FP8_DYNAMIC quant of Nanbeige4.3-33B (llm-compressor), with fidelity + throughput card
324f2c1 verified | { | |
| "_from_model_config": true, | |
| "bos_token_id": 166100, | |
| "eos_token_id": 166101, | |
| "pad_token_id": 0, | |
| "transformers_version": "5.21.0", | |
| "use_cache": true | |
| } |