TencentARC/ST-LLM

Issues

• Which GPT-3.5 version did you use during evaluation?

  #19 opened 3 months ago by SCZwangxiao
  1

• Improve HF artifacts

  #22 opened 3 months ago by NielsRogge
  0

• GPU out of memory

  #21 opened 4 months ago by Backdrop9019
  1

• AttributeError: 'MetaLoader' object has no attribute 'dataset'

  #20 opened 4 months ago by Richar-Du
  1

• question about training recipe

  #17 opened 5 months ago by Nastu-Ho
  3

• Inference Error

  #18 opened 4 months ago by liguopeng0923
  4

• how to modify the code to support llama3?

  #16 opened 6 months ago by dragen1860
  1

• How to fine-tune on image data

  #15 opened 6 months ago by Richar-Du
  4

• what's the difference between get_context_emb() and get_context_emb_sim()?

  #13 opened 6 months ago by dragen1860
  1

• 微调过程中loss问题

  #14 opened 6 months ago by zhanghang-official
  2

• Some weights of the model checkpoint at stllm/output/instructblipbase_stllm_conversation/ were not used?

  #12 opened 6 months ago by dragen1860
  1

• The specific settings of Lora finetuning

  #10 opened 7 months ago by Toneyaya
  5

• MVbench的测试情况

  #9 opened 7 months ago by ruishuzhao
  6

• Training Time Discrepancies

  #11 opened 7 months ago by AlexTurner90
  1

• MVM loss

  #8 opened 7 months ago by mutonix
  4

• Question about eval

  #4 opened 7 months ago by HenryHZY
  2

• HF weights

  #7 opened 7 months ago by mutonix
  2

• Cuda Version

  #6 opened 7 months ago by saroo25
  1

• Release the inference result of the benchmark

  #5 opened 7 months ago by Richar-Du
  1

• MVBench测试结果不一致

  #3 opened 7 months ago by emmating12
  5

• Questions about the testing strategy

  #1 opened 7 months ago by Richar-Du
  2