Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / deepseek-ai/DeepSeek-Coder-V2 issues and pull requests

#53 - Clarification on Code Implementation in DeepSeek vs Llama

Issue - State: open - Opened by dog14230pp about 1 month ago

#52 - doc: recommend SGLang for DeepSeek Coder V2 inference

Pull Request - State: closed - Opened by Ying1123 about 2 months ago

#51 - 硬件的硬性要求

Issue - State: closed - Opened by walkchen9 about 2 months ago - 1 comment

#50 - ollama Model is configured wrong: Double BOS

Issue - State: open - Opened by Snowman-25 about 2 months ago - 1 comment

#50 - ollama Model is configured wrong: Double BOS

Issue - State: open - Opened by Snowman-25 about 2 months ago - 1 comment

#48 - Error: An unknown error was encountered while running the model

Issue - State: open - Opened by vishnunuk about 2 months ago - 1 comment

#48 - Error: An unknown error was encountered while running the model

Issue - State: open - Opened by vishnunuk about 2 months ago - 1 comment

#47 - Questions about exceeding Max_Token

Issue - State: closed - Opened by Hoyeon-Yu 2 months ago

#47 - Questions about exceeding Max_Token

Issue - State: closed - Opened by Hoyeon-Yu 2 months ago

#46 - details about the paper

Issue - State: open - Opened by Brucewuzhang 2 months ago

#46 - details about the paper

Issue - State: open - Opened by Brucewuzhang 2 months ago

#45 - File name char prefix used in training

Issue - State: open - Opened by valerybugakov 3 months ago

#45 - File name char prefix used in training

Issue - State: open - Opened by valerybugakov 3 months ago

#44 - add fine-tuning code with lora support

Pull Request - State: open - Opened by Muhtasham 3 months ago - 1 comment

#44 - add fine-tuning code with lora support

Pull Request - State: open - Opened by Muhtasham 3 months ago - 1 comment

#43 - issue bug

Issue - State: open - Opened by healerwhy 3 months ago

#43 - issue bug

Issue - State: open - Opened by healerwhy 3 months ago

#42 - 建议

Issue - State: open - Opened by Geek-Bob 3 months ago

#42 - 建议

Issue - State: open - Opened by Geek-Bob 3 months ago

#41 - Hi, I have a question about fine tuning.

Issue - State: open - Opened by Yindy07 3 months ago

#41 - Hi, I have a question about fine tuning.

Issue - State: open - Opened by Yindy07 3 months ago

#39 - How to evaluate on defects4j?

Issue - State: open - Opened by WentaoTan 3 months ago

#39 - How to evaluate on defects4j?

