SPB Git

Repository Public Research preview

tokenizer_train_summary.json 739 B 34 lines json

1{2  "created_at": "2026-11-09T18:45:26Z",3  "git": {4    "commit": "91800b580daed6774dc2e18911a23bd7b4b871e2",5    "branch": "main",6    "dirty": true7  },8  "libraries": {9    "python": "3.14.4",10    "torch": "2.12.0",11    "numpy": "2.5.4",12    "anthropic": "2.3.0",13    "transformers": "5.8.1",14    "sentencepiece": "0.2.2",15    "lxml": "6.1.3",16    "pyarrow": "24.0.0",17    "sacrebleu": "2.6.0",18    "datasketch": "2.0.0",19    "rapidfuzz": "3.14.6"20  },21  "hardware": {22    "platform": "macOS-27.0-arm64-arm-64bit-Mach-O",23    "machine": "arm64",24    "cpu_count": 18,25    "chip": "Apple M5 Max",26    "ram_gb": 48.0,27    "torch_mps": true,28    "torch_cuda": false29  },30  "n_lines": 258264,31  "vocab_size": 32000,32  "train_docs": 1026833}34
Files main
Menu

Theme