help-forum

577 threads · Page 4 of 12

AssertionError: Total sequence length exceeds cache size in model.forward 8 messages
exl2 model error: 'Nonetype' Object is not subscriptable 20 messages
Windows
I can't load an AI model (any model) into the program. 2 messages
[HELP] RuntimeError: CUDA error: device-side assert triggered 30 messages
Windows
Suddenly really bad responses 21 messages
Python code request to api for responds generation. 20 messages
What's even the point of this Discord server? 15 messages
Really slow generation times 12 messages
Hardware Windows
Queuing Requests or Parallel Operations in Ooba API 18 messages
WebUI on Tesla p40 5 messages
can't update anymore 6 messages
Setup Windows
Llama 3 instruction template 3 messages
CodeQwen EXL2 error on load 3 messages
In which file please ? (llm_int8_enable_fp32_cpu_offload) 6 messages
Windows
Need help sorting out the stopping strings for LLAMA 3. 11 messages
disable skip special tokens from openAI api 20 messages
How to build llama.cpp with cuda on windows? 10 messages
Exllamav2 issues on linux + AMD 11 messages
Linux Setup AMD
Text Generation issue with characters that have large tokens. 19 messages
Linux LLaMA Prompts & Characters
how can i install WizardLM-2? the One that supposedly beats gpt-4-0314? 12 messages
Hardware Setup Prompts & Characters Windows
Superbooga 7 messages
Error whenever loading an AWQ Model. 3 messages
Windows
AI generates random things the first time, but works in future attempts if I don't change the prompt 4 messages
Windows
Can't load previous models 2 messages
Running Command R+ on 70GB vram? 7 messages
Suggestions of light models for the following Gamer PC and a Macbook Air M1 2 messages
Windows
I can't load a model 3 messages
Segmentation fault (core dumped) 2 messages
AssertionError: Torch not compiled with CUDA enabled 3 messages
Windows
increase output 8 messages
Windows
What size EXL quants can my rig run? 128GB RAM, RTX 4060 TI 3 messages
Interface does not see models folder 2 messages
Windows
After updating I cannot run models that I have run before. It says out of memory. 2 messages
Windows
Cheap accelerator for local AI? 7 messages
coding with ai 4 messages
Windows
Whisper STT Error 3 messages
Gradio Setup Windows
Running Models via CLI on Jetson AGX Xavier with Dusky Container 2 messages
With --multi-user and --gradio-auth-path in flags, users cannot use model 5 messages
Gradio Windows
Unable to install TheBloke/dolphin-2.6-mixtral-8x7b-GPTQ 12 messages
Setup Windows
Models outputs gibberish 6 messages
Understanding Different Quantisation Techniques in Model Names 17 messages
Issue with whisper (unhashable type: 'list') 2 messages
Gradio Windows
No module named 'soundfile' 9 messages
websocket not found 2 messages
Gradio Windows
assistance regarding model downloading 17 messages
API Error With LangChain 2 messages
Need to extend context in some form from 20k 5 messages
AutoAWQ not working 11 messages
Setup Windows
What are Instruction and Chat templates, and how do I use them? 105 messages
Setup Prompts & Characters Windows
Trouble installing the oobabot-plugin 9 messages
Windows