Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / deepseek-ai/DeepSeek-Coder issues and pull requests
#184 - Handle cases where a model does not repeat the function signature
Pull Request -
State: open - Opened by XZ-X 25 days ago
#183 - 对DeepSeek-Coder-V2-LIte sft之后输出会带上<|EOT|>然后一直打满
Issue -
State: open - Opened by SamuelScc about 1 month ago
#182 - is it still under development?
Issue -
State: open - Opened by nikhil-swamix about 1 month ago
#182 - is it still under development?
Issue -
State: open - Opened by nikhil-swamix about 1 month ago
#181 - I try Fine-tune DeepSeek-Coder
Issue -
State: closed - Opened by Siwakonrome 2 months ago
- 1 comment
#180 - 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)
Issue -
State: open - Opened by zhangyaoyue01 3 months ago
#179 - 6.7B模型量化失败,但是33B模型能够正常量化
Issue -
State: open - Opened by Soulscb 3 months ago
#178 - 6.7B
Issue -
State: closed - Opened by Soulscb 3 months ago
#177 - Function call sample code 需要更新下
Issue -
State: open - Opened by markshao 3 months ago
#175 - Problem in Math Evaluation
Issue -
State: open - Opened by chang-github-00 4 months ago
- 1 comment
#174 - dependency parsing code and deduplication script
Issue -
State: open - Opened by wentinghome 4 months ago
#173 - What is the correct padding side for train/eval of base model for FIM?
Issue -
State: open - Opened by zhzhangcc 5 months ago
#172 - 加载模型时出错
Issue -
State: closed - Opened by virt9 5 months ago
#171 - deepseek-coder-6.7b-base vuejs代码补全上存在一些问题
Issue -
State: open - Opened by godkun 5 months ago
#170 - Long Code Arena
Issue -
State: open - Opened by DifferentialityDevelopment 5 months ago
#170 - Long Code Arena
Issue -
State: open - Opened by DifferentialityDevelopment 5 months ago
#169 - Where is DeepSeek-Coder-V2?
Issue -
State: closed - Opened by RoacherM 6 months ago
#169 - Where is DeepSeek-Coder-V2?
Issue -
State: closed - Opened by RoacherM 6 months ago
#168 - RuntimeError: CUDA error: no kernel image is available for execution on the device
Issue -
State: closed - Opened by TobiMoelti 6 months ago
#168 - RuntimeError: CUDA error: no kernel image is available for execution on the device
Issue -
State: closed - Opened by TobiMoelti 6 months ago
#167 - 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?
Issue -
State: open - Opened by ZhiyuYUE 6 months ago
#167 - 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?
Issue -
State: open - Opened by ZhiyuYUE 6 months ago
#166 - Deepseekcoder 6 spitting out corrupt output for code generation question
Issue -
State: open - Opened by kodergeek 6 months ago
#166 - Deepseekcoder 6 spitting out corrupt output for code generation question
Issue -
State: open - Opened by kodergeek 6 months ago
#165 - 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?
Issue -
State: open - Opened by yucc-leon 6 months ago
#165 - 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?
Issue -
State: open - Opened by yucc-leon 6 months ago
#164 - 训练数据切分问题
Issue -
State: open - Opened by sm307 6 months ago
- 1 comment
#163 - Are EOS tokens masked during pre-training? If so, how does FIM mode know how to connect to the `text_after`?
Issue -
State: open - Opened by zhzhangcc 6 months ago
#163 - Are EOS tokens masked during pre-training? If so, how does FIM mode know how to connect to the `text_after`?
Issue -
State: open - Opened by zhzhangcc 6 months ago
#162 - Fix env name
Pull Request -
State: open - Opened by bigstomach 6 months ago
#162 - Fix env name
Pull Request -
State: open - Opened by bigstomach 6 months ago
#161 - 用vllm加速推理框架 推理速度还是很慢
Issue -
State: open - Opened by zhuzhiwei88 6 months ago
- 1 comment
#160 - 并发数目
Issue -
State: open - Opened by ChenVadder 7 months ago
#160 - 并发数目
Issue -
State: open - Opened by ChenVadder 7 months ago
#159 - 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
Issue -
State: open - Opened by aigc001 7 months ago
#158 - 使用vllm加速inference后输出容易不符合格式要求
Issue -
State: open - Opened by zhengrongz 7 months ago
#158 - 使用vllm加速inference后输出容易不符合格式要求
Issue -
State: open - Opened by zhengrongz 7 months ago
#157 - How to use fine-tuned model?
