ypeleg/llama

Issues

• data format

  #12 opened 2 years ago by sekomer
  1

• How to organize customized text dataset ?

  #4 opened 2 years ago by kriskrisliu
  1

• AttributeError: module 'llama' has no attribute 'LLaMATokenizer' when using example

  #5 opened 2 years ago by benjamin32561
  7

• What's the difference of this llama and huggingface's llama module?

  #14 opened 2 years ago by fjljlzy
  0

• llama 7b 4bit

  #13 opened 2 years ago by GalloLuigi
  0

• OutOfMemoryError: CUDA out of memory

  #11 opened 2 years ago by Prakash19921206
  0

• GPU hardware for inference

  #1 opened 2 years ago by dcolumbus1492
  2

• Add Quantization Code

  #10 opened 2 years ago by htcml
  0

• how to put model and tensor on mac m1 gpu?

  #6 opened 2 years ago by srulik-ben-david
  1

• OOM with 80GB-A100

  #8 opened 2 years ago by kriskrisliu
  0

• peft training?

  #7 opened 2 years ago by xloem
  0

• torch using all GPU RAM

  #3 opened 2 years ago by YoSoyElZorlak
  1

• KeyError: 'decoder.layers.35.attention_norm.weight' when running inference

  #2 opened 2 years ago by ShaiMeital
  1