Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

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

#65 - problems with gradio api

Issue - State: closed - Opened by SwannSchilling almost 2 years ago - 7 comments

#64 - Not compiled with CUDA

Issue - State: closed - Opened by CodeDog04 almost 2 years ago - 3 comments

#64 - Not compiled with CUDA

Issue - State: closed - Opened by CodeDog04 almost 2 years ago - 3 comments

#63 - Unable to load bigger models in 8 bits mode

Issue - State: closed - Opened by Manimap almost 2 years ago - 7 comments
Labels: stale

#63 - Unable to load bigger models in 8 bits mode

Issue - State: closed - Opened by Manimap almost 2 years ago - 7 comments
Labels: stale

#62 - How to get this working with an AMD GPU?

Issue - State: closed - Opened by robonxt-ai almost 2 years ago - 43 comments
Labels: stale

#62 - How to get this working with an AMD GPU?

Issue - State: closed - Opened by robonxt-ai almost 2 years ago - 41 comments
Labels: stale

#61 - Any way to convert larger models to pytorch ?

Issue - State: closed - Opened by Manimap almost 2 years ago - 3 comments
Labels: question

#61 - Any way to convert larger models to pytorch ?

Issue - State: closed - Opened by Manimap almost 2 years ago - 3 comments
Labels: question

#59 - wiki error

Issue - State: closed - Opened by Wilaz almost 2 years ago - 1 comment

#59 - wiki error

Issue - State: closed - Opened by Wilaz almost 2 years ago - 1 comment

#58 - one server, multiple sessions (users) ((feature request))

Issue - State: closed - Opened by ThatCoffeeGuy almost 2 years ago - 24 comments
Labels: enhancement, stale

#58 - one server, multiple sessions (users) ((feature request))

Issue - State: closed - Opened by ThatCoffeeGuy almost 2 years ago - 24 comments
Labels: enhancement, stale

#57 - Fix a regex issue in `tokenize_dialogue`.

Pull Request - State: closed - Opened by martinnj almost 2 years ago - 3 comments

#57 - Fix a regex issue in `tokenize_dialogue`.

Pull Request - State: closed - Opened by martinnj almost 2 years ago - 3 comments

#56 - Error when saving dialogue

Issue - State: closed - Opened by Manimap almost 2 years ago - 2 comments

#56 - Error when saving dialogue

Issue - State: closed - Opened by Manimap almost 2 years ago - 2 comments

#55 - Error when generating using 8-bit mode: Illegal memory access

Issue - State: closed - Opened by sashasubbbb almost 2 years ago - 1 comment

#55 - Error when generating using 8-bit mode: Illegal memory access

Issue - State: closed - Opened by sashasubbbb almost 2 years ago - 1 comment

#54 - Unable to install deepspeed

Issue - State: closed - Opened by sashasubbbb almost 2 years ago - 1 comment

#54 - Unable to install deepspeed

Issue - State: closed - Opened by sashasubbbb almost 2 years ago - 1 comment

#53 - Error when using --load-in-8bit: no kernel image is available for execution on the device

Issue - State: closed - Opened by Pounix01 almost 2 years ago - 6 comments
Labels: bug, stale

#53 - Error when using --load-in-8bit: no kernel image is available for execution on the device

Issue - State: closed - Opened by Pounix01 almost 2 years ago - 6 comments
Labels: bug, stale

#51 - Deepspeed error on WSL - exits with return code = -9

Issue - State: closed - Opened by lolxdmainkaisemaanlu almost 2 years ago - 4 comments
Labels: bug, stale

#51 - Deepspeed error on WSL - exits with return code = -9

Issue - State: closed - Opened by lolxdmainkaisemaanlu almost 2 years ago - 4 comments
Labels: bug, stale

#50 - [Suggestion] Make the saved dialogue the same as saved images in automatic webui

Issue - State: closed - Opened by Manimap almost 2 years ago - 4 comments

#50 - [Suggestion] Make the saved dialogue the same as saved images in automatic webui

