oobabooga/text-generation-webui issues and pull requests

#6276 - Make compress_pos_emb float

Pull Request - State: closed - Opened by hocjordan 4 months ago - 1 comment

#6273 - Render the output without refocusing the cursor on the screen

Issue - State: open - Opened by srevenant 4 months ago - 3 comments
Labels: enhancement

#6272 - Saving a character causes the character selector to become blank and the UI fails to save logs correctly as a result

Issue - State: closed - Opened by sinful-developer 4 months ago - 2 comments
Labels: bug

#6270 - Update dependencies for getting LLAMA 3.1 to work

Issue - State: open - Opened by reuschling 4 months ago - 11 comments
Labels: enhancement

#6269 - Getting argument device not found error from utils.py

Issue - State: closed - Opened by JulienBeck 4 months ago - 2 comments
Labels: bug

#6267 - load Mistral-Nemo-Instruct-2407(exl2) fail

Issue - State: open - Opened by turandot2017 4 months ago - 1 comment
Labels: bug

#6266 - Request to Update Exllamav2 Module to version 0.1.8

Issue - State: closed - Opened by GrennKren 4 months ago - 3 comments
Labels: enhancement

#6264 - update llama.cpp

Issue - State: open - Opened by imilli 4 months ago - 5 comments
Labels: enhancement

#6256 - Truncate prompt value from settings

Issue - State: open - Opened by mykeehu 4 months ago - 1 comment
Labels: enhancement

#6255 - FileNotFoundError: Could not find module 'J:\AI\text-generation-webui\installer_files\env\Lib\site-packages\llama_cpp_cuda\lib\llama.dll'

Issue - State: closed - Opened by allrobot 4 months ago - 3 comments
Labels: bug

#6253 - [WinError 126] Error loading "backend_with_compiler.dll" Intel ARC

Issue - State: open - Opened by Magenta-Flutist 4 months ago - 5 comments
Labels: bug

#6250 - ExLlamav2 won't unload model commit 0315122c

Issue - State: open - Opened by Remowylliams 4 months ago - 1 comment
Labels: bug

#6246 - API Request not working correctly

Issue - State: open - Opened by Chepko932 4 months ago - 1 comment
Labels: bug

#6237 - All characters replying with 'Char:' in this version

Issue - State: closed - Opened by spike4379 4 months ago - 2 comments
Labels: bug

#6235 - Exception: Cannot import 'llama-cpp-cuda' because 'llama-cpp' is already imported. Switching to a different version of llama-cpp-python currently requires a server restart.

Issue - State: open - Opened by dark-passages 4 months ago - 4 comments
Labels: bug

#6225 - RuntimeWarning: Detected duplicate leading "<|begin_of_text|>" in prompt

Issue - State: open - Opened by Kaszebe 4 months ago - 4 comments
Labels: bug

#6210 - Illegal instruction (core dumped) after update

Issue - State: closed - Opened by NXTler 4 months ago - 4 comments
Labels: bug

#6209 - Oobabooga login not working through reverse proxy

Issue - State: open - Opened by binkleym 4 months ago - 2 comments
Labels: bug

#6207 - Saving the interface theme is missing

Issue - State: closed - Opened by Alkohole 4 months ago
Labels: bug

#6204 - Issue installing

Issue - State: open - Opened by jaimedeoya 4 months ago - 2 comments
Labels: bug

#6202 - Llama-cpp-python 0.2.81 'already loaded' fails to load models

Issue - State: open - Opened by Patronics 4 months ago - 18 comments
Labels: bug

#6189 - Whisper Fix, js replacement of the gradio element to prevent browser crash.

Pull Request - State: closed - Opened by RandomInternetPreson 4 months ago - 3 comments

#6176 - Resolving the 'LlamaCppModel' Object Missing 'Device' Attribute Error in OpenAI LogitsBiasProcessor function - Ubuntu Linux

Issue - State: open - Opened by BlueprintCoding 5 months ago - 2 comments
Labels: bug

#6169 - AMDGPU is broken on 1.8

Issue - State: open - Opened by pl752 5 months ago - 6 comments
Labels: bug

#6168 - Add Q4/Q8 cache for llama.cpp

Issue - State: open - Opened by GodEmperor785 5 months ago - 4 comments
Labels: enhancement

#6144 - Impossible to load DeepSeek-Coder-V2-Instruct.gguf

Issue - State: open - Opened by narikm 5 months ago - 10 comments
Labels: bug

#6138 - Update script will redownload from the beginning all files in temp_requirements.txt if there's any download problem, even in the last file.

