| { |
| "_name_or_path": "/home/g/gnikesh/projects/PlantCaduceus/FunDLM-20M_NoLCF_M0_512bp", |
| "architectures": [ |
| "CaduceusForMaskedLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_caduceus.CaduceusConfig", |
| "AutoModel": "kuleshov-group/PlantCaduceus_l20--modeling_caduceus.Caduceus", |
| "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", |
| "AutoModelForSequenceClassification": "kuleshov-group/PlantCaduceus_l20--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_model": 384, |
| "fused_add_norm": true, |
| "initializer_cfg": { |
| "initializer_range": 0.02, |
| "n_residuals_per_layer": 1, |
| "rescale_prenorm_residual": true |
| }, |
| "model_type": "caduceus", |
| "n_layer": 20, |
| "norm_epsilon": 1e-05, |
| "pad_token_id": -100, |
| "pad_vocab_size_multiple": 8, |
| "rcps": true, |
| "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": "4.40.0", |
| "vocab_size": 8 |
| } |
|
|
