| { |
| "vocab_size": 8000, |
| "block_size": 384, |
| "n_layer": 8, |
| "n_head": 7, |
| "n_embd": 448, |
| "dropout": 0.2, |
| "tokenizer_type": "sentencepiece_bpe", |
| "tokenizer_file": "MTP2_9_tokenizer.model", |
| "special_tokens": { |
| "pad_id": 0, |
| "bos_id": 1, |
| "eos_id": 2, |
| "unk_id": 3 |
| }, |
| "generation_defaults": { |
| "max_new_tokens": 200, |
| "temperature": 0.8, |
| "top_k": 40, |
| "top_p": 0.9, |
| "repetition_penalty": 1.2, |
| "no_repeat_ngram_size": 3 |
| }, |
| "meta": { |
| "model_name": "MTP-2.9", |
| "architecture": "gpt_rope_swiglu_rmsnorm", |
| "trained_examples": 7136, |
| "augmented_examples": 21512, |
| "corpus_fragments": 318, |
| "total_sequences": 21864, |
| "best_val_loss": 2.4462781286239625, |
| "stopped_early": false, |
| "label_smoothing": 0.1, |
| "created": "2026-07-15 07:09:14" |
| } |
| } |