Issue - State: closed - Opened by Manimap almost 2 years ago - 4 comments

#49 - Token count

Issue - State: closed - Opened by Manimap almost 2 years ago - 2 comments

#49 - Token count

Issue - State: closed - Opened by Manimap almost 2 years ago - 2 comments

#48 - 8-bit mode on older GPUs

Issue - State: closed - Opened by nonetrix almost 2 years ago - 21 comments
Labels: bug, stale

#48 - 8-bit mode on older GPUs

Issue - State: closed - Opened by nonetrix almost 2 years ago - 21 comments
Labels: bug, stale

#47 - BeautifulSoup soup is not installed when going through the install instructions

Issue - State: closed - Opened by nonetrix almost 2 years ago - 1 comment

#47 - BeautifulSoup soup is not installed when going through the install instructions

Issue - State: closed - Opened by nonetrix almost 2 years ago - 1 comment

#46 - Deepspeed Error on Windows - LINK : fatal error LNK1181: cannot open input file 'aio.lib'

Issue - State: closed - Opened by lolxdmainkaisemaanlu almost 2 years ago - 9 comments
Labels: bug, stale

#46 - Deepspeed Error on Windows - LINK : fatal error LNK1181: cannot open input file 'aio.lib'

Issue - State: closed - Opened by lolxdmainkaisemaanlu almost 2 years ago - 9 comments
Labels: bug, stale

#45 - Add a easy start script

Issue - State: closed - Opened by nonetrix almost 2 years ago - 4 comments
Labels: enhancement

#45 - Add a easy start script

Issue - State: closed - Opened by nonetrix almost 2 years ago - 4 comments
Labels: enhancement

#44 - fix needed to load in 8-bit precision

Issue - State: closed - Opened by Dravoss almost 2 years ago

#44 - fix needed to load in 8-bit precision

Issue - State: closed - Opened by Dravoss almost 2 years ago

#43 - Add DeepSpeed ZeRO-3 integration

Pull Request - State: closed - Opened by ghost almost 2 years ago - 5 comments

#43 - Add DeepSpeed ZeRO-3 integration

Pull Request - State: closed - Opened by ghost almost 2 years ago - 5 comments

#42 - 8bit mode on older GPUs to reduce the VRAM usage by half

Issue - State: closed - Opened by lolxdmainkaisemaanlu almost 2 years ago - 3 comments
Labels: bug, stale

#42 - 8bit mode on older GPUs to reduce the VRAM usage by half

Issue - State: closed - Opened by lolxdmainkaisemaanlu almost 2 years ago - 3 comments
Labels: bug, stale

#41 - Couldn't start server on WSL, It always get killed

Issue - State: closed - Opened by VenkatLohithDasari almost 2 years ago - 5 comments
Labels: bug

#41 - Couldn't start server on WSL, It always get killed

Issue - State: closed - Opened by VenkatLohithDasari almost 2 years ago - 5 comments
Labels: bug

#40 - Implement ZeRO inference

Issue - State: closed - Opened by Silver267 almost 2 years ago - 25 comments
Labels: enhancement

#40 - Implement ZeRO inference

Issue - State: closed - Opened by Silver267 almost 2 years ago - 25 comments
Labels: enhancement

#39 - Unable to download models or convert them

Issue - State: closed - Opened by Manimap almost 2 years ago - 2 comments

#39 - Unable to download models or convert them

Issue - State: closed - Opened by Manimap almost 2 years ago - 2 comments

#38 - Fix an error

Pull Request - State: closed - Opened by Silver267 almost 2 years ago - 1 comment

#37 - Suggestions for a faster response?

Issue - State: closed - Opened by GrubbyGroo almost 2 years ago - 2 comments
Labels: question

#36 - 'Send last reply to input' doesn't include formatting

Issue - State: closed - Opened by chaiiiiiii almost 2 years ago - 2 comments

#35 - API docs?

Issue - State: closed - Opened by jryebread almost 2 years ago - 2 comments

#34 - Not seeing a place to upload a character

Issue - State: closed - Opened by GrubbyGroo almost 2 years ago - 1 comment

#32 - Error when trying to limit GPU memory

Issue - State: closed - Opened by ANimeisbestu almost 2 years ago - 2 comments

#31 - support for uploading tavernAI format embedded character image

Issue - State: closed - Opened by Slug-Cat almost 2 years ago - 1 comment
Labels: enhancement

#30 - Add listening port options for listening mode.

