| { | |
| "architectures": [ | |
| "BiMambaForMaskedLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_bimamba.BiMambaConfig", | |
| "AutoModel": "modeling_bimamba.BiMamba", | |
| "AutoModelForMaskedLM": "modeling_bimamba.BiMambaForMaskedLM" | |
| }, | |
| "bidirectional": true, | |
| "bidirectional_strategy": "add", | |
| "bidirectional_weight_tie": true, | |
| "d_model": 2, | |
| "fused_add_norm": true, | |
| "initializer_cfg": { | |
| "initializer_range": 0.02, | |
| "n_residuals_per_layer": 1, | |
| "rescale_prenorm_residual": true | |
| }, | |
| "model_type": "bimamba", | |
| "n_layer": 1, | |
| "norm_epsilon": 1e-05, | |
| "pad_token_id": -100, | |
| "pad_vocab_size_multiple": 8, | |
| "residual_in_fp32": true, | |
| "rms_norm": true, | |
| "ssm_cfg": { | |
| "bias": false, | |
| "conv_bias": true, | |
| "d_conv": 4, | |
| "d_state": 16, | |
| "dt_init": "random", | |
| "dt_init_floor": 0.0001, | |
| "dt_max": 0.1, | |
| "dt_min": 0.001, | |
| "dt_rank": "auto", | |
| "dt_scale": 1.0, | |
| "expand": 2, | |
| "use_fast_path": true | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.1", | |
| "vocab_size": 8 | |
| } | |