THUDM/LongAlign

Issues

• packing loss 的归一化问题

  #12 opened a month ago by Chandler-Bing
  1

• Question about ShareGPT data

  #10 opened 3 months ago by S1s-Z
  2

• 关于packing loss的问题

  #8 opened 4 months ago by mxjmtxrm
  3

• Needel_test CUDA OOM 了应该怎么解决？

  #11 opened 4 months ago by SefaZeng
  1

• Prediction Results of LongBench-Chat

  #9 opened 4 months ago by guanzhchen
  2

• How to get length value in the dataset

  #7 opened 4 months ago by Geaming2002
  1

• AttributeError: 'LlamaForCausalLM' object has no attribute 'chat'

  #4 opened 6 months ago by liuyongjie985
  3

• [BUG] 使用Langchain-Chatchat框架加载chatglm3-6-b-128k出现自问自答，停不下来的情况

  #5 opened 7 months ago by nmbtwzt
  1

• Questions about ChatGLM3-6b-128k

  #2 opened 8 months ago by KaiLv69
  7

• 关于Packing和 直接Batch的loss区别？

  #3 opened 8 months ago by BitVoyage
  3