Glaciohound/LM-Infinite

Issues

• passkey代码运行不通

  #10 opened 2 months ago by xjwhy
  0

• kv_seq_len bug?

  #9 opened 4 months ago by chenlidar
  0

• Improve GPU memory usage but slower inference speed?

  #8 opened 4 months ago by ys-zong
  0

• TypeError: attn_forward_factory() missing 5 required positional arguments: 'top_k_attention', 'top_k_insert_at', 'top_k_from_layer', 'top_k_to_layer', and 'layer_i'

  #7 opened 5 months ago by canelxie
  4

• Some errors.

  #6 opened 8 months ago by chaochen99
  1

• limited_distance_forward() got an unexpected keyword argument 'padding_mask'

  #3 opened 9 months ago by dittops
  1

• Should the llama model be fine-tuned?

  #5 opened 10 months ago by yinwangsong
  1

• Implementation with RoPE

  #4 opened 10 months ago by sdc17
  2

• How to Inferance?

  #2 opened 10 months ago by farrael004
  1

• GPTNeoX or Transformers support?

  #1 opened a year ago by fblgit
  2