CarlOwOs
/

MNLP_M2_mcqa_model-W4A8

8-bit precision

compressed-tensors

Model card Files Files and versions

MNLP_M2_mcqa_model-W4A8 / tokenizer.json

Commit History

Add FP8 dynamically quantized MNLP_M2_mcqa_model model using llm-compressor

cc8a543
verified

CarlOwOs commited on May 27, 2025