Issue -
State: open - Opened by aldialimucaj 8 months ago
- 3 comments
#156 - 本地部署怎么实现vscode自动代码补全?
Issue -
State: closed - Opened by lingyezhixing 8 months ago
- 1 comment
#155 - 微调完的模型,如何跟基础模型合并?
Issue -
State: open - Opened by libingbingd 8 months ago
- 1 comment
#154 - markdown格式的数据预训练
Issue -
State: open - Opened by huangqingyi-code 8 months ago
- 3 comments
#153 - 请问支持function call吗?支持在RAG中实现inline citations吗?
Issue -
State: closed - Opened by hiber-niu 8 months ago
#152 - What is the base context length of the model before extension to 16k?
Issue -
State: closed - Opened by Calvinnncy97 8 months ago
- 1 comment
#151 - Why generate "GGGGG...." ,when the input string is longer than a certain length in GGUF model?
Issue -
State: open - Opened by hzgdeerHo 8 months ago
- 3 comments
#150 - Does DeepSeek-Coder have wasm related knowledge?
Issue -
State: open - Opened by XinyuShe 8 months ago
- 1 comment
#148 - 使用react调用接口错误
Issue -
State: closed - Opened by trookie2000 8 months ago
#147 - clarification on the sentinel token format
Issue -
State: closed - Opened by Zane-XY 9 months ago
#146 - Are NTP and FIM 2 separate stages of training, or are they combined?
Issue -
State: closed - Opened by Calvinnncy97 9 months ago
- 4 comments
#145 - How can I do continue pretraining?
Issue -
State: open - Opened by hwaking 9 months ago
- 1 comment
#144 - Fail to fine-tune V1.5 model with custom llama script
Issue -
State: closed - Opened by lijierui 9 months ago
- 1 comment
#143 - Align Scheduler Configuration with Finetuning Script
Pull Request -
State: closed - Opened by richardodliu 9 months ago
#142 - 33B inference too slowly
Issue -
State: open - Opened by ZJXNEFU 9 months ago
- 1 comment
#141 - Leetcode数据集的构建脚本请问可以开源吗
Issue -
State: open - Opened by jzzzf 9 months ago
#140 - 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)
Issue -
State: closed - Opened by tongyuhome 9 months ago
- 1 comment
#139 - 如何构建微调的CoT数据
Issue -
State: open - Opened by wangqn1 9 months ago
- 1 comment
#138 - 33B AWQ量化+vLLM部署问题
Issue -
State: open - Opened by CarolXh 9 months ago
#137 - Trying to finetune DeepSeek-Coder on custom Dataset
Issue -
State: closed - Opened by A-Janj 9 months ago
- 13 comments
#136 - chat completion任务时输出大量<|EOT|> token
Issue -
State: closed - Opened by CarolXh 9 months ago
- 3 comments
#135 - Complete missing `import`
Pull Request -
State: closed - Opened by AntiQuality 9 months ago
#134 - Catastrophic forgetting problem
Issue -
State: open - Opened by shatealaboxiaowang 9 months ago
- 2 comments
#133 - 模型推理完成后怎么一直占用显存呢?
Issue -
State: open - Opened by chris-rong 9 months ago
- 2 comments
#132 - Pretraining code
Issue -
State: closed - Opened by Calvinnncy97 9 months ago
- 2 comments
#131 - Code to generate data
Issue -
State: open - Opened by tbressers 9 months ago
- 1 comment
#130 - Reproduce FIM Evaluation
Issue -
State: closed - Opened by Hambaobao 9 months ago
- 1 comment
#129 - deepseek-coder-7b-base-v1.5 tokenizer=LlamaTokenizerFast 为什么 分词会有很多乱码字符呢?
Issue -
State: open - Opened by zheng5yu9 9 months ago
- 1 comment
#128 - How is the amount of training data measured?
Issue -
State: open - Opened by WentaoChen0813 9 months ago
- 1 comment
#127 - Detailed version information of test programs in different languages.
