0cc4m/KoboldAI

Issues

• Install

  #77 opened 2 months ago by Bobbylargykisjo
  0

• ./play-rocm.sh gptq error fedora 39

  #76 opened 8 months ago by EtereosDawn
  1

• ImportError: cannot import name 'url_quote' from 'werkzeug.urls'

  #75 opened a year ago by archiebhl
  0

• Attempting to pass model params to ExLlama on startup causes an AttributeError

  #59 opened a year ago by InconsolableCellist
  2

• [Regression] Can't participate in horde with `exllama` branch, stopping sharing breaks processing

  #73 opened a year ago by InconsolableCellist
  0

• Support for MythoMax-L2-13B-GPTQ

  #72 opened a year ago by yukkun
  0

• How to load multiple graphics cards

  #71 opened a year ago by qweronly
  0

• Exllama in KoboldAI emits a spurious space at the beginning of generations that end with a stop token.

  #61 opened a year ago by pi6am
  2

• Significant Speed Recression on P40 compared to United

  #60 opened a year ago by wereretot
  0

• Slow speed for some models.

  #33 opened a year ago by BadisG
  4

• "expected scalar type BFloat16 but found Half"

  #58 opened a year ago by j2l
  0

• i keep getting a merge conflict when trying to git pull from the new updated 4bit-plugin dev branch

  #57 opened a year ago by 0xYc0d0ne
  1

• when will the new update kobold just got for llama-2 be pushed here?

  #56 opened a year ago by 0xYc0d0ne
  1

• cant load models 4bit

  #55 opened a year ago by scavru
  4

• Can't load 4bit models on Rocm

  #52 opened a year ago by Infection321
  4

• WinError 127 on nvfuser_codegen.dll

  #54 opened a year ago by racinmat
  0

• Request for T5 gptq model support.

  #53 opened a year ago by sigmareaver
  1

• please add code for landmark attention to 4bit-plugin

  #51 opened a year ago by BlairSadewitz
  0

• 1 token generation in story mode

  #49 opened a year ago by Hotohori
  2

• i cannot load any ai models and i keep getting this error no matter what i do. this happened after i did "git pull" command from this repository

  #50 opened a year ago by 0xYc0d0ne
  1

• Hey, I'm not sure what's wrong, but it does automatically delete a lot of output at the end of each generation.

  #46 opened a year ago by anyezhixie
  4

• ModuleNotFoundError: No module named 'gptq.bigcode'

  #47 opened a year ago by sigmareaver
  1

• anaconda3/lib/python3.9/runpy.py:127: RuntimeWarning: 'gptq.bigcode' found in sys.modules after import of package 'gptq', but prior to execution of 'gptq.bigcode'; this may result in unpredictable behaviour

  #48 opened a year ago by sigmareaver
  0

• Interface not loading... WSL/Windows

  #45 opened a year ago by bbecausereasonss
  0

• ModuleNotFoundError when starting "play.bat"

  #44 opened a year ago by anyezhixie
  4

• how i can uninstall

  #43 opened a year ago by gandolfi974
  1

• Can't split 4bit model between gpu/cpu, and can't run only on cpu

  #39 opened a year ago by tdtrumble
  1

• install_requirements error libmamba

  #42 opened a year ago by TFlame82
  0

• Cannot find the path specified & No module named 'hf_bleeding_edge' when trying to start.

  #41 opened a year ago by TheFairyMan
  20

• Failed to load 4bit-128g WizardLM 7B

  #36 opened a year ago by lee-b
  3

• Loading a model via command line (--model) does not work in 0cc4m Branch

  #27 opened a year ago by RandomBanana122132
  5

• AMD install out of date?

  #29 opened a year ago by jthree2001
  6

• Error involving bfloat 16 on generation with MPT 7B 4-bit_128g

  #31 opened a year ago by Bytemixer
  2

• Issue with loading 30b model which was previously good

  #28 opened a year ago by szarkab123
  1

• Error using previously good model.

  #30 opened a year ago by HeroMines
  2

• NameError: name 'os' is not defined after last commit

  #26 opened a year ago by OValete
  2

• What is the best way to update?

  #24 opened a year ago by silvestron
  2

• ImportError when running "play.sh"

  #22 opened a year ago by brendan-donohoe
  1

• No 4-bit toggle

  #23 opened a year ago by Magnaderra
  2

• Can't Generate With 4bit Quantized Model

  #19 opened a year ago by chigkim
  13

• i got an other error

  #14 opened 2 years ago by akdcelcopr77
  1

• Error on start

  #21 opened 2 years ago by conradcn
  2

• pt not found

  #16 opened 2 years ago by olamedia
  2

• Can't Find 4Bit Model

  #17 opened 2 years ago by chigkim
  3

• Flask Error

  #15 opened 2 years ago by xSparksx
  1

• ERROR: quant_cuda-0.0.0-cp38-cp38-win_amd64.whl is not a supported wheel on this platform.

  #13 opened 2 years ago by akdcelcopr77
  2

• src/sentencepiece_processor.cc error when loading GPT4X model

  #11 opened 2 years ago by Mu2u
  1