{ "architectures": [ "MTPTransformerForCausalLM" ], "bos_token_id": 1, "elementwise_affine": true, "eos_token_id": 2, "fuse_cross_entropy": true, "fuse_norm": true, "fuse_swiglu": true, "hidden_act": "swish", "hidden_ratio": 4, "hidden_size": 2048, "initializer_range": 0.006, "intermediate_size": null, "max_position_embeddings": 8192, "model_type": "mtp_transformer", "n_future_tokens": 4, "norm_eps": 1e-06, "num_heads": 32, "num_hidden_layers": 32, "num_kv_heads": null, "pad_token_id": 2, "qk_norm": false, "qkv_bias": false, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.50.3", "use_cache": true, "use_custom_backward": false, "vocab_size": 32000, "window_size": null }