issues
search
deepseek-ai
/
DeepSeek-Coder
DeepSeek Coder: Let the Code Write Itself
https://coder.deepseek.com/
MIT License
6.61k
stars
461
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
I try Fine-tune DeepSeek-Coder
#181
Siwakonrome
closed
1 week ago
1
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
zhangyaoyue01
opened
3 weeks ago
0
6.7B模型量化失败,但是33B模型能够正常量化
#179
Soulscb
opened
1 month ago
0
6.7B
#178
Soulscb
closed
1 month ago
0
Function call sample code 需要更新下
#177
markshao
opened
1 month ago
0
Problem in Math Evaluation
#175
chang-github-00
opened
1 month ago
1
dependency parsing code and deduplication script
#174
wentinghome
opened
2 months ago
0
What is the correct padding side for train/eval of base model for FIM?
#173
zhzhangcc
opened
2 months ago
0
加载模型时出错
#172
virt9
closed
3 months ago
0
deepseek-coder-6.7b-base vuejs代码补全上存在一些问题
#171
godkun
opened
3 months ago
0
Long Code Arena
#170
DifferentialityDevelopment
opened
3 months ago
0
Where is DeepSeek-Coder-V2?
#169
RoacherM
closed
3 months ago
0
RuntimeError: CUDA error: no kernel image is available for execution on the device
#168
TobiMoelti
closed
3 months ago
0
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
ZhiyuYUE
opened
3 months ago
0
Deepseekcoder 6 spitting out corrupt output for code generation question
#166
kodergeek
opened
3 months ago
0
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
yucc-leon
opened
3 months ago
0
训练数据切分问题
#164
sm307
opened
4 months ago
1
Are EOS tokens masked during pre-training? If so, how does FIM mode know how to connect to the `text_after`?
#163
zhzhangcc
opened
4 months ago
0
Fix env name
#162
bigstomach
opened
4 months ago
0
用vllm加速推理框架 推理速度还是很慢
#161
zhuzhiwei88
opened
4 months ago
1
并发数目
#160
ChenVadder
opened
4 months ago
0
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
aigc001
opened
5 months ago
0
使用vllm加速inference后输出容易不符合格式要求
#158
zhengrongz
opened
5 months ago
0
How to use fine-tuned model?
#157
aldialimucaj
opened
5 months ago
3
本地部署怎么实现vscode自动代码补全?
#156
lingyezhixing
closed
5 months ago
1
微调完的模型,如何跟基础模型合并?
#155
libingbingd
opened
5 months ago
1
markdown格式的数据预训练
#154
huangqingyi-code
opened
5 months ago
3
请问支持function call吗?支持在RAG中实现inline citations吗?
#153
hiber-niu
closed
6 months ago
0
What is the base context length of the model before extension to 16k?
#152
Calvinnncy97
closed
6 months ago
1
Why generate "GGGGG...." ,when the input string is longer than a certain length in GGUF model?
#151
hzgdeerHo
opened
6 months ago
3
Does DeepSeek-Coder have wasm related knowledge?
#150
XinyuShe
opened
6 months ago
1
使用react调用接口错误
#148
trookie2000
closed
6 months ago
0
clarification on the sentinel token format
#147
Zane-XY
closed
5 months ago
0
Are NTP and FIM 2 separate stages of training, or are they combined?
#146
Calvinnncy97
closed
6 months ago
4
How can I do continue pretraining?
#145
hwaking
opened
6 months ago
1
Fail to fine-tune V1.5 model with custom llama script
#144
lijierui
closed
6 months ago
1
Align Scheduler Configuration with Finetuning Script
#143
richardodliu
opened
6 months ago
0
33B inference too slowly
#142
ZJXNEFU
opened
6 months ago
1
Leetcode数据集的构建脚本请问可以开源吗
#141
jzzzf
opened
6 months ago
0
官方提供的微调训练脚本是否支持33B模型训练?(及训练相关问题)
#140
tongyuhome
closed
5 months ago
1
如何构建微调的CoT数据
#139
wangqn1
opened
6 months ago
1
33B AWQ量化+vLLM部署问题
#138
CarolXh
opened
6 months ago
0
Trying to finetune DeepSeek-Coder on custom Dataset
#137
A-Janj
closed
6 months ago
13
chat completion任务时输出大量<|EOT|> token
#136
CarolXh
closed
6 months ago
3
Complete missing `import`
#135
AntiQuality
closed
6 months ago
0
Catastrophic forgetting problem
#134
shatealaboxiaowang
opened
6 months ago
2
模型推理完成后怎么一直占用显存呢?
#133
chris-rong
opened
7 months ago
2
Pretraining code
#132
Calvinnncy97
closed
6 months ago
2
Code to generate data
#131
tbressers
opened
7 months ago
1
Reproduce FIM Evaluation
#130
Hambaobao
opened
7 months ago
1
Next