NouamaneTazi/bloomz.cpp

Issues

• download and convert the 7B1 model to ggml FP16 format fails!

  #35 opened a year ago by distalx
  0

• May you release a windows build binary?

  #17 opened 2 years ago by progressionnetwork
  4

• Convert bloomz-7b1-mt to ggml error.

  #34 opened a year ago by knamg
  0

• Convert HF to ggml error.

  #33 opened a year ago by phamkhactu
  0

• -n param doesn't work?

  #22 opened 2 years ago by darshisen
  0

• Quantization doesn't work with Bloomz 176B

  #14 opened 2 years ago by agemagician
  10

• Running 'make' warnings in bloom_model_load() function

  #29 opened 2 years ago by linuxmagic-mp
  1

• Bloomz 176B inference doesn't work

  #15 opened 2 years ago by agemagician
  9

• Something wrong with the tokenize function.

  #30 opened 2 years ago by samsha1971
  0

• Eval result is wrong compare to huggingface

  #27 opened 2 years ago by yangyaofei
  0

• several questions

  #26 opened 2 years ago by wesleysanjose
  1

• error

  #25 opened 2 years ago by win10ogod
  0

• document sampling parameters and/or minimal "viable" codegen model ?

  #12 opened 2 years ago by laurentperez
  1

• Is there any plan for mT0 model support?

  #20 opened 2 years ago by qdwang
  1

• There was a problem loading the model

  #16 opened 2 years ago by ScottishFold007
  1

• setting -t 8 (n_threads) "locks" the python process

  #11 opened 2 years ago by laurentperez
  0

• [Open-to-community] Benchmark bloomz.cpp on different hardware

  #4 opened 2 years ago by Vaibhavs10
  6

• Load a ggml model from the hub

  #6 opened 2 years ago by NouamaneTazi
  0

• [RFE] Add interactive mode

  #8 opened 2 years ago by lapo-luchini
  3

• Quantised model?

  #5 opened 2 years ago by amrrs
  2