TheBloke
/

WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Resources

View closed (1)

Oobabooga Chat Errors

#9 opened about 1 year ago by

special_tokens_map.json is different from the original LlamaTokenizer file. It is either customized or outdated.

#7 opened over 1 year ago by

Use these flags to run this model and any model thats GPTQ split between gpu and cpu if you dont have enough vram

#6 opened over 1 year ago by

Struggles with outputting years

#5 opened over 1 year ago by

generating sometimes early stopped

#4 opened over 1 year ago by

Great job!

#3 opened over 1 year ago by

ModuleNotFoundError: No module named 'transformers_modules.TheBloke.WizardLM-33B-V1'

#2 opened over 1 year ago by

Tips on running on 3090 24gb VRAM?

#1 opened over 1 year ago by