Patrick Oliver Bustamante

Psychopatz's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in TheBloke/Wizard-Vicuna-13B-Uncensored-GGML almost 2 years ago

New quant 8bit method, how is it performing on your CPU? (share your token/s, CPU model and -- thread)

24

#2 opened almost 2 years ago by

alphaprime90

New activity in TehVenom/Metharme-7b-4bit-Q4_1-GGML almost 2 years ago

Pygmalion GGML vs Metharme?

1

#1 opened almost 2 years ago by

Psychopatz

New activity in TehVenom/Pygmalion-7b-4bit-Q4_1-GGML almost 2 years ago

No models

5

#1 opened almost 2 years ago by

Psychopatz

New activity in anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g almost 2 years ago

LLAMA running slow with this model.

1

#17 opened almost 2 years ago by

BoreGuy1998

Error using ooba-gooba

39

#6 opened almost 2 years ago by

blueisbest