autobots
/

gpt-j-fourchannel-4bit

Text Generation

Inference Endpoints

Model card Files Files and versions Community

gpt-j-fourchannel-4bit / ggml

1 contributor

History: 2 commits

autobots's picture

quantize linux bin to convert models, not sure if it's useful

6f08488 almost 2 years ago

ggml-model-q4_0.bin

3.79 GB
LFS

GGML 4bit version.. its pretty fast almost 2 years ago
quantize

433 kB

quantize linux bin to convert models, not sure if it's useful almost 2 years ago