anon8231489123/vicuna-13b-GPTQ-4bit-128g

#55 opened 10 months ago by

WayneTheWiz

can we use it for commercial use ?

#53 opened 11 months ago by

balajim27

Can it be trained after quantization? How to do it?

#52 opened 11 months ago by

haluna

Web UI loaded correctly but no response with Generate button pressed

#49 opened 11 months ago by

pkr8

Multiple-GPUs

#48 opened 11 months ago by

taoq22

Can we finetune the GPTQ model ?

#47 opened 11 months ago by

thisislsj

Bot Stuck On "Is Typing", CMD Error Code Included

#46 opened 12 months ago by

LoganG045

how to use this model

#45 opened 12 months ago by

william0014

Issue Editing Start.bat webui

#44 opened 12 months ago by

LoganG045

WebUI doesn't start

#43 opened 12 months ago by

Dany19212050

Responses stop loading in.

#42 opened 12 months ago by

Setphus

Shape invalid for input size 0

#40 opened 12 months ago by

anon325543

Getting model not found error

5

#39 opened 12 months ago by

drathi

Am I delusional or is this model much better than the newly trained ones?

#37 opened about 1 year ago by

samjack

how does one train this model with your own documents like how chatbase does it?

#36 opened about 1 year ago by

arjunkrishna

Problem with start-webui start-up. Help pleas

#35 opened about 1 year ago by

Holipoli

[GUIDE] Installing Vicuna on Linux

15

#34 opened about 1 year ago by

ltnn1

Problem when starting web UI, when I I want to type or chat, it only shows the assistant as "Typing"

#33 opened about 1 year ago by

Alphafi

Problem with start-webui start-up. Help please

5

#32 opened about 1 year ago by

Maximiliano228

Newbie question - My responses are all jibberish

#31 opened about 1 year ago by

qikappcn

how to convert the safetensors to pth?

#30 opened about 1 year ago by

goathacker

New weights of Vicuna (v1.1) are available. Could you update the weights?

#29 opened about 1 year ago by

lmzheng

where could find 30B vicuna

#28 opened about 1 year ago by

baby1

Failure to load using DeepSpeed

#27 opened about 1 year ago by

Hazarth

Why did Steve Jobs get fired from Apple?

#26 opened about 1 year ago by

TheBobDoleExp

AI asks and answers itself errors

5

#25 opened about 1 year ago by

terbina

Issue with starting "Start-WebUI" bat.

4

#24 opened about 1 year ago by

Miltank

How to use this model ?

#23 opened about 1 year ago by

Kevy

is there a way to run this on Mac?

#20 opened about 1 year ago by

pandoraSama

Any chances/plans for an unfiltered version of this model?

#19 opened about 1 year ago by

9cento

Curious this model able to run on 3060 12g?

6

#18 opened about 1 year ago by

cyx123

New to this . . .

#17 opened about 1 year ago by

PaintedDreams

pytorch_model.bin.index.json out of date

#15 opened about 1 year ago by

DataPhreak

torch.cuda.OutOfMemoryError: CUDA out of memory. with a RTX3070 8gb

12

#14 opened about 1 year ago by

VAVUSH

do you have 8bit version? with 8bit works better than 4bit?

#13 opened about 1 year ago by

cowboymind

CUDA Setup failed despite GPU being available

#12 opened about 1 year ago by

Giaser

I keep getting this: ImportError: Using `load_in_8bit=True` requires Accelerate

40

#11 opened about 1 year ago by

Zelan

7B version

#10 opened about 1 year ago by

Yuuru

Bug: `Encountered 1 file(s) that may not have been copied correctly on Windows: vicuna-13b-4bit-128g.safetensors`