Issue - State: open - Opened by CalculonPrime 5 months ago - 2 comments
Labels: bug

#6112 - Add support for Nvidia Optimum

Issue - State: open - Opened by Iaotle 5 months ago - 1 comment
Labels: enhancement

#6102 - start_macos.sh fails on unabling to find torch version

Issue - State: open - Opened by sadovsf 5 months ago - 1 comment
Labels: bug

#6085 - In-progress chat session resets / disappears when returning to chat after a time away

Issue - State: closed - Opened by MovingSymbols 5 months ago - 12 comments
Labels: bug

#6081 - hi

Issue - State: closed - Opened by ngaile 5 months ago
Labels: enhancement

#6036 - Can't connect api to SillyTavern or Agnai

Issue - State: open - Opened by alferitu 6 months ago - 2 comments
Labels: bug

#6028 - Full use of dual GPU

Issue - State: open - Opened by Skit5 6 months ago - 6 comments
Labels: enhancement

#6021 - Batched/multi replies

Issue - State: closed - Opened by Beinsezii 6 months ago - 5 comments
Labels: enhancement

#6019 - one click not working

Issue - State: open - Opened by pro9code 6 months ago - 7 comments
Labels: bug

#6003 - Multi-GPU cannot load transformers on a single card

Issue - State: closed - Opened by Urammar 6 months ago - 2 comments
Labels: bug, stale

#5998 - How can I change web port 7860 to another port?

Issue - State: closed - Opened by union-cmd 6 months ago - 2 comments
Labels: enhancement, stale

#5997 - Since some update min_token_length or minimum length has disapeared

Issue - State: closed - Opened by iboyles 6 months ago - 3 comments
Labels: bug, stale

#5995 - Failed to build the chat prompt.

Issue - State: open - Opened by thejohnd0e 6 months ago - 3 comments
Labels: bug

#5994 - Support for real-time TTS!

Pull Request - State: open - Opened by czuzu 6 months ago - 4 comments

#5986 - ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.

Issue - State: open - Opened by nanshaws 6 months ago - 3 comments
Labels: bug

#5985 - RuntimeError: FlashAttention only supports Ampere GPUs or newer.

Issue - State: open - Opened by linzm1007 6 months ago - 3 comments
Labels: bug

#5983 - Incorrect LLaMA 3 Instruct tokenization with llama.cpp loader

Issue - State: closed - Opened by JohannesGaessler 6 months ago - 1 comment
Labels: bug, stale

#5981 - break external extentions

Issue - State: closed - Opened by kalle07 6 months ago - 1 comment
Labels: bug, stale

#5980 - character user

Issue - State: closed - Opened by kalle07 6 months ago - 9 comments
Labels: bug, stale

#5979 - CSS loading from incorrect endpoint

Issue - State: open - Opened by bars0um 6 months ago - 2 comments
Labels: bug

#5977 - Cant load llama 3 safetensor model

Issue - State: open - Opened by Bedoshady 6 months ago - 7 comments
Labels: bug

#5974 - not a directory

Issue - State: closed - Opened by moonciest 6 months ago - 1 comment
Labels: bug, stale

#5972 - Conda environment is empty.

Issue - State: open - Opened by wbrunoFC 7 months ago - 1 comment
Labels: bug

#5971 - Mismatch GPU architecture causes excessive vram usage for exl2

Issue - State: closed - Opened by lawallet 7 months ago - 1 comment
Labels: bug, stale

#5968 - I do not know how to use some llm models with gpu some deprecated stuff

Issue - State: closed - Opened by makrse 7 months ago - 3 comments
Labels: bug, stale

#5966 - The same model, with the same prompt has different performance in webui and LM Studio

Issue - State: open - Opened by AndreyRGW 7 months ago - 2 comments
Labels: bug

#5965 - Run Llama 3 70b locally combining ram and vram like with other apps?

