help-forum

805 threads · Page 16 of 17

RWKV from ui? 63 messages
[docker setup] GPU works but its not used 22 messages
serialized input error after fresh install 17 messages
Oogabooga Arguments 33 messages
Gradio Setup Windows
Pyg7b - Can't determine model type from model name. 9 messages
Gradio LLaMA Hardware Windows
StableLM Guide? 3 messages
StableVicuna-13B Guide? 2 messages
"IndexError: index 32 is out of range" and "RuntimeError: Error(s) in loading state_dict for Llama" 3 messages
Gradio Windows
Some Cuda; Bitsandbytes and PyTorch errors when installing the webui. 2 messages
Windows
Text-generation-webui with ROCM 73 messages
Linux Hardware AMD
Can't start with monkey_patch enabled 9 messages
Setup Windows
Gradio leaves Port in Use on Restart or Terminate 8 messages
I have 8 A100 GPUs...is there a guide to training a non lora model and inferencing with lora after? 2 messages
how to setup GPTQ-for-LLaMa one click installer? 4 messages
Setup LLaMA Windows
FileNotFoundError: [Errno 2] No such file or directory, with MetaIX_GPT4-X-Alpaca-30B-4bit 18 messages
Linux LLaMA
Problem with TheBloke_vicuna-13B-1.1-GPTQ-4bit-128g 4 messages
This extension for Discord bot is not working for me 47 messages
Massive slowdown with longer conversations well past token limit. 22 messages
Windows
can someone help me train a model? 100 messages
Ooobabooga refusing to run on3060 2 messages
new gptq-for-llama update is slow? 38 messages
Setup LLaMA Windows
https://github.com/haotian-liu/LLaVA 2 messages
training pythia 410M 2 messages
Windows
problem with the output 2 messages
Prompts & Characters LLaMA Windows
critical libmamba error 2 messages
Setup Windows
llama to vicuna install, what could possibly go wrong? 7 messages
Linux Setup LLaMA
Loading the Example.yaml doesn't work 6 messages
Prompts & Characters Windows
Trying to get 30b 4bit running on 4090 13 messages
Linux
Trouble getting Text Generation WebUI to work for the first time 14 messages
Cuda model no longer working 42 messages
Setup Windows
Ways to increase token/second? 2 messages
Windows
[SOLVED] Could not find the quantized model in .pt or .safetensors format, exiting... 9 messages
Linux
llama-7b-4bit quickly turns to programming discussion 5 messages
Prompts & Characters LLaMA Windows
CPU Allocator: Not Enough Memory 28 messages
LLaMA
Some models generating gibberish 16 messages
How do I get Vicuna to work on this? 8 messages
GPT4 x Alpaca: torch.cuda.OutOfMemoryError: CUDA out of memory. 4 messages
Windows
declare-lab/flan-alpaca 2 messages
Text only generates at full speed when in a different tab 8 messages
Gradio LLaMA Windows
anon8231489123_gpt4-x-alpaca-13b-native-4bit-128g 11 messages
Telsa K80 help 84 messages
OSError: models/pygmalion-6b_sharded is not a local folder 36 messages
Setup Windows
TavernAI: (ForbiddenError: invalid csrf token) 13 messages
Windows
adding extensions / augmenting character context 6 messages
Gradio Prompts & Characters
Training your own LoRa 2 messages
How would one use the training tab? 19 messages
How to run gpt-4chan? TypeError: expected str, bytes or os.PathLike object, not NoneType 9 messages
settings.json 12 messages
How does the API work? 195 messages
Error in screenshot. (Solved.) 6 messages
Setup LLaMA Windows