help-forum

577 threads · Page 6 of 12

"/v1/models" API Endpoint no longer returning all models after update 2 messages
Traceback Error when loading model 5 messages
Setup Windows
Out of memory when loading model 48 messages
Windows
Min-p preset broke down after the the update 6 messages
Windows
Lora Training and Datasets 2 messages
Linux
Using API (SillyTavern) with identical settings to OobaBooga webUI creates identical gens in API 15 messages
Linux LLaMA
Can not install oobabooga on ubuntu 22.04 12 messages
Linux Setup
why latest webui (checkpoint 28 - 1 - 2024) have slower t/s compare to the previous from october?? 4 messages
Web interface not rendering properly. 2 messages
How can I train a model using a hosted GPU? 9 messages
Linux Setup
How can i send a prompt via api to change character persona? 2 messages
Prompts & Characters
I got this error when I try to run exllamav2 loader. 2 messages
Perfomance lost in multiGPU CUDA 18 messages
Hardware
Help with the API extension 71 messages
Setup
I installed the latest snapshot from scratch, but my chat quality is garbage. 8 messages
Setup Prompts & Characters Windows
how could chatml template be broken for one model but not another? 12 messages
How to regenerate or continue generation with API 3 messages
Prompts & Characters Windows
Memory sliders are ignored when loading Mistral-Instruct-0.2-AWQ 11 messages
Sillytavern works, but doesn't stream 3 messages
CPU models only download a few kilobytes 16 messages
Weird context length issue 10 messages
Windows
What is the quickest way to determine version/revision that is currently installed on my linux box? 8 messages
API Issue 6 messages
Silly tavern Api issue 113 messages
Linux
ngrok slow generation 3 messages
q_weight and gptq_qzeros have incompatible shapes 4 messages
AMD/CPU/NVIDIA - Trying to Run 1 but not the other 2 messages
Setup Windows
Cannot Load Any Large Model 4 messages
Can't load any model, due to Exceptions 25 messages
Setup Windows
Loading model on multiple GPUs 2 messages
Network Error While Loading Large Model 5 messages
help 2 messages
Model loading error. 26 messages
Setup Windows
Api URL not working anymore 403 messages
Setup Windows
Localhost Error 4 messages
Setup
Error load_model_wrapper, load_model and llamacpp_loader, index out of range 6 messages
TextGenUi not using GPU 2 messages
Hardware Windows
Setting up OpenAI compatible API with mistral model 5 messages
Starting only the Openai Server without having to go through the UI process. 9 messages
Performance deteriorates with longer chat 3 messages
Stop AI from writing actions and dialogue for the user 5 messages
Windows
long term memory 7 messages
Loading saved instruction templates works but causes UI error 2 messages
Mixtral LLMs 3 messages
How to make model directory compatible with LM Studio? 61 messages
Setup Windows
RuntimeError: No HIP GPUs are available 29 messages
Linux Setup AMD
My WebUI is supper slow and takes forever to respond, Please Help D: 16 messages
ROCm LoRA Training 4 messages
Linux LLaMA AMD
Noob looking for help on Ooba/RunPod 5 messages
Setup
elevenlabs extension 2 messages
Windows