help-forum
Llama CPP GPU offloading doesn't work for me. (Windows)
Hardware
Windows
Constant Error No module named 'monkaypatch'
Setup
--listen isn't working
Windows
Error loading ExLlama extension
Updated WebUI and now it's not loading at all
Searching for oobabooga WebUI alternative
what does this mean when i try to load a model ?
ERROR: Failed building wheel for llama-cpp-python
Windows
Clobber errors - Can't get the UI to work (solved)
Setup
Windows
Slow Exllama performance?
M1/ M2 Mac and memory questions
Hardware
API Endpoints?
Prompts & Characters
Windows
wont load model on latest version
Upgraded to 3060, but ooba won't run with it and kicks down to CPU mode.
Hardware
Windows
Unable to load GGML Models with Llama.cpp
Linux
LLaMA
DLL error when loading any GPTQ model with exllama
Windows
Response text generation is too slow.
Linux
Hardware
--share = True
Windows
Please help to apply Lora
what settings, tools and prompts are recommend when generating a detailed alternate history scenario
Setup
Prompts & Characters
No models working on latest version of WebUI
Basic Newbie Questions
how are flags supposed to be used? where do i input them?
Older version of WebUi
how do I use llama ccp backend instead of transformers
messed up conda install?
Linux
Dual GPU setup?
Windows
Unable to get 30b model to load (size mismatch for model.embed_tokens.weight)
LLaMA
Windows
Error code: 404 for API url
Windows
Output is cut off prematurely.
pygmalion-13b-4bit-128g error after working fine for (5 to 12 prompt)
Linux
Windows
WARNING:The safetensors archive passed at models\TheBloke_Wizard-Vicuna-13B-Uncensored-GPTQ\Wizard-V
Windows
Issues after extraction of packages with one-click installer (Windows)
Hardware
Setup
Windows
A bit confused, or: looking for Documents
WARNING:The model weights are not tied.
Gradio
Setup
LLaMA
Windows
Garbage output with GGML and cublas
low token (SOLVED)
Setup
Prompts & Characters
Hardware
Windows
LLaMA
Trouble with GTPQ training
llamacpp token generation
LLaMA
Windows
Character Datasets for LoRA Training
Terrible performance with 13b GPTQ, confirmed using GPU
Linux
Hardware
How to simply load a model without webui
Setup
Windows
More extensions for oobabooga?
Lora Training
cannot load GPTQ model
Linux
LLaMA
llama 7b crash run out of vram
Linux
LLaMA
Choosing a model for LoRA training
Hardware
LLaMA
2.7b 6.7b 13b 30b ram requirements?
Hardware
Windows
API ignores stopping string
Windows
How do i safely delete all Files Ooga booga installed?