help-forum

805 threads · Page 14 of 17

Llama CPP GPU offloading doesn't work for me. (Windows) 3 messages
Hardware Windows
Constant Error No module named 'monkaypatch' 7 messages
Setup
--listen isn't working 7 messages
Windows
Error loading ExLlama extension 4 messages
Updated WebUI and now it's not loading at all 2 messages
Searching for oobabooga WebUI alternative 4 messages
what does this mean when i try to load a model ? 5 messages
ERROR: Failed building wheel for llama-cpp-python 3 messages
Windows
Clobber errors - Can't get the UI to work (solved) 6 messages
Setup Windows
Slow Exllama performance? 3 messages
M1/ M2 Mac and memory questions 9 messages
Hardware
API Endpoints? 8 messages
Prompts & Characters Windows
wont load model on latest version 183 messages
Upgraded to 3060, but ooba won't run with it and kicks down to CPU mode. 75 messages
Hardware Windows
Unable to load GGML Models with Llama.cpp 3 messages
Linux LLaMA
DLL error when loading any GPTQ model with exllama 3 messages
Windows
Response text generation is too slow. 28 messages
Linux Hardware
--share = True 11 messages
Windows
Please help to apply Lora 7 messages
what settings, tools and prompts are recommend when generating a detailed alternate history scenario 2 messages
Setup Prompts & Characters
No models working on latest version of WebUI 3 messages
Basic Newbie Questions 29 messages
how are flags supposed to be used? where do i input them? 2 messages
Older version of WebUi 106 messages
how do I use llama ccp backend instead of transformers 8 messages
messed up conda install? 3 messages
Linux
Dual GPU setup? 11 messages
Windows
Unable to get 30b model to load (size mismatch for model.embed_tokens.weight) 3 messages
LLaMA Windows
Error code: 404 for API url 2 messages
Windows
Output is cut off prematurely. 15 messages
pygmalion-13b-4bit-128g error after working fine for (5 to 12 prompt) 4 messages
Linux Windows
WARNING:The safetensors archive passed at models\TheBloke_Wizard-Vicuna-13B-Uncensored-GPTQ\Wizard-V 2 messages
Windows
Issues after extraction of packages with one-click installer (Windows) 3 messages
Hardware Setup Windows
A bit confused, or: looking for Documents 13 messages
WARNING:The model weights are not tied. 16 messages
Gradio Setup LLaMA Windows
Garbage output with GGML and cublas 3 messages
low token (SOLVED) 89 messages
Setup Prompts & Characters Hardware Windows LLaMA
Trouble with GTPQ training 45 messages
llamacpp token generation 6 messages
LLaMA Windows
Character Datasets for LoRA Training 2 messages
Terrible performance with 13b GPTQ, confirmed using GPU 15 messages
Linux Hardware
How to simply load a model without webui 9 messages
Setup Windows
More extensions for oobabooga? 12 messages
Lora Training 20 messages
cannot load GPTQ model 4 messages
Linux LLaMA
llama 7b crash run out of vram 7 messages
Linux LLaMA
Choosing a model for LoRA training 74 messages
Hardware LLaMA
2.7b 6.7b 13b 30b ram requirements? 12 messages
Hardware Windows
API ignores stopping string 43 messages
Windows
How do i safely delete all Files Ooga booga installed? 6 messages