
#159 opened Apr 26, 2024 by aigc001
使用vllm加速inference后输出容易不符合格式要求
#158 opened Apr 25, 2024 by zhengrongz
How to use fine-tuned model?
#157 opened Apr 18, 2024 by aldialimucaj
3
微调完的模型，如何跟基础模型合并？
#155 opened Apr 16, 2024 by libingbingd
1
markdown格式的数据预训练
#154 opened Apr 15, 2024 by huangqingyi-code
3
Why generate "GGGGG...." ,when the input string is longer than a certain length in GGUF model?
#151 opened Mar 26, 2024 by hzgdeerHo
3
Does DeepSeek-Coder have wasm related knowledge?
#150 opened Mar 26, 2024 by XinyuShe
1
How can I do continue pretraining?
#145 opened Mar 18, 2024 by hwaking
1
ProTip! Mix and match filters to narrow down what you’re looking for.