| { |
| "add_cross_attention": false, |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bos_token_id": null, |
| "classifier_dropout": null, |
| "document_chunk_length": 512, |
| "document_pooling": "max_log1p_relu", |
| "dtype": "float32", |
| "eos_token_id": null, |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "inference_free_query": true, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "is_decoder": false, |
| "layer_norm_eps": 1e-12, |
| "max_chunks_per_document": 2, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 3, |
| "pad_token_id": 0, |
| "position_embedding_type": "absolute", |
| "pruned_from_checkpoint": "/vol/static_splade/numpy_pandas_pybind11_v1/checkpoints/splade_v3_doc_static_full_v3_stronger_flops/best_proxy", |
| "pruned_layer_indices": [ |
| 0, |
| 6, |
| 11 |
| ], |
| "query_encoder_type": "learned_static_token_weights", |
| "static_query_weight_file": "static_query_weights.pt", |
| "tie_word_embeddings": true, |
