{ "_name_or_path": "/groups/pupko/edodotan/BetaAlignPart3/test_architecture/mix_training_state_space_models_10_15_0p200_different_seed_v2/ZAMBA/layers_24_d_1024_e-4_ZAMBA/checkpoint-20480/", "architectures": [ "ZambaForCausalLM" ], "attention_dropout": 0.0, "attention_head_dim": 128, "attention_hidden_size": 2048, "attn_layer_offset": 4, "attn_layer_period": 6, "bos_token_id": 1, "eos_token_id": 4, "hidden_act": "gelu", "hidden_mamba_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "layers_block_type": [ "mamba", "mamba", "hybrid", "mamba", "mamba", "mamba", "mamba", "hybrid", "mamba", "mamba", "mamba", "mamba", "mamba", "hybrid", "mamba", "mamba", "mamba", "mamba", "mamba", "hybrid", "mamba", "mamba", "mamba", "mamba" ], "mamba_conv_bias": true, "mamba_d_conv": 4, "mamba_d_state": 16, "mamba_dt_rank": 64, "mamba_expand": 2, "mamba_proj_bias": false, "max_position_embeddings": 2048, "model_type": "zamba", "n_mamba_heads": 2, "num_attention_heads": 16, "num_heads": 32, "num_hidden_layers": 24, "num_key_value_heads": 16, "num_logits_to_keep": 1, "pad_token_id": 3, "rms_norm_eps": 1e-05, "time_step_floor": 0.0001, "time_step_max": 0.1, "time_step_min": 0.001, "torch_dtype": "float32", "transformers_version": "4.48.1", "use_cache": true, "use_mamba_kernels": true, "vocab_size": 6400 }