help-forum
cannot load Llama 3.1
torch not built with cuda error
Setup
Windows
Newly installed system, no prevalent errors but outputs are totally random
Setup
Prompts & Characters
Windows
Sharing api on network
Referencing Valid URLs in replies.
Trying to understand how to get Superbooga v2 functioning as intended.
Windows
GGUF split
cannot run with silly tavern
Strange startup error
Setup
Windows
OSError: models\mixtral-8x22b
Prompts & Characters
AMD
Windows
Moin, torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 28.00 MiB. GPU 0 has a tota
text web ui API on applying chat template for llama 3
Serving an LLM: Models and Parameter|Generation Tabs?
Setup
Prompts & Characters
Windows
Invalid HTTP request: router problems?
Possible remote code on my webui?
Trojan and threat warnings from the port I have textweb ui?
Fusing Layers never finishing
Linux
Setup
AMD
What is the difference between SuperboogaV1 and SuperboogaV2?
Hardware
Setup
Windows
How to change the local IP or PORT for Oobabooga?
Setup
Windows
truncation length issue
xTTS and Conqui TTS blank/partial messages
CUDA out of memory
Windows
Everytime i try to load a character from characterhub this appear, what can i do?
AttributeError: namespace object has no attribute 'no_stream'
Trying to deploy to Spaces from Colab
RuntimeError: CUDA error: device-side assert triggered
Problem with deploying gradio: Error 504
Could not load the model because a tokenizer in Transformers format was not found.
Getting HTTP Error 404
Optimize inference
Sometimes the model breaks and only prints token 81918
LLaMA
Windows
Error generating text, getting no text in response
AttributeError: 'MistralAWQForCausalLM' object has no attribute 'dtype'
Prompts & Characters
Windows
NotImplementedError: Cannot copy out of meta tensor; no data!
How do you make AI use less emoji's frequently?
Models won't load
Problem after starting start_windows.bat
Windows
cant get silero_tts to work
Invisible Answers
Can't run these models; AttributeError: 'LlamaCppModel' object has no attribute 'model'
LoneStriker_Llamix2-MLewd-4x13B-3.5bpw-h6-exl2-2 Dont know how to set up
API Output Trash Compared to WEBIU Chat inference
Openai API prompt as TGWU
CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)`
Windows
Nonsense output
Windows
Is It Possible to Give Models Web Access?
CUDA Out of memory - The longer a conversation goes
llama
LLaMA
Warnings upon loading model
Windows
Can't load command-r models after webui update
Windows