help-forum

577 threads · Page 7 of 12

Loading larger models 5 messages
Hardware Linux Setup
Traceback 9 messages
Windows
Long Term Memory Extension Error, Please help me or santa will kill you in your sleep. 3 messages
All models suddenly failing to load "unpack requires a buffer of 4 bytes" 2 messages
Gradio Windows
Webui is too slow, but not consuming too much resources 5 messages
Windows
need to integrate the webui to a python code 2 messages
Windows
Yi-34B 200k based models double spaces in notebook mode 6 messages
ElevenLabs - Still supported? 2 messages
Hello to everyone , I run ggml-model-q4_0.gguf . It is talking in very poor english (-it seems to me 19 messages
UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 451: character maps to 2 messages
Can't install: No module named 'conda' 2 messages
Text output error □□□□□□□□□□□□ 2 messages
"load_model_wrapper" & "IndexError: list index out of range" errors 3 messages
Setup
Issue with rocBLAS on amd rx 580 31 messages
dolphin-mixtral8x7b_4km not loading --please help! 42 messages
Linux Setup AMD
Continue generation via API 13 messages
Trying to run TheBloke_dolphin-2.5-mixtral-8x7b-GPTQ getting an error with every model loader 2 messages
slow generation on GTX4080 13 messages
PC resources maxing out, Dolphin-mixtral extremely slow 164 messages
Running out of VRAM even with --gpu-memory set 9 messages
Linux
Slow text generation in latest versions with llama.cpp 2 messages
Prompt from Python script 5 messages
Prompts & Characters Windows
ERROR: byte not found in vocab: ''Segmentation fault (core dumped) 4 messages
Taskweaver WebUI Question 4 messages
Superbooga loading txt files added permanent? 3 messages
Why doesn't it stream the tokens? 13 messages
Windows
requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=80): Max retries exce 4 messages
Windows
Getting no answers. Stuck in "Is typing.." 2 messages
Windows
I can't get multimodal to run 4 messages
is it possible to Run Mixtral8x7B? 18 messages
Why am I getting this error? When I try to load any preset I get this. Reinstalling the interface to 11 messages
Mistral MOE loading? 6 messages
ggml_new_object: not enough space in the context's memory pool 2 messages
can I use the new opensource Mistral 8x7B model that is supposedly better than gpt 3.5 locally? 64 messages
Hardware Setup Windows
Trouble downloading/loading 2 messages
OobaBot not connecting 19 messages
AutoAWQ? 2 messages
Add mixtral compatibility 193 messages
Optimal way of running a LLM 15 messages
Hardware Windows
slow answer...Hello all of you. 2 messages
Does anyone have a python token streaming example code using the API? 10 messages
Inference speed slows down drastically as context window fills up. 2 messages
Windows
large Context Testing 7 messages
Windows
Seeking a webui to permit remote queries to vector db 3 messages
Problem to install llama cpp 16 messages
Linux
Slow Answers 9 messages
Hardware Setup LLaMA Windows
Wizard-Lm-7B Generating random gibberish on 1660 ti 3 messages
Windows
How to work with the api? 5 messages
Prompts & Characters
Can't chat 2 messages
Linux Gradio
How to prevent ai reply from emoticon, or emotion 15 messages
LLaMA Windows