kel-dx
/

llm-jp-4-8b-instruct-NVFP4

Text Generation

Model card Files Files and versions

llm-jp-4-8b-instruct-NVFP4 / quantization_recipe /03_ptq_modelopt.py

Commit History

Improved calibration (strict-format slice), modelopt 0.45, vLLM 0.24 validation, plugin fixes (adjust_request scoping, extract_content_ids, indentation), full reproducibility bundle (pinned revision, env freeze, calibration file), LICENSE

7484310
verified

ege-g commited on Jul 13

llm-jp-4-8b-instruct NVFP4 (Japanese-calibrated, mixed-precision recipe): weights, model card, vLLM plugin, full reproduction recipe

000c932
verified

ege-g commited on Jul 6