Issue - State: closed - Opened by 311-code 7 months ago - 2 comments
Labels: enhancement, stale

#5956 - powershell install script

Issue - State: closed - Opened by Xcertik-Realist 7 months ago - 1 comment
Labels: enhancement, stale

#5952 - Fix async events for OpenAI API extension + Other small fixes

Pull Request - State: open - Opened by Artificiangel 7 months ago

#5950 - Request: Stop current generation in API

Issue - State: closed - Opened by Wladastic 7 months ago - 1 comment
Labels: enhancement, stale

#5949 - Low performance - need help

Issue - State: closed - Opened by RndUsr123 7 months ago - 4 comments
Labels: bug, stale

#5948 - if you have python installed already, you can just install the requiremenst_amd.txt and that would get you started.

Issue - State: closed - Opened by cgwers 7 months ago - 2 comments
Labels: stale

#5930 - PHI-3 128K GGUF - Model Fails to Load

Issue - State: closed - Opened by dmsweetser 7 months ago - 5 comments
Labels: bug, stale

#5928 - Unable to train LoRA

Issue - State: closed - Opened by Cohejh 7 months ago - 3 comments
Labels: bug, stale

#5925 - install error

Issue - State: closed - Opened by VladTheDestructor 7 months ago - 8 comments
Labels: bug, stale

#5919 - The checksum verification for miniconda_installer.exe has failed

Issue - State: open - Opened by cgwers 7 months ago - 5 comments
Labels: bug

#5914 - Can no longer start: AttributeError: module 'lib' has no attribute 'X509_V_FLAG_NOTIFY_POLICY'. Did you mean: 'X509_V_FLAG_EXPLICIT_POLICY'?

Issue - State: closed - Opened by thelabcat 7 months ago - 9 comments
Labels: bug, stale

#5902 - Update API documentation with examples to list/load models

Pull Request - State: closed - Opened by joachimchauvet 7 months ago

#5896 - requirements conflict between text-generation-webui, superbooga and coqui_tts

Issue - State: closed - Opened by bridgesense 7 months ago - 2 comments
Labels: bug, stale

#5894 - Auto-Split Error for GPTQ on Nvidia

Issue - State: closed - Opened by Zaxl445 7 months ago - 9 comments
Labels: bug, stale

#5888 - can't load models

Issue - State: closed - Opened by MenrichKoller 7 months ago - 7 comments
Labels: bug, stale

#5882 - error when start_windows.bat run

Issue - State: closed - Opened by YondSun 7 months ago - 2 comments
Labels: bug, stale

#5861 - rope_freq_base > 1,000,000

Issue - State: closed - Opened by oldgithubman 7 months ago - 4 comments
Labels: enhancement, stale

#5845 - when trying to use pygmalion-7b-4bit-128g-cuda-2048Token it gives a missing keyword error

Issue - State: closed - Opened by paulpackgithub 7 months ago - 3 comments
Labels: bug, stale

#5765 - Loading Model Error

Issue - State: open - Opened by MateuszUlan 8 months ago - 9 comments
Labels: bug

#5764 - loading model errors

Issue - State: closed - Opened by ARCIST-AI 8 months ago - 5 comments
Labels: bug, stale

#5736 - AWQ model error: ERROR Failed to load the model. NotImplementedError: Cannot copy out of meta tensor; no data!

Issue - State: closed - Opened by guispfilho 8 months ago - 3 comments
Labels: bug, stale

#5734 - AttributeError: 'function' object has no attribute 'wrapped'

Issue - State: closed - Opened by varkappadev 8 months ago - 3 comments
Labels: bug, stale

#5705 - UserWarning: 1Torch was not compiled with flash attention.

Issue - State: open - Opened by capactiyvirus 8 months ago - 24 comments
Labels: bug

#5702 - EXL2 formatting is busted through the openai like API

Issue - State: closed - Opened by MrMojoR 8 months ago - 3 comments
Labels: bug, stale

#5689 - ERROR text-generation-webui???