Issue -
State: closed - Opened by Hambaobao 9 months ago
#126 - Undefined variable in `Evaluation/MBPP/human_eval/evaluation.py`
Issue -
State: closed - Opened by ya0guang 9 months ago
#125 - Question about training dataset
Issue -
State: open - Opened by TJ1999 9 months ago
#124 - tokenizer.json issue creating gguf files
Issue -
State: open - Opened by RonanKMcGovern 9 months ago
- 2 comments
#123 - Finetune of FIM
Issue -
State: open - Opened by shatealaboxiaowang 9 months ago
- 4 comments
#122 - Swift and Objective C?
Issue -
State: open - Opened by rlaferla 10 months ago
- 2 comments
#121 - How many tokens of code in pretraining
Issue -
State: closed - Opened by bigeagle 10 months ago
- 2 comments
#120 - fix in-page link for detailed eval results
Pull Request -
State: closed - Opened by JacobLinCool 10 months ago
#119 - Clarification Request on Discrepancies Between Appendix B and Section 4.1 Results
Issue -
State: closed - Opened by s-JoL 10 months ago
- 4 comments
#118 - eos_token_id for v1.5 model
Issue -
State: closed - Opened by G07cha 10 months ago
- 4 comments
#117 - TensorRT Quantization Breaks for `LlamaLinearScalingRotaryEmbedding`
Issue -
State: open - Opened by Sanger2000 10 months ago
#116 - Repository Level Code Completion format question
Issue -
State: closed - Opened by zch-cc 10 months ago
- 2 comments
#115 - Regex of HASDEPENDENCY in Dependency Parsing
Issue -
State: open - Opened by alex8937 10 months ago
- 1 comment
#114 - ERROR: ImportError: cannot import name 'SyncManager' from partially initialized module 'multiprocessing.managers' (most likely due to a circular import)
Issue -
State: open - Opened by kokolerk 10 months ago
- 3 comments
#113 - 预训练细节(fim)
Issue -
State: open - Opened by lightdf 10 months ago
- 3 comments
#112 - Please pass your input's `attention_mask` to obtain reliable results.
Issue -
State: closed - Opened by metero20000 10 months ago
- 1 comment
#111 - 微调后用代码中的evaluation做humaneval评测时报错Failed to extract code block with error `list index out of range`:
Issue -
State: closed - Opened by mst272 10 months ago
- 13 comments
#110 - 请问一下最新发布的7b-v1.5模型不支持中间补全吗
Issue -
State: closed - Opened by Reve1ations 10 months ago
- 9 comments
#109 - Update README.md
Pull Request -
State: closed - Opened by eltociear 10 months ago
#108 - Possible generation bug?
Issue -
State: open - Opened by kyesniper 10 months ago
- 2 comments
#107 - Construction of the FIM training data
Issue -
State: open - Opened by shatealaboxiaowang 10 months ago
- 4 comments
#106 - Training loss extremely noisy during fine-tuning and randomly goes to 0
Issue -
State: open - Opened by zpx01 10 months ago
- 1 comment
#105 - Update leetcode contest evaluation
Pull Request -
State: closed - Opened by DejianYang 10 months ago
#104 - HF chat-ui Prompt Template (DeepSeek Coder 6.7B)
Issue -
State: open - Opened by GANJAC 10 months ago
- 1 comment
#103 - 请问finetune脚本是全参微调么,最少需要多少显存和内存。
Issue -
State: open - Opened by juhengzhe 10 months ago
- 5 comments
#102 - inference with tensorrt_llm
Issue -
State: open - Opened by thanhtung901 10 months ago
- 9 comments
#101 - Update README.md
Pull Request -
State: open - Opened by timxx 10 months ago
#100 - 加载模型出现json错误
Issue -
State: closed - Opened by mst272 11 months ago
- 1 comment
#99 - How to extended window size during train step2?
Issue -
State: open - Opened by jiejie1993 11 months ago
- 2 comments
#98 - 不能把模型转化为gguf格式
Issue -
State: open - Opened by dotyuu 11 months ago
- 1 comment
#97 - The installed version of bitsandbytes was compiled without GPU support
Issue -
State: open - Opened by hs117 11 months ago
- 2 comments
#96 - Why is the size of the fine tuned model only a few hundred kb
Issue -
State: closed - Opened by vvvvk1 11 months ago
#95 - How to do code completion in Visual studio code?
Issue -
State: closed - Opened by vikasd22 11 months ago
- 1 comment
#94 - deepseek coder能够在base模型基础上继续与训练吗?
Issue -
State: open - Opened by EnderWu 11 months ago
- 2 comments