| {"architectures": ["OuroForCausalLM"], "attention_dropout": 0.0, "auto_map": {"AutoConfig": "configuration_ouro.OuroConfig", "AutoModel": "modeling_ouro.OuroModel", "AutoModelForCausalLM": "modeling_ouro.OuroForCausalLM"}, "bos_token_id": 0, "dtype": "bfloat16", "early_exit_threshold": 1.0, "eos_token_id": 0, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "layer_types": ["full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention"], "max_position_embeddings": 65536, "max_window_layers": 24, "model_type": "ouro", "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "total_ut_steps": 4, "transformers_version": "4.57.6", "use_cache": true, "use_sliding_window": false, "vocab_size": 49152, "torch_dtype": "float16", "matryoshka_bits": [2, 4, 8], "weight_bit": "matryoshka", "quant_ut_steps": [0, 1, 2, 3], "quantized_weights_path": "2bit_model.quant"} |