Hugging Face's logo

TheBloke
/
Wizard-Vicuna-13B-Uncensored-GPTQ

Text Generation
Transformers
Safetensors
English
llama
uncensored
text-generation-inference
4-bit precision
gptq
Model card Files Community
24
New discussion

Adding Evaluation Results
#24 opened 6 months ago by leaderboard-pr-bot

Adding Evaluation Results
#23 opened 7 months ago by leaderboard-pr-bot

import crash
#22 opened 10 months ago by xevilstar

Adding Evaluation Results
#21 opened 12 months ago by leaderboard-pr-bot

Model generates only censored content

1
#20 opened about 1 year ago by fakelifesucks

Can we have more bit and group size combinations like in other models?
#19 opened about 1 year ago by teefan

Prompt formats and referencing the user or model by a specific name?

2
#18 opened over 1 year ago by Mincookie

Speed up inference

3
#15 opened over 1 year ago by mr96

RuntimeError: CUDA error: an illegal memory access was encountered
#14 opened over 1 year ago by Nafnlaus

Lora Upload Dtype Error - Solved
#13 opened over 1 year ago by Jaragua

Unable to load GPTQ model, despite utilizing autoGPTQ

2
#11 opened over 1 year ago by DarvinDelray

It wont load

2
#9 opened over 1 year ago by GaymerDanny

Error no file named...

1
#8 opened over 1 year ago by solotrek

Can't see it better than the censored one. Some advise?

2
#7 opened over 1 year ago by anon7463435254

Model doesnt load

1
#5 opened over 1 year ago by agonzalez

TheBloke is GOAT

2
#4 opened over 1 year ago by hussainwali1

Error when loading the model in ooba's UI (colab version)

14
#3 opened over 1 year ago by PopGa

Gibberish on 'latest', with recent qwopqwop GPTQ/triton and ooba?

7
#2 opened over 1 year ago by andysalerno

DefaultCPUAllocator: not enough memory

5
#1 opened over 1 year ago by VladCorvi