alphaXiv
/

filter-0.5B-W8A8

8-bit precision

compressed-tensors

Model card Files Files and versions

filter-0.5B-W8A8 / tokenizer.json

Commit History

Add W8A8 int8 quantized model via llmcompressor compressed-tensors

95cfd64
verified

alphaXiv commited on 30 days ago