abgulati/LARS

Issues

• There was an error when loading the LLM in the method

  #21 opened 22 days ago by manub14
  45

• Pytorch memory usage balloons with each subsequent inference or query

  #23 opened 24 days ago by synchronic1
  2

• Typo in requirements.txt

  #22 opened a month ago by synchronic1
  9

• Failed to start llama.cpp local-server persists after saving settings

  #19 opened a month ago by yvileapsis
  4

• Feature Requests: Use llamafile / OpenAI compatible / API?

  #17 opened 2 months ago by quantumalchemy
  1

• Docker build fails

  #16 opened 2 months ago by ruze00
  6

• Fails on M2 Mac

  #15 opened 2 months ago by ruze00
  3

• Error with CUDA Dockerfile i.e dockerized_nvidia_cuda_gpu/Dockerfile

  #7 opened 3 months ago by AjayVarmaK
  7

• [Feature Request]: Change LARS behaviour to reset document context on New Chat

  #12 opened 3 months ago by ShaswatPanda
  1

• idea: embeddings should be generated using llama.cpp

  #9 opened 3 months ago by daboe01
  3

• Fedora 39: requirements installation fails on pywin32

  #5 opened 4 months ago by emulated24
  6

• requirements.txt is UTF-16LE encoding

  #8 opened 3 months ago by jabberjabberjabber
  1

• Issue to build llama.cpp with CMAKE

  #1 opened 3 months ago by diegomontania
  15

• Hybrid search support

  #2 opened 4 months ago by Jhyrachy
  1

• Converts txt files to pdf and back to text again

  #4 opened 4 months ago by Pomyk
  1

• Only Loading pdfs

  #6 opened 4 months ago by Hisma
  5