help-forum
What can be considered as 'best' model for instruction-chat in ooba with a 8GB card?
Windows
promt format for web generation ui model
training have been trying to train vicuna 13b to speak hinglish..it ends up speaking gibberish
ERROR: Could not build wheels for llama-cpp-python
Setup
LLaMA
xformers and model cohesion degradation...
Fine-tuning quantized Llama2
exllamav2 loading attempts - WSL2 on W11
Linux
How to load gguf format
Cannot install with the Windows Installer - OpenSSL error?
Setup
Windows
Problems when running GPTQ and GGUF models
LLaMA
Windows
Error starting .bat
Windows
oobabot-plugin
Running a larger LLM model on mix of vRAM (GPU) + RAM - possible?
Can't load any GGUF model
Windows
CUDA Out Of Memory with 0 allocated?
Windows
ModuleNotFoundError: No module named 'gptq_for_llama'
Linux
LLaMA
Llama-2 LoRA fine-tuning based on books/novels help
prompt template when streaming via port 5005
Model Reply Blank
I am getting errors about no path existing, no model being loaded and an unlocatable checkpoint file
From origin has been blocked by CORS policy
Notebook Tab - Text generation stops before 2k context is reached
Webui api returns an error while running on second gpu or split.
Linux
Setup
Hardware
Can't generate using ExLlama...
Linux
Setup
Hardware
LLaMA
Problems with autoGPTQ
Linux
gguf loads slower than ggml
Linux
LLaMA
Hardware
unrecognized arguments
[solved] error "Illegal instruction (core dumped)" when trying to use llama.cpp.
Linux
LLaMA
AMD
Windows
Absence of ExLlama.
Linux
LLaMA
AMD
Mac M1 Air issue
unexpected keyword argument 'mul_mat_q'
Gradio
Linux
Setup
Which model for my usage ?
Hardware
Setup
Windows
cuda out of memory
Linux
LLaMA
Hardware
RuntimeError: The installed version of g++ (12.3.0) is greater than the maximum req by CUDA 11.7
Linux
Can execute the start_windows.bat! There is no web ui. No nothing. Only an empty shell
Chat edit
"Continue" only adds a single word
Cant launch any models I get an error that llama.cpp is not installed. How do I install it?
Unable to load ggml-llama-q4_0.bin
Windows
Accessing web UI API through Jupyter notebook on Runpod.io
Hardware
LLaMA
Just got new error (traceback error) when trying to load model
Using default generate UI seems to create different output than the api even using same preset
The model is loaded without errors but no replies!
Hardware
Setup
Prompts & Characters
Windows
best settings for GGML models (13b), 6gb vram, 16gb ram for best speed
Windows
Download HF Model Branch
I am a complete donut and am trying to figure everything out, can I get someone to help me?
Download Llama 2 hugging face
Linux
Setup
LLaMA
Getting error in Colab
Am kind of lost even after reading the instructions
I get this error when trying to launch the start_windows.bat file