Bip-Rep/sherpa

Issues

• Support for Linux (Debian-class or other) ?

  #28 opened 8 months ago by farhi
  0

• Share link to `ggml-model.bin`

  #27 opened 9 months ago by jo-elimu
  3

• Does this support GGUF models?

  #25 opened a year ago by Kansi420
  2

• Support for GGMLv3?

  #26 opened 10 months ago by trignomtry
  1

• Add support for MobileLLaMA/MobileVLM models

  #24 opened a year ago by Foul-Tarnished
  0

• App crash on mtk 1080+ 8GB

  #22 opened a year ago by suoko
  1

• Does it support GGUF (instead of GGML)?

  #20 opened a year ago by Duxon
  3

• how to make it faster

  #6 opened 2 years ago by scrawnyether5669
  6

• Building libllama.so file for Android

  #16 opened a year ago by abusaadp
  2

• [Feature Request] Add ability to edit pre-prompt (and save them)

  #19 opened a year ago by Foul-Tarnished
  0

• libllama.so is 64-bit instead of 32-bit error when trying to load the model on my Samsung Device

  #15 opened a year ago by VigneshPasupathy
  2

• Is this app support Llama 2?

  #17 opened a year ago by GaryChen10128
  1

• Support GGML quantitized models

  #18 opened a year ago by Foul-Tarnished
  0

• Model file not working

  #14 opened a year ago by abusaadp
  3

• How to run it on Mac?

  #13 opened a year ago by realcarlos
  1

• It crashes

  #7 opened 2 years ago by Asory2010
  7

• Add support for k-quant latest models

  #10 opened 2 years ago by x-legion
  2

• How does this work?!?!?!?

  #8 opened 2 years ago by Leichesters
  2

• what is the folder of 'download folder'?

  #9 opened 2 years ago by TianRuiHe
  1

• Model file too old

  #4 opened 2 years ago by minfuel
  2

• Generation never starts: "context is null"

  #1 opened 2 years ago by sharpy66
  42

• This can work with Vicuna?

  #3 opened 2 years ago by NoNamedCat
  2

• Context Is null CPU tensor

  #2 opened 2 years ago by zeerodark
  1