{ "_name_or_path": "configs/transformer_16M.json", "architectures": [ "TransformerForCausalLM" ], "attention_bias": false, "bos_token_id": 1, "clamp_min": null, "elementwise_affine": true, "eos_token_id": 2, "fuse_cross_entropy": true, "fuse_norm": true, "hidden_act": "swish", "hidden_ratio": 4, "hidden_size": 256, "initializer_range": 0.02, "intermediate_size": null, "max_position_embeddings": 2048, "model_type": "transformer", "norm_eps": 1e-06, "norm_first": false, "num_heads": 4, "num_hidden_layers": 10, "num_kv_heads": 4, "rope_theta": 10000.0, "state_size": 16, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.47.0", "use_cache": true, "use_gk": true, "use_gv": false, "vocab_size": 32000, "window_size": null }