Download quantization-provenance.json from WIlfLin/S1-mini-Chinese-1106-INT8: direct link, hf CLI and curl.
- Browser
- Download file 656 Bytes
-
https://huggingface.co/WIlfLin/S1-mini-Chinese-1106-INT8/resolve/main/quantization-provenance.json
- Command line
-
hf download hf://WIlfLin/S1-mini-Chinese-1106-INT8/quantization-provenance.json
-
curl -L -o quantization-provenance.json https://huggingface.co/WIlfLin/S1-mini-Chinese-1106-INT8/resolve/main/quantization-provenance.json
656 Bytes
| { | |
| "format": "INT8", | |
| "scheme": "W8A16", | |
| "algorithm": "per-channel RTN", | |
| "calibration_rows": 0, | |
| "calibration_scope": "No activation calibration required for weight-only RTN", | |
| "kv_cache": "BF16 (not quantized)", | |
| "embeddings_lm_head_norm": "BF16", | |
| "seconds": 7.70783578499686, | |
| "verified_runtime_backend": "", | |
| "rope_compatibility": "Both legacy rope_theta and rope_parameters.rope_theta explicitly 1000000 to preserve trained position encoding in Transformers4/vLLM0.17 and Transformers5", | |
| "source_release": "WIlfLin/S1-mini-Chinese-1106-BF16", | |
| "base_weights_sha256": "c0d2cf58468359e0a44970083f9ce38078208c291430d20a5c685c5ce6759312" | |
| } | |