gotzmann/llama.go

Issues

• provide offline option for llama_download_file

  #31 opened 3 months ago by codefromthecrypt
  0

• Anyone taking this project forward for real?

  #29 opened 10 months ago by ouvaa
  1

• @mfreeman451 possible to take this forward with a forked repo?

  #30 opened 9 months ago by sprappcom
  7

• is this proj abandon?

  #23 opened a year ago by hiqsociety
  2

• please keepPR

  #25 opened a year ago by ChinaGISboyYang
  1

• Failed to load model, Wrong MAGIC in header

  #27 opened a year ago by TeqGin
  1

• avx hardware calculation optimization doesn't seem to work

  #28 opened 10 months ago by Nuclear6
  0

• What is the project's maturity level?

  #21 opened a year ago by alph4b3th
  1

• Trying to run thebloke guanaco-3b-uncensored-v2.ggmlv1.q4_0.bin but got this error, how to convert to format for llama.go?

  #24 opened a year ago by hiqsociety
  3

• Able to build and run not able to test

  #22 opened a year ago by nagapadmasrip
  0

• Need to move faster

  #20 opened 2 years ago by af913337456
  0

• Postman gives "Cannot POST /" error with server mode.

  #19 opened 2 years ago by ffreality
  2

• benchmarks comparison to C++ version

  #3 opened 2 years ago by nikolaydubina
  0

• How do I convert huggingface llama models for llama.go?

  #18 opened 2 years ago by eugenepentland
  0

• Go commands to build from source seem wrong

  #17 opened 2 years ago by Germain-L
  1

• How to implement INT4/INT8 quantization and optimal way to use AVX instructions?

  #11 opened 2 years ago by alph4b3th
  10

• interested in ai and would like to contribute code but not sure where to start

  #16 opened 2 years ago by kolinfluence
  0

• Where is the model ggml-model-f32.bin ?

  #14 opened 2 years ago by SilvaRaulEnrique
  0

• add a readme in project details please.

  #1 opened 2 years ago by alph4b3th
  9

• feat: interactive mode for a chatgpt like experience

  #5 opened 2 years ago by mfreeman451
  1

• How to quantize

  #2 opened 2 years ago by guyvdb
  1