Issues
- 4
Finetune of FIM
#123 opened by shatealaboxiaowang - 1
How to use fine-tuned model?
#157 opened by aldialimucaj - 1
本地部署怎么实现vscode自动代码补全?
#156 opened by lingyezhixing - 3
markdown格式的数据预训练
#154 opened by huangqingyi-code - 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 opened by aigc001 - 0
使用vllm加速inference后输出容易不符合格式要求
#158 opened by zhengrongz - 1
微调完的模型,如何跟基础模型合并?
#155 opened by libingbingd - 1
Does DeepSeek-Coder have wasm related knowledge?
#150 opened by XinyuShe - 0
clarification on the sentinel token format
#147 opened by Zane-XY - 1
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 opened by tongyuhome - 1
- 13
Trying to finetune DeepSeek-Coder on custom Dataset
#137 opened by A-Janj - 1
Why generate "GGGGG...." ,when the input string is longer than a certain length in GGUF model?
#151 opened by hzgdeerHo - 0
请问支持function call吗?支持在RAG中实现inline citations吗?
#153 opened by hiber-niu - 1
How can I do continue pretraining?
#145 opened by hwaking - 3
ERROR: ImportError: cannot import name 'SyncManager' from partially initialized module 'multiprocessing.managers' (most likely due to a circular import)
#114 opened by kokolerk - 4
- 1
- 13
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`:
#111 opened by mst272 - 0
使用react调用接口错误
#148 opened by trookie2000 - 2
tokenizer.json issue creating gguf files
#124 opened by RonanKMcGovern - 2
Catastrophic forgetting problem
#134 opened by shatealaboxiaowang - 3
预训练细节(fim)
#113 opened by lightdf - 1
- 1
33B inference too slowly
#142 opened by ZJXNEFU - 2
Pretraining code
#132 opened by Calvinnncy97 - 0
Leetcode数据集的构建脚本请问可以开源吗
#141 opened by jzzzf - 1
如何构建微调的CoT数据
#139 opened by wangqn1 - 0
33B AWQ量化+vLLM部署问题
#138 opened by CarolXh - 3
chat completion任务时输出大量<|EOT|> token
#136 opened by CarolXh - 1
How is the amount of training data measured?
#128 opened by WentaoChen0813 - 1
- 1
Code to generate data
#131 opened by tbressers - 1
模型推理完成后怎么一直占用显存呢?
#133 opened by chris-rong - 2
Repository Level Code Completion format question
#116 opened by zch-cc - 0
- 1
Reproduce FIM Evaluation
#130 opened by Hambaobao - 9
请问一下最新发布的7b-v1.5模型不支持中间补全吗
#110 opened by Reve1ations - 0
- 0
Question about training dataset
#125 opened by TJ1999 - 4
Clarification Request on Discrepancies Between Appendix B and Section 4.1 Results
#119 opened by s-JoL - 3
Construction of the FIM training data
#107 opened by shatealaboxiaowang - 2
How many tokens of code in pretraining
#121 opened by bigeagle - 1
Swift and Objective C?
#122 opened by rlaferla - 4
eos_token_id for v1.5 model
#118 opened by G07cha - 0
- 1
Regex of HASDEPENDENCY in Dependency Parsing
#115 opened by alex8937 - 1
- 2
Possible generation bug?
#108 opened by kyesniper - 0
HF chat-ui Prompt Template (DeepSeek Coder 6.7B)
#104 opened by GANJAC