2 Pull requests merged by 1 person

• Add strftime_now to JINJA to sattisfy LLAMA 3.1 and 3.2

  #6692 merged Jan 24, 2025

• Training pro- removed monkeypatch references

  #6695 merged Jan 24, 2025

4 Pull requests opened by 1 person

• Bump speechrecognition from 3.10.0 to 3.14.1

  #6704 opened Jan 27, 2025

• Update gradio requirement from ==4.37.* to ==5.13.*

  #6705 opened Jan 27, 2025

• Bump fastapi from 0.112.4 to 0.115.7

  #6706 opened Jan 27, 2025

• Bump pydantic from 2.8.2 to 2.10.6

  #6707 opened Jan 27, 2025

15 Issues closed by 3 people

• 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.

  #5986 closed Jan 28, 2025

• Support Qualcomm Snapdragon X NPU

  #6298 closed Jan 27, 2025

• Lower performance with text streaming enabled at high context and possible solutions?

  #6283 closed Jan 26, 2025

• Ban the eos_token and auto_max_new_tokens are not working

  #6293 closed Jan 26, 2025

• jetson agx orin uses llama3.1-7b

  #6295 closed Jan 26, 2025

• Update TGW Error

  #6296 closed Jan 26, 2025

• Text in chat window fails to scroll.

  #6297 closed Jan 26, 2025

• User Information Not Saved (Parameters → Chat → User)

  #6698 closed Jan 26, 2025

• Failing to load model

  #6287 closed Jan 25, 2025

• Latest oobabooga build always creates errors in the console after asking several questions, and tried different models.

  #6688 closed Jan 25, 2025

• support ipv6

  #6284 closed Jan 24, 2025

• load Mistral-Nemo-Instruct-2407(exl2) fail

  #6267 closed Jan 23, 2025

• Add Q6 cache support for ExllamaV2

  #6278 closed Jan 23, 2025

• Can't initialize NVML on WSL

  #6282 closed Jan 23, 2025

• update llama.cpp

  #6264 closed Jan 22, 2025

14 Issues opened by 11 people

• Error Loading DeepSeek-R1-Distill-Qwen-1.5B-uncensored.Q6_K.gguf in oobabooga Web UI: Unknown Pre-Tokenizer Type 'deepseek-r1-qwen'

  #6710 opened Jan 29, 2025

• [AMD] [Linux] AttributeError: 'NoneType' object has no attribute 'lower'

  #6709 opened Jan 28, 2025

• V2.3 Blank responses from any model

  #6708 opened Jan 28, 2025

• LogitsWarper deprecated in upstream transformers

  #6703 opened Jan 26, 2025

• new static_cache option seem to have broken API with exl2 models

  #6702 opened Jan 26, 2025

• Attempts to connect to "api.gradio.app" on startup

  #6701 opened Jan 26, 2025

• Add an Option to Retrieve the Token ID of a word/sentence for the Loaded Model

  #6700 opened Jan 26, 2025

• Clean UTF-8 Text Support for YAML Card Files Generated with text-generation-webui

  #6697 opened Jan 26, 2025

• Failed to extact conda Packages

  #6696 opened Jan 24, 2025

• Fresh installation of text-generation-webui-2.3 missing current branch information for update

  #6694 opened Jan 24, 2025

• Maybe it is time to rename the Chat Template?

  #6693 opened Jan 23, 2025

• Issue with Git Network Access During Installation

  #6691 opened Jan 23, 2025

• Deleted comments in chat and Copy last reply bug

  #6690 opened Jan 23, 2025

• Can not resume training

  #6689 opened Jan 23, 2025

14 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Issue on Training

  #6676 commented on Jan 22, 2025 • 0 new comments

• Training on CPU produces division by zero error when computing progress value to display.

  #6615 commented on Jan 23, 2025 • 0 new comments

• RuntimeError: FlashAttention only supports Ampere GPUs or newer.

  #5985 commented on Jan 24, 2025 • 0 new comments

• Cannot load GGUF models with newest version(s)

  #6659 commented on Jan 28, 2025 • 0 new comments

• So SLOW with NVidia GPU and Codestral model

  #6326 commented on Jan 29, 2025 • 0 new comments

• Feature Request: Anti-slop / fine tuning of a model output in realtime / on the fly for output quality enhancement.

  #6443 commented on Jan 29, 2025 • 0 new comments

• New SOTA model DeepSeek-R1-Qwen won't load

  #6679 commented on Jan 29, 2025 • 0 new comments

• Lag/delay when clicking buttons in the gradio UI

  #4138 commented on Jan 29, 2025 • 0 new comments

• Fix async events for OpenAI API extension + Other small fixes

  #5952 commented on Jan 28, 2025 • 0 new comments

• Fix extensions/openai/completions.py to enable system prompt through API

  #6083 commented on Jan 24, 2025 • 0 new comments

• OpenAI API: new parameter to change model list behavior

  #6358 commented on Jan 23, 2025 • 0 new comments

• fixed perplexity_color extension

  #6485 commented on Jan 24, 2025 • 0 new comments

• Add a user profile selector.

  #6550 commented on Jan 29, 2025 • 0 new comments

• Allow for Model Subfolder Organization

  #6686 commented on Jan 26, 2025 • 0 new comments