| | Remove Calibration Dataset section | cvoegele-nv | Jul 6, 2026 |
| | Add benchmarking parameters (T=1.0, top_p=0.95, max num tokens 65536) and MXFP8 baseline note to Evaluation section | cvoegele-nv |
| | refactor: rename shards to model-NNNNN-of-00088 convention; update index weight_map | zhiyucheng |
| | Remove M3 Coding and Agentic Benchmark Results (BF16 baseline) table | cvoegele-nv |
| | Copy vocab.json from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy video_processor.py from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy tokenizer_config.json from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy tokenizer.json from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy special_tokens_map.json from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy processing_minimax.py from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy preprocessor_config.json from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy model.safetensors.index.json from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy merges.txt from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy image_processor.py from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy hf_quant_config.json from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy generation_config.json from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy experts-layer-059.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy experts-layer-058.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy experts-layer-057.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |
| | Copy experts-layer-056.safetensors from nvidia/MiniMax-M3-NVFP4-Preview0615 | zhiyucheng |