Pull Request - State: closed - Opened by 10sa almost 2 years ago

#29 - OSError: [Errno 36] File name too long

Issue - State: closed - Opened by ytpk almost 2 years ago - 4 comments
Labels: invalid

#28 - Add option to set use_cache=False when loading model to save on VRAM

Issue - State: closed - Opened by tahamirza almost 2 years ago - 4 comments
Labels: enhancement, stale

#27 - bump transformers

Pull Request - State: closed - Opened by Silver267 almost 2 years ago - 1 comment

#26 - Output of pygmalion-6b model doesn't terminate (?)

Issue - State: closed - Opened by catboxanon almost 2 years ago - 5 comments
Labels: bug

#25 - Manual VRAM/RAM layer adjustment

Issue - State: closed - Opened by Slug-Cat almost 2 years ago - 2 comments

#24 - Change `--auto-devices` and model offload behavior

Pull Request - State: closed - Opened by ghost almost 2 years ago - 6 comments

#23 - `device_map='auto'` is inserted by default

Issue - State: closed - Opened by ghost almost 2 years ago
Labels: wontfix

#22 - Feature Request: Add support for API keys.

Issue - State: closed - Opened by TheZennou almost 2 years ago - 3 comments
Labels: wontfix

#21 - Feature Request: Support for API keys.

Issue - State: closed - Opened by TheZennou almost 2 years ago

#20 - 8-bit precision not working on Windows

Issue - State: closed - Opened by minipasila almost 2 years ago - 26 comments
Labels: bug

#19 - HTML tab while running the 4chan model isnt formatting correctly.

Issue - State: closed - Opened by BushyToaster88 almost 2 years ago - 2 comments

#18 - Offering additional new features in the web ui

Issue - State: closed - Opened by TRGLN almost 2 years ago - 2 comments
Labels: enhancement, wontfix

#16 - Allow specifying the Hugging Face Git branch when downloading models

Pull Request - State: closed - Opened by ghost almost 2 years ago - 1 comment

#15 - Server.py start-up error with "Torch not compiled with CUDA enabled"

Issue - State: closed - Opened by KnightChaser almost 2 years ago - 10 comments
Labels: help wanted, wontfix

#14 - Doesn't run on colab with Pygmalion-6B / results look different on Colab

Issue - State: closed - Opened by waifusd almost 2 years ago - 18 comments
Labels: bug

#13 - Break models into pieces / safetensors support / keep session state

Issue - State: closed - Opened by Silver267 almost 2 years ago - 4 comments
Labels: enhancement

#12 - Add --disk-cache-dir and --max-cpu-mem parameters

Pull Request - State: closed - Opened by Silver267 almost 2 years ago - 3 comments

#11 - missing 4 python modules

Issue - State: closed - Opened by peteblank almost 2 years ago - 1 comment

#10 - [Feature Request] Add disk cache and Token streaming

Issue - State: closed - Opened by Silver267 almost 2 years ago - 7 comments

#9 - Downloading models from the web UI and exporting chat logs

Issue - State: closed - Opened by neuralinternet almost 2 years ago - 2 comments

#8 - Add a flag for using all CPU threads in CPU mode

Issue - State: closed - Opened by BugReporterZ almost 2 years ago - 4 comments

#7 - Error on Text Generation Related to Memory Management

Issue - State: closed - Opened by ZachLorenzo almost 2 years ago - 2 comments

#6 - `download-model.py` script not working

Issue - State: closed - Opened by disarray2077 almost 2 years ago - 2 comments

#5 - Are Radeon GPUs supported?

Issue - State: closed - Opened by fromtheeast710 almost 2 years ago - 2 comments

#4 - server.py doesn't seem to use DP/DDP for multi-GPU

Issue - State: closed - Opened by quarterturn almost 2 years ago - 7 comments

#2 - Cannot run the 4chan model

Issue - State: closed - Opened by BushyToaster88 almost 2 years ago - 2 comments

#1 - Problem with installation

Issue - State: closed - Opened by TRGLN almost 2 years ago - 1 comment