help-forum
AWQ Context leakage between modes
Linux
Update issue
[SOLVED] KeyError: 'user_input' when using API example
ERROR: HTTP error 404 while getting flash_attn2.3.2
Setup
Windows
unable to load model - meta tensor; no data
No responses and Cuda error with "TheBloke_CodeLlama-7B-Instruct-GPTQ"
Linux
pulled latest version from git and get a gradio Dropdown() error
Linux
Error after git pulling and updating:
Linux
Adding extensions
Is there an alternative chat interface I can use that remembers past conversations using embeddings?
Linux
Prompts & Characters
Cant seem to get Textgen webui api to respond with different response.
Setup
Windows
Benchmarks & Which GPU should I get ?
Linux
LLaMA
Too slow text generation
Can't load models (Fixed)
Windows
Issue loading models with llama.cpp
Linux
LLaMA
AMD
Error downloading/loading model? pygmalion 13B
How to Check Logs? (TextGen Ui Crashes with Unknown reasons)
"Best" recent models
Extensions- Whisper_stt Having Issues
AI stops generating after a while
Windows
grammar_string usage with llama.cpp loader
Exllama 2 on Ooba?
Cannot install on ubuntu
Linux
Setup
I open the UI with my phone using the same WiFi, but it seems like it's not secure
Windows
Cuda out of memory
Output to SillyTavern from Ooba not working
Windows
Use GPU for embeddings?
IndexError: list index out of range
LLaMA
Windows
Using EXL2 models for faster tickets
Gradio
LLaMA
Windows
Was hoping if I gave it a while then reinstalled WebUI would work again, but here we are
Can't get cuBLAS working
Windows
Gpu layers and threads, how much i can set
OSError: models/... does not appear to have a file named config.json.
Linux
Setup
Api Import requests failed (Solved)
Why does WebUI do this?
LLaMA
Windows
First time trying to run.
How to use grammar for dummies?
GGUF settings
Hardware
Windows
exllamav2 with flash-attention under wsl (OneClick installer)
Setup
Illegal instruction (core dumped) - Ubuntu 22.04 - conda - no gpu - openstack vm
Linux
LLaMA
ExllHFv2 Error
Hardware
Setup
Windows
--model-dir doesn't get found
Exllv2 Docker Issue
CUDA out of memory
Different result when use same model with opena ai and webui
Whisper STT broken
Response times with GGUF are catastrophic
Exception: You are using an outdated GGUF, please download a new one.
Exllv2/ExllHFv2 errors
LLaMA
Am I making a mistake? Codellama-34b, Phind_Codellama-34b, etc
Linux
LLaMA