help-forum
Strange symbols (New stupid question)
Gibberish output from model
Where exactly do I set "trust_remote_code=True"?
I keep getting Alc _ _ Alc _ Alc as the output when talking to the model
to create public link set share=true
Is there an API call that gets me the token counts for a prompt?
API not working right.
missing "load model" button
webui cpu setup
Setup
LLaMA
Windows
Performance CPU bound when generating on a 4090
(Solved) SD API endpoint
Windows
API error
Windows
[RESOLVED] OSError: Error no file named pytorch_model.bin
Setup
Windows
New Install not loading GGML model
LLaMA
How to not let character not make things up
Training LoRA to speak like an author
what is the best approach for generating small chunks of text, using several examples as a base ?
public link
Failed to load GPTQ-for-LLaMa
Setup
LLaMA
Windows
ModuleNotFoundError (Mac)
Gradio
Setup
llama stopped generating
LLaMA
Windows
Unable to Load "TheBloke/WizardLM-30B-Uncensored-GPTQ"
LLaMA
Windows
Need help with installing with AMD ROCm 5.4.2
Linux
Setup
AMD
"is this really a GGML file?" error
Different results through webui vs api
Gradio
Prompts & Characters
Problem loading 13b GPTQ models
how to load pytorch_models?
bitsandbytes.nn' has no attribute 'Linear4bit'
Setup
Windows
CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)
LLaMA
Windows
server.py loaded correctly, but another PC was refused to visit WebUI server
Windows
Getting memory error when running server.py
Hardware
How to download other models after initial setup?
Traceback when loading LoRA "AttributeError: ... no attribute 'disable_adapter'
Windows
Traceback error when loading model
training a lora to help with the implementation of 3d printing or laser cutting possible ?
Setup
Windows
Issues with Wizard mega 13B
need help making a memory/chatlog to use with api
Linux
Gradio
Prompts & Characters
Windows
Calling API for different users
Gradio
Prompts & Characters
Pygmalion-Metharme-7b-4bit-TopScore : Repeats itself after 6 responses
optimizing CPU mode for GGML models like Wizard Mega 13B
Hardware
Setup
LLaMA
Windows
how to gather scrape data for training lora?
How can I learn more about configuring existing models?
Web UI loaded correctly but no response with Generate button pressed
Setup
LLaMA
Prompts & Characters
Windows
Training on dataset errors out but training on raw text is fine
Getting lots of "error loading model: unknown (magic, version)" for multiple models.
AMD
Windows
can't load characters on multiple models
Prompts & Characters
Windows
Unable to access webui, hosting on GCP instance (port 7860 filtered)
Linux
Setup
Managing context with API
Prompts & Characters
GPT4-x-Alpaca30b does a weird text token thingy idk what to describe it as
LLaMA
Windows
Which datasheet to use to train for javascript, php, node js, html, css web programming?