deepseek-ai/DeepSeek-LLM

Issues

• 一个账户创建了五十个api，但一个api没问题，但多了会报错 处理时发生未知错误: Connection error

  #49 opened 2 months ago by wanglu2014
  0

• 关于System Prompt

  #28 opened a year ago by DirtyKnightForVi
  5

• Is the compute calculation wrong for Chinchilla in the paper?

  #48 opened 8 months ago by yzlnew
  1

• 贵团队是否会升级长上下文的版本？

  #47 opened 9 months ago by edisonzf2020
  1

• Humaneval, use base model or instruct finetuned model?

  #46 opened 9 months ago by jasonzliang
  1

• 关于模型指标有一些疑问

  #45 opened 9 months ago by MangoFF
  1

• TriviaQA结果复现求助

  #33 opened a year ago by HYZ17
  4

• Deepseek VL?

  #44 opened 9 months ago by IdiotSandwichTheThird
  1

• Could you please release intermediate pretraining checkpoints at HuggingFace?

  #43 opened 9 months ago by Yangjinluan
  0

• Deepseek SFT数据包含system应该如何处理？

  #41 opened 10 months ago by xiatingyu
  1

• Scaling laws data

  #42 opened 10 months ago by borgr
  1

• 请问LLM和coder的base model结构是一样的吗？还是有什么区别呢？

  #40 opened 10 months ago by cherishtttz
  1

• AWS CLI 使用问题与 deepseek-ai S3 桶访问问题

  #34 opened a year ago by go-with-me000
  1

• can you please share sharded (<2gb / bin) model?

  #2 opened a year ago by amrrs
  2

• Programming Language in LeetCode Weekly Contest

  #24 opened a year ago by ShaneTian
  3

• 关于vllm使用的疑问

  #37 opened a year ago by xuyifan-0731
  1

• Training data distribution

  #36 opened a year ago by pluiez
  1

• AlignBench测评结果复现求助

  #32 opened a year ago by FoolMark
  2

• 67B-Instructor – will it be released shortly/ever?

  #21 opened a year ago by BuildBackBuehler
  1

• Will finetune scripts be provided?

  #23 opened a year ago by ftgreat
  1

• Missing files in released pretrain ckpts

  #26 opened a year ago by Wizardcoast
  1

• 为什么不能复现你们的结果（why can't i reproduce your results）

  #10 opened a year ago by tanguagua
  4

• Inquiry about Prompt Engineering and Handling Toxicity/Hallucination

  #25 opened a year ago by eric-chen-igs
  0

• lora sft deepseek 67b base版本

  #20 opened a year ago by liwenju0
  0

• question on "Revisit Multi-Choice Question Benchmarks"

  #18 opened a year ago by imhmhm
  1

• DeepSeek 7B Chat Lora 效果太棒了！

  #12 opened a year ago by KMnO4-zx
  4

• GPTQ模型量化

  #13 opened a year ago by 315930399
  1

• Will technical reports be released in the future?

  #11 opened a year ago by XChen-Zero
  1

• German umlaut missing with deepseek-llm on llama

  #9 opened a year ago by p3d-dev
  1

• LeetCode Weekly Contest Data

  #8 opened a year ago by tonysy
  1

• 图很好

  #7 opened a year ago by tpoisonooo
  0

• Learning rate schedule seems very helpful.

  #1 opened a year ago by GanjinZero
  1

• About LR schedule

  #3 opened a year ago by futuristx
  1