help-forum

577 threads · Page 8 of 12

Batch Prompt Raw Data? 4 messages
Windows
Possible to get webui to remember parameters? 9 messages
I can't start qwen 72b 69 messages
Pass stopping criteria through API 4 messages
is there a way to reduce the output lenght? 2 messages
Brand new install of text-generation-webui doesn't support Zephyr (Mistral) GPTQ 2 messages
Running as a daemon 4 messages
roBLAS error and CUDA 98. How do I fix those? 10 messages
Want to try running some local LLMs, getting error when attempting to generate. 3 messages
Setup Windows
--listen checkbox in webui doesn't do anything... I have to call it directly with commandline 2 messages
Windows
DLL load failed while importing flash_attn_2_cuda: The specified module could not be found. 3 messages
Who is Chiharu Yamada? 6 messages
Gradio Windows
ERROR:Failed to load the extension "superbooga" 3 messages
Windows
Issues hosting local api 27 messages
Setup Windows
Starting out, performance woes 7 messages
Hardware Setup Windows
Error with loading Llama 2 on Mac 21 messages
Gradio Setup LLaMA
VPet openai api 2 messages
Generating nonsense 7 messages
Prompts & Characters
Can't use API 62 messages
GPU Usage 5 messages
Linux
LLM's not behaving like it should when running in an API workflow. 4 messages
chat memory 31 messages
How to download only 1 model 2 messages
Gradio Setup
VRAM on linux 12 messages
Linux Setup Hardware
how can i run 2 concurrent Public APIs 19 messages
Can't disable ExLlama when loading with Transformers 3 messages
Linux LLaMA
my webui can only output “□□□□□□□□□□□□□□□□□□□□□□□□” 25 messages
LLaMA Windows
Llama.cpp limited to 128 layers for n-gpu-layers? 3 messages
Setup
auto load model on startup 3 messages
Can't run as OpenAI host 5 messages
allow outside connections 7 messages
Windows
Loading model traceback error 33 messages
Windows
which architectures have problems currently? 3 messages
Max character card length? 3 messages
Prompts & Characters Windows
How do I split memory between CPU and GPU? I'm running a 13B GTPQ model. 3 messages
Windows
Unable to Load AWQ model 3 messages
TypeError: Not a string - when loading EM German Leo Mistral (any version) 2 messages
Linux
trying to train a new lora and it errors out, wizardlm 7b uncensored gptq 2 messages
Can I use Tesla GPUs to run Ooba? 5 messages
Why is the bot devolving instantly? 2 messages
Inilialism meanings 4 messages
API Usage to load and generate output 2 messages
Windows
Use multiple GPUs when loading a model 34 messages
how to use api on text-generation-wubei on postman 10 messages
Best way to be totally sure the model is running on GPU? 2 messages
Hardware Windows
Expected all tensors to be on the same device 29 messages
Linux Setup
Extremely slow generation with a 4090 13 messages
Windows
Strange responsive from LLM 3 messages
Linux
Cant see awnsers 32 messages
Vectorization Source - Chat memory help 2 messages
Prompts & Characters Windows