Issue - State: open - Opened by WentaoTan 3 months ago

#38 - dependency parsing code, deduplication script

Issue - State: open - Opened by wentinghome 3 months ago - 1 comment

#38 - dependency parsing code, deduplication script

Issue - State: open - Opened by wentinghome 3 months ago - 1 comment

#34 - VLLM推理报错 模型：DeepSeek-V2-Chat-0628

Issue - State: open - Opened by zhangfan-algo 4 months ago

#34 - VLLM推理报错 模型：DeepSeek-V2-Chat-0628

Issue - State: open - Opened by zhangfan-algo 4 months ago

#33 - 请问有考虑发布量化版本吗？

Issue - State: open - Opened by ybdesire 4 months ago - 1 comment

#33 - 请问有考虑发布量化版本吗？

Issue - State: open - Opened by ybdesire 4 months ago - 1 comment

#32 - 关于论文结果复现

Issue - State: closed - Opened by yingweima2022 4 months ago - 1 comment

#32 - 关于论文结果复现

Issue - State: closed - Opened by yingweima2022 4 months ago - 1 comment

#31 - reinforcement learning improvement

Issue - State: closed - Opened by Ski-ing 4 months ago - 2 comments

#31 - reinforcement learning improvement

Issue - State: closed - Opened by Ski-ing 4 months ago - 2 comments

#29 - Inference freezes using the recommended VLLM approach

Issue - State: closed - Opened by dhaneshsabane 4 months ago - 1 comment

#29 - Inference freezes using the recommended VLLM approach

Issue - State: closed - Opened by dhaneshsabane 4 months ago - 1 comment

#28 - Weird responses

Issue - State: open - Opened by EduardDoronin 4 months ago

#28 - Weird responses

Issue - State: open - Opened by EduardDoronin 4 months ago

#27 - FIM not working

Issue - State: open - Opened by gergap 4 months ago - 3 comments

#27 - FIM not working

Issue - State: open - Opened by gergap 4 months ago - 3 comments

#26 - Requirements for the DS-Coder-V2-Instruct

Issue - State: open - Opened by Urvesh71 4 months ago - 3 comments

#26 - Requirements for the DS-Coder-V2-Instruct

Issue - State: open - Opened by Urvesh71 4 months ago - 3 comments

#25 - mismatch between example code and model files

Issue - State: open - Opened by yucc-leon 4 months ago - 1 comment

#25 - mismatch between example code and model files

Issue - State: open - Opened by yucc-leon 4 months ago - 1 comment

#23 - deepseek-coder-v2在使用到一定次数后开始疯狂胡乱输出。

Issue - State: open - Opened by DoiiarX 5 months ago - 3 comments

#23 - deepseek-coder-v2在使用到一定次数后开始疯狂胡乱输出。

Issue - State: open - Opened by DoiiarX 5 months ago - 3 comments

#22 - Any changes on repo level concatenation?

Issue - State: open - Opened by IQ179 5 months ago - 13 comments

#22 - Any changes on repo level concatenation?

Issue - State: open - Opened by IQ179 5 months ago - 13 comments

#20 - paper number not aligned

Issue - State: open - Opened by lwaekfjlk 5 months ago

#20 - paper number not aligned

Issue - State: open - Opened by lwaekfjlk 5 months ago

#19 - When will the vllm PR be merged to the main branch?

Issue - State: open - Opened by zuxin666 5 months ago - 8 comments

#19 - When will the vllm PR be merged to the main branch?

Issue - State: open - Opened by zuxin666 5 months ago - 8 comments

#18 - Why DeepSeek-Coder-v2 236B is not trained with FIM objective?

Issue - State: open - Opened by wasiahmad 5 months ago - 3 comments

#18 - Why DeepSeek-Coder-v2 236B is not trained with FIM objective?

Issue - State: open - Opened by wasiahmad 5 months ago - 3 comments

#17 - OutOfMemoryError: CUDA out of memory on RunPod

Issue - State: open - Opened by loyal812 5 months ago - 1 comment

#17 - OutOfMemoryError: CUDA out of memory on RunPod

Issue - State: open - Opened by loyal812 5 months ago - 1 comment

#16 - Reward model in the reinforcement learning process

Issue - State: open - Opened by bin123apple 5 months ago

#16 - Reward model in the reinforcement learning process

Issue - State: open - Opened by bin123apple 5 months ago

#15 - about basemodel choice

Issue - State: open - Opened by han508 5 months ago

#15 - about basemodel choice

Issue - State: open - Opened by han508 5 months ago

#14 - Document tool calling capabilities

Issue - State: open - Opened by goodov 5 months ago - 1 comment

#14 - Document tool calling capabilities

Issue - State: open - Opened by goodov 5 months ago - 1 comment

#13 - continue.dev autocomplete integration

Issue - State: open - Opened by symph-antonio 5 months ago

#13 - continue.dev autocomplete integration

Issue - State: open - Opened by symph-antonio 5 months ago

#11 - DeepSeek-Coder-V2-Lite model GPU/RAM requirement

Issue - State: closed - Opened by HashedViking 5 months ago - 4 comments

#10 - How many tokens are generally trained in total?

Issue - State: closed - Opened by lengyueyang 5 months ago - 1 comment

#10 - How many tokens are generally trained in total?

Issue - State: closed - Opened by lengyueyang 5 months ago - 1 comment

#9 - Model just solved RAS accounting problem correctly

Issue - State: closed - Opened by Priestru 5 months ago

#8 - 可以说明一下2024高考数学的评测方法和评测数据吗？

Issue - State: closed - Opened by Chenzongchao 5 months ago - 2 comments

#7 - exponential normalization technique

Issue - State: open - Opened by futuristx 5 months ago

#7 - exponential normalization technique

Issue - State: open - Opened by futuristx 5 months ago

#6 - CanNot Finetune deepseek-coder-v2-lite via modeling_deepseek.py

Issue - State: closed - Opened by chencyudel 5 months ago - 8 comments

#5 - Any plan to release the fintune example?

Issue - State: open - Opened by SupercarryNg 5 months ago - 3 comments

#4 - Any plans to release the 1B model as well?

Issue - State: closed - Opened by zuxin666 5 months ago - 1 comment

#3 - How is the result on SWE-bench obtained?

Issue - State: closed - Opened by zkx06111 5 months ago - 1 comment

#2 - Is the API pricing for the Deepseek v2 coder 230B model?

Issue - State: closed - Opened by Hangsiin 5 months ago - 4 comments

#1 - Knowledge cutoff date

Issue - State: closed - Opened by JeroenAdam 5 months ago - 3 comments