k-l-lambda
/

Kimi-K2-Instruct-FP4-MTP

8-bit precision

Model card Files Files and versions

Kimi-K2-Instruct-FP4-MTP / hf_quant_config.json

Commit History

updated hf_quant_config.json to adapt fp4 mlp weights in layer 61.

d388331

k-l-lambda commited on Jul 24

added basic config files.

4536b41

k-l-lambda commited on Jul 24