oobabooga / text-generation-webui

A Gradio web UI for Large Language Models.

oobabooga/text-generation-webui Issues

issue with downloading
Updated 6 hours ago
Can't load any model, Please help.
Updated 6 hours ago
Ollama. Please?
Updated 6 hours ago2
Issue with one click and manual install, not working out of the box... Ubuntu 24.04
Updated a day ago
Some UI unreachable in chat tab in chat-instruct mode
Updated 2 days ago1
update_wizard_windows.bat
Updated 3 days ago
Cannot import model
Closed 3 days ago1
List Index out of Range histories[0][1]
Updated 4 days ago2
Invoking any grammar except None causes webui to crash
Closed 4 days ago4
So SLOW with NVidia GPU and Codestral model
Updated 5 days ago3
Lorebook/worldbook functionality
Updated 7 days ago1
Unable to upload character JSON
Updated 7 days ago
Only able to generate gibberish (Wizard-Vicuna-13B-Uncensored-GPTQ)
Updated 7 days ago3
Text Generation/Responses NOT following user prompts/responses/replies/inputs (ie. Sillytavern + Textgen)
Updated 11 days ago
"Start Reply with" in the chat API
Updated 12 days ago
git clone on linux is broken
Updated 13 days ago12
Llama-cpp fails to install
Updated 14 days ago1
MS are releasing a DeepSpeed WHL for Windows :)
Updated 14 days ago
Render the output without refocusing the cursor on the screen
Updated 15 days ago3
Error at install (Windows - CPU only) <-> ModuleNotFoundError: No module named 'yaml'
Updated 16 days ago3
Adding files to the context
Updated 16 days ago
Help Needed with Local Dataset Support for PPL Evaluation
Updated 17 days ago
Llama 3.1 GGUF incompatibility using latest release of llama.cpp and text-generation-webui.
Updated 17 days ago11
Can't train LoRA for Phi-3-medium-128k-instruct (transformers)
Updated 17 days ago
API examples in docs outdated
Updated 18 days ago2
Getting argument device not found error from utils.py
Closed 18 days ago2
Update dependencies for getting LLAMA 3.1 to work
Updated 18 days ago11
Smarter crash diagnosis
Updated 18 days ago
Exllama v2 crashes when starting to load in the third gpu
Updated 18 days ago4
When running the start_windows.bat file in the Windows interface, ModuleNotFoundError: No module named 'yaml' appears And I didn't see some important tool files in the download list
Updated 18 days ago1
Censorship
Updated 19 days ago4
Exllamav2 qcache support (Q4, Q6, Q8)
Updated 19 days ago1
VideoLLM-online, CosyVoice, and SenseVoice Integration
Updated 20 days ago
OpenAI api issues with Huggingface Chat UI
Updated 20 days ago
Unexpected behavior: Model loads on single GPU but fails on dual GPU setup
Updated 20 days ago2
Support Qualcomm Snapdragon X NPU
Updated 23 days ago
Lower performance with text streaming enabled at high context and possible solutions?
Updated 24 days ago1
Text in chat window fails to scroll.
Updated 24 days ago
AutoAWQ gone missing (model loader) and charecter not loading (for my case, out of 5 charecters, only 2 of them are loading)
Updated 25 days ago5
Ban the eos_token and auto_max_new_tokens are not working
Updated 25 days ago
Update TGW Error
Updated 25 days ago
jetson agx orin uses llama3.1-7b
Updated 25 days ago
Speculative Decoding
Updated 25 days ago
Failing to load model
Updated 25 days ago1
Can't load TheBloke_openchat-3.5-0106-GPTQ using the Transformers model loader
Closed 25 days ago2
support ipv6
Updated a month ago
load Mistral-Nemo-Instruct-2407(exl2) fail
Updated a month ago1
Can't initialize NVML on WSL
Updated a month ago
Add Q6 cache support for ExllamaV2
Updated a month ago2
Saving a character causes the character selector to become blank and the UI fails to save logs correctly as a result
Closed a month ago2