{ "model_config": { "n_layer": 24, "n_head": 16, "n_embd": 1024, "block_size": 1024, "bias": false, "dropout": 0.0, "n_codes_total": 8, "n_codes_given": 1, "input_vocab_size": 1056, "output_vocab_size": 1056 }, "model_type": "fine", "torch_dtype": "float32", "parameter_count": 319358976, "needs_tokenizer": true, "best_val_loss": 2.0785889791647594 }