| { |
| "_name_or_path": "hf_bert/bp_medium_step49", |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "attn_norm_layer_type": "layer_norm", |
| "attn_num_groups": "None", |
| "classifier_dropout": "None", |
| "embedding_norm_layer_type": "layer_norm", |
| "embedding_num_groups": "None", |
| "embedding_size": 768, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 2000, |
| "model_type": "bert", |
| "mup": false, |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "output_mult": 1, |
| "pad_token_id": 0, |
| "position_embedding_type": "absolute", |
| "prenorm": false, |
| "query_zero_init": false, |
| "readout_zero_init": false, |
| "summary_activation": "gelu", |
| "summary_last_dropout": 0.1, |
| "summary_type": "first", |
| "summary_use_proj": true, |
| "torch_dtype": "float32", |
| "transformers_version": "4.25.1", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 9 |
| } |
|
|
