Hugging Face's logo
tp's picture
8

tp

Onix22
·

AI & ML interests

None yet

Organizations

None yet

Onix22's activity

New activity in TheBloke/CodeLlama-34B-GPTQ 11 months ago

This model breaks laws of physic.

2
#4 opened 12 months ago by Onix22
New activity in TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-SuperHOT-8K-GPTQ over 1 year ago

Does it work for anyone?

3
#1 opened over 1 year ago by Onix22
New activity in anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g over 1 year ago

Running out of memory with 12GB of VRAM on 3080TI

3
#39 opened over 1 year ago by faaaaaaaaaaaa

If 4-bit = 8GB model would 8-bit = 16GB? And how much better would it be?

2
#40 opened over 1 year ago by Wildstar50
New activity in tsumeone/llama-30b-supercot-3bit-128g-cuda over 1 year ago

30B 3bit seems pretty sweet by the official evaluation

2
#1 opened over 1 year ago by Yhyu13
New activity in GamerUntouch/LLaMa-Storytelling-4Bit over 1 year ago

update is needed

2
#5 opened over 1 year ago by Onix22
New activity in tsumeone/llama-30b-supercot-4bit-cuda over 1 year ago

3bit version

1
#1 opened over 1 year ago by Onix22