| { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "hf-compo-cad2-l24-ms-v-chtk-c12k-1t-v2-b2-lr4e4-pHntE6-ep1-ba320185/", |
| "architectures": [ |
| "CaduceusForMaskedLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_caduceus.CaduceusConfig", |
| "AutoModel": "modeling_caduceus.Caduceus", |
| "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", |
| "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" |
| }, |
| "bidirectional": true, |
| "bidirectional_strategy": "add", |
| "bidirectional_weight_tie": true, |
| "complement_map": { |
| "0": 0, |
| "1": 1, |
| "2": 2, |
| "3": 6, |
| "4": 5, |
| "5": 4, |
| "6": 3, |
| "7": 7 |
| }, |
| "d_intermediate": 0, |
| "d_model": 768, |
| "fused_add_norm": true, |
| "initializer_cfg": { |
| "initializer_range": 0.02, |
| "n_residuals_per_layer": 1, |
| "rescale_prenorm_residual": true |
| }, |
| "model_type": "caduceus", |
| "n_layer": 24, |
| "norm_epsilon": 1e-05, |
| "pad_token_id": -100, |
| "pad_vocab_size_multiple": 8, |
| "rcps": true, |
| "residual_in_fp32": false, |
| "rms_norm": true, |
| "ssm_cfg": { |
| "bias": false, |
| "conv_bias": true, |
| "d_conv": 4, |
| "d_state": 64, |
| "dt_init_floor": 0.0001, |
| "dt_max": 0.1, |
| "dt_min": 0.001, |
| "expand": 2 |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.36.1", |
| "vocab_size": 8 |
| } |
|
|
