{ "_name_or_path": "../../configs/transformer_3B.json", "architectures": [ "TransformerForCausalLM" ], "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": 0.02, "intermediate_size": 11008, "max_position_embeddings": 32768, "model_type": "transformer", "norm_eps": 1e-06, "num_heads": 16, "num_hidden_layers": 36, "num_kv_heads": 2, "qkv_bias": true, "rope_theta": 1000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.48.2", "use_cache": true, "vocab_size": 151936, "window_size": null }