help-forum

Not sure how setup hosting 2 messages

Jul 9, 2023, 6:40 PM Gradio

IndexError: list index out of range 9 messages

Jul 9, 2023, 2:50 PM

Oobabot installation help 2 messages

Jul 9, 2023, 5:52 AM

Upload History Not Recognized By Model 9 messages

Jul 9, 2023, 2:09 AM Gradio Prompts & Characters Windows

Expose server to local LAN. Is there a flag to just allow local LAN access? 2 messages

Jul 8, 2023, 1:26 PM Windows

ExLlama not working as intended 21 messages

Jul 7, 2023, 11:20 PM

GGML models are not using GPU at all 20 messages

Jul 7, 2023, 12:52 PM

Oobabooga api and streaming url not found 8 messages

Jul 7, 2023, 1:20 AM Windows

Using Text-Gen GGML (CPU ONLY) 6 messages

Jul 6, 2023, 10:54 PM Setup LLaMA

Function Calling 22 messages

Jul 6, 2023, 8:58 PM LLaMA

Getting error trying to use EX_Llama 20 messages

Jul 6, 2023, 7:05 PM

Gradual slowdown as the chat gets longer, normal or not? 7 messages

Jul 6, 2023, 2:03 AM

EleutherAI/pythia-1b-deduped wont load under any model loader. 2 messages

Jul 5, 2023, 11:30 PM Windows

Solved | RuntimeError: DefaultCPUAllocator: not enough memory: you tried to allocate 238551040 bytes 6 messages

Jul 5, 2023, 8:47 PM Setup Windows

How to ask questions about custom data? 8 messages

Jul 5, 2023, 7:48 PM

Not getting a link. No errors just... nothing 2 messages

Jul 5, 2023, 7:39 PM

New installation, fails to load model 4 messages

Jul 5, 2023, 6:58 PM

line 134, in download_model_wrapper downloader = downloader_module.ModelDownloader() TypeError: Mode 12 messages

Jul 5, 2023, 3:22 AM

2 mismatched GPUs 17 messages

Jul 4, 2023, 9:04 AM

What is the difference between chat, chat-instruct and instruct ? 13 messages

Jul 4, 2023, 8:27 AM

TypeError: arange() received an invalid combination of arguments 11 messages

Jul 4, 2023, 4:18 AM Linux LLaMA

RuntimeError: CUDA error: an illegal memory access was encountered 5 messages

Jul 3, 2023, 6:24 PM Linux LLaMA Hardware

How do i open the WebUI? 18 messages

Jul 3, 2023, 4:28 PM

Selecting GPU over CPU? 7 messages

Jul 3, 2023, 1:18 AM

Unable to run xformers 4 messages

Jul 2, 2023, 5:00 PM

0.2 tokens/s when reaching context size limit 24 messages

Jul 1, 2023, 9:09 PM

Ran Update Script, Now Broken (Windows) 27 messages

Jul 1, 2023, 6:01 PM

please help to run 2 GPU with ooba 3 messages

Jul 1, 2023, 5:41 PM

does text-generation-webiui has api? 51 messages

Jul 1, 2023, 3:52 PM

compile llama on linux 5 messages

Jul 1, 2023, 1:53 AM

Newest update failing 40 messages

Jun 30, 2023, 3:17 AM

RuntimeError: data. DefaultCPUAllocator: not enough memory: you tried to allocate 238551040 bytes. 5 messages

Jun 29, 2023, 8:22 PM Setup Windows

.BAT FILE FAIL 13 messages

Jun 29, 2023, 10:57 AM Setup Windows

INCREASE RESPONSE LENGTH? 4 messages

Jun 29, 2023, 10:48 AM Gradio Windows

Exception: Model couldn't generate your text, probably it's too long 5 messages

Jun 29, 2023, 10:24 AM

API broken after Update - SOLVED 4 messages

Jun 28, 2023, 8:00 PM

Disable default load model 2 messages

Jun 28, 2023, 6:18 PM

Update process is outputting errors. 2 messages

Jun 28, 2023, 5:25 PM Windows

Different speeds in UI vs console 5 messages

Jun 28, 2023, 11:35 AM

Model way too creative, inventing too much stuff. 15 messages

Jun 28, 2023, 1:18 AM

Webui cpu to gpu 2 messages

Jun 28, 2023, 12:12 AM Setup

adapter_config.json 2 messages

Jun 27, 2023, 9:48 PM

SuperHOT 8k Model for ExLlama as GPTQ or FP16? 3 messages

Jun 27, 2023, 9:12 PM Setup LLaMA Windows

LLamacpp GPU acceleration 19 messages

Jun 27, 2023, 7:14 PM Setup Windows

Installing cuda extensions problem 6 messages

Jun 27, 2023, 6:03 PM

I'm having problems with the "--api" flag 4 messages

Jun 27, 2023, 4:39 PM Setup

Downloading with zip 2 messages

Jun 26, 2023, 4:49 AM Linux Setup

30B Model "out of memory" autogptq-for-llama "only support 2,3,4 and 8 bits" 9 messages

Jun 25, 2023, 11:33 PM Linux

Faster Contrastive search? 4 messages

Jun 25, 2023, 9:00 PM

I cant load models 10 messages

Jun 25, 2023, 12:08 PM Setup Windows