replicate/cog-vicuna-13b

Issues

• Tips for prompting Vicuna-13b

  #5 opened 2 years ago by rlancemartin
  4

• High latency on the first inference call

  #7 opened 2 years ago by rlancemartin
  3

• max_length parameter is not honored w/ Vicuna13-b

  #4 opened 2 years ago by rlancemartin
  11

• convert llama weights to vicuna weights

  #2 opened 2 years ago by joehoover
  0

• Release vicuna-13b on replicate

  #1 opened 2 years ago by joehoover
  1

• Thanay

  #6 opened 2 years ago by kannanjiji
  0

• You should consider increasing `max_new_tokens` error

  #3 opened 2 years ago by rlancemartin
  4