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

1.95 MB

Ctrl+K

1 contributor

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 about 1 month ago

03_ptq_modelopt.py

6.85 kB
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 about 1 month ago
04_export_and_patch.py

6.04 kB
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 about 1 month ago
build_calib_set.py

10.7 kB
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 about 1 month ago
build_calib_strict_format.py

8.1 kB
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 about 1 month ago
calib_full.jsonl

1.91 MB
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 about 1 month ago
calibration_datasheet.json

2.35 kB
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 about 1 month ago
environment_freeze.txt

2.39 kB
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 about 1 month ago
scan_weight_scale_nan.py

2.81 kB
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 about 1 month ago