| { | |
| "architectures": [ | |
| "Mamba2ForCausalLM" | |
| ], | |
| "bos_token_id": 0, | |
| "chunk_size": 256, | |
| "conv_kernel": 4, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "expand": 2, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.1, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "mamba2", | |
| "n_groups": 1, | |
| "num_heads": 80, | |
| "num_hidden_layers": 64, | |
| "pad_token_id": 1, | |
| "rescale_prenorm_residual": false, | |
| "residual_in_fp32": true, | |
| "rms_norm": true, | |
| "state_size": 128, | |
| "tie_word_embeddings": true, | |
| "time_step_floor": 0.0001, | |
| "time_step_limit": [ | |
| 0.0, | |
| 1e+30 | |
| ], | |
| "time_step_max": 0.1, | |
| "time_step_min": 0.001, | |
| "time_step_rank": 160, | |
| "transformers_version": "4.57.6", | |
| "use_bias": false, | |
| "use_cache": true, | |
| "use_conv_bias": true, | |
| "vocab_size": 50288 | |
| } | |