| { |
| "_name_or_path": "None", |
| "architectures": [ |
| "NetFoundLanguageModelling" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "embedding_size": 1024, |
| "encoder_layout": null, |
| "flat": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-12, |
| "limit_bursts": false, |
| "max_burst_length": 109, |
| "max_bursts": 12, |
| "max_position_embeddings": 109, |
| "metaFeatures": 4, |
| "model_max_length": 1308, |
| "model_type": "NetFound", |
| "no_direction_loss": false, |
| "no_meta": false, |
| "no_metadata_loss": false, |
| "no_mlm": false, |
| "no_swapped_bursts": false, |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "p": 0, |
| "pad_token_id": 0, |
| "position_embedding_type": "absolute", |
| "pretraining": true, |
| "rep_output_path": null, |
| "roformer": false, |
| "rotary_value": false, |
| "subflow_bursts": 3, |
| "subflow_len": -1, |
| "torch_dtype": "float32", |
| "transformers_version": "4.47.0.dev0", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 65539 |
| } |
|
|
