{ "model_type": "byte-level BPE (HF tokenizers)", "vocab_size": 4096, "special_tokens": [ "<|endoftext|>", "<|user|>", "<|assistant|>", "<|system|>", "<|end|>", "", "", "<|sep|>", "<|pad|>" ], "digits": "split individually", "normalization": "none", "sample_chars": 400000000, "sample_shares": { "qa-plain": 0.14100000000000001, "qa-distill": 0.055, "facts-plain": 0.041, "capability-distill": 0.0165, "reasoning-distill": 0.006500000000000001, "math-direct-3m": 0.19999999999999998, "cosmopedia-wikihow": 0.0757, "commonsense-distill": 0.0092, "procedural-anneal": 0.006900000000000001, "everyday-activity": 0.0045000000000000005, "social-situations": 0.0045000000000000005, "everyday-reasoning": 0.00135, "ds-prose": 0.00135, "cosmopedia-stanford": 0.12300000000000001, "cosmopedia-openstax": 0.027000000000000003, "tiny-stories-v2": 0.14150000000000001, "fineweb-edu-10bt": 0.09, "wiki-dense": 0.055 } }