Issue - State: closed - Opened by kangz543g 8 months ago - 4 comments
Labels: bug, stale

#5627 - Use webui with external OpenAI compatible model server

Issue - State: closed - Opened by StableLlama 8 months ago - 6 comments
Labels: enhancement, stale

#5603 - Multimodal for llama.cpp GGUF and Llava 1.6

Issue - State: closed - Opened by Dartvauder 9 months ago - 3 comments
Labels: enhancement

#5562 - Add support for Google Gemma Model

Issue - State: closed - Opened by shreyanshsaha 9 months ago - 13 comments
Labels: enhancement, stale

#5532 - Ollama Integration

Issue - State: closed - Opened by CHesketh76 9 months ago - 5 comments
Labels: enhancement

#5501 - Memory Management BSOD after loading model with exllamav2

Issue - State: closed - Opened by Norwaere 9 months ago - 6 comments
Labels: bug, stale

#5474 - Fixed, improved, and unified Docker environment

Pull Request - State: open - Opened by StefanDanielSchwarz 9 months ago - 2 comments

#5457 - Docker Install / Transformer Cache issue

Issue - State: closed - Opened by tilllt 9 months ago - 12 comments
Labels: bug, stale

#5408 - RuntimeError: Failed to import transformers.models.llama.modeling_llama

Issue - State: closed - Opened by HeroMines 10 months ago - 13 comments
Labels: bug, stale

#5381 - Swap to huggingface_hub get_token function

Pull Request - State: closed - Opened by Anthonyg5005 10 months ago - 1 comment

#5270 - No module named 'yaml'

Issue - State: closed - Opened by karsontsang23 10 months ago - 18 comments
Labels: bug, stale

#5185 - Add function calling ability to openai extension

Pull Request - State: closed - Opened by yhyu13 10 months ago - 20 comments

#5166 - Installation fails due to missing gradio, dateuil and probably others

Issue - State: closed - Opened by rowild 10 months ago - 3 comments
Labels: bug, stale

#5129 - Allow Path Recursive Search In Models Folder

Issue - State: closed - Opened by JiHa-Kim 11 months ago - 4 comments
Labels: stale

#5084 - Loading in Exllama results in enormous VRAM usage

Issue - State: closed - Opened by azulika 11 months ago - 3 comments
Labels: bug, stale

#5038 - Bug fixes for llava multimodal

Pull Request - State: open - Opened by szelok 11 months ago - 4 comments

#5036 - Unable to start with arguments --model liuhaotian_llava-v1.5-13b --multimodal-pipeline llava-v1.5-13b

Issue - State: closed - Opened by szelok 11 months ago - 14 comments
Labels: bug, stale

#4720 - Add supports for multiple system messages on OpenAI API extensions.

Issue - State: closed - Opened by justpain02 12 months ago - 5 comments
Labels: enhancement

#4707 - Support for Styletts2

Issue - State: closed - Opened by D3voz 12 months ago - 3 comments
Labels: enhancement, stale

#4672 - 404 Error: {"detail":"Not Found"} response to a post request made to the API running on port 5000 (/api/v1/generate)

Issue - State: closed - Opened by jaquielajoie 12 months ago - 3 comments
Labels: bug

#4561 - Adds multiple file input to superboogav2

Pull Request - State: open - Opened by carlulsoe about 1 year ago - 1 comment

#4371 - Error loading multiple LORAs on Transformers Adapter

Issue - State: closed - Opened by Xeba111 about 1 year ago - 13 comments
Labels: bug, stale

#4357 - RuntimeError: Failed to import transformers.models.llama.modeling_llama because of the following error (look up to see its traceback): DLL load failed while importing flash_attn_2_cuda: The specified module could not be found.

Issue - State: closed - Opened by ayush1268 about 1 year ago - 24 comments
Labels: enhancement, stale

#4195 - ImportError: libcudart.so.11.0: cannot open shared object file: No such file or directory

Issue - State: closed - Opened by mushinbush about 1 year ago - 13 comments
Labels: bug, stale

GitHub / oobabooga/text-generation-webui issues and pull requests