issues
search
deepseek-ai
/
DeepSeek-Coder-V2
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
MIT License
1.14k
stars
58
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
What is the special token "<|completion|>" used for?
#24
yucc-leon
opened
3 days ago
0
deepseek-coder-v2在使用到一定次数后开始疯狂胡乱输出。
#23
DoiiarX
opened
6 days ago
1
Any changes on repo level concatenation?
#22
IQ179
opened
6 days ago
0
《开源大模型食用指南》sel-llm更新了DeepSeek-Coder-V2-Lite-Instruct模型的部署与微调教程!
#21
KMnO4-zx
opened
1 week ago
0
paper number not aligned
#20
lwaekfjlk
opened
1 week ago
0
When will the vllm PR be merged to the main branch?
#19
zuxin666
opened
1 week ago
3
Why DeepSeek-Coder-v2 236B is not trained with FIM objective?
#18
wasiahmad
opened
1 week ago
0
OutOfMemoryError: CUDA out of memory on RunPod
#17
loyal812
opened
1 week ago
0
Reward model in the reinforcement learning process
#16
bin123apple
opened
1 week ago
0
about basemodel choice
#15
han508
opened
1 week ago
0
Document tool calling capabilities
#14
goodov
opened
1 week ago
1
continue.dev autocomplete integration
#13
symph-antonio
opened
1 week ago
0
Model always responds in Chinese, ignores system prompts stating to only reply in English
#12
sammcj
closed
1 week ago
17
DeepSeek-Coder-V2-Lite model GPU/RAM requirement
#11
HashedViking
opened
1 week ago
3
How many tokens are generally trained in total?
#10
lengyueyang
opened
1 week ago
1
Model just solved RAS accounting problem correctly
#9
Priestru
closed
1 week ago
0
可以说明一下2024高考数学的评测方法和评测数据吗?
#8
Chenzongchao
opened
1 week ago
2
exponential normalization technique
#7
futuristx
opened
1 week ago
0
CanNot Finetune deepseek-coder-v2-lite via modeling_deepseek.py
#6
chencyudel
opened
1 week ago
7
Any plan to release the fintune example?
#5
SupercarryNg
opened
1 week ago
1
Any plans to release the 1B model as well?
#4
zuxin666
closed
1 week ago
1
How is the result on SWE-bench obtained?
#3
zkx06111
opened
1 week ago
1
Is the API pricing for the Deepseek v2 coder 230B model?
#2
Hangsiin
closed
1 week ago
3
Knowledge cutoff date
#1
JeroenAdam
opened
1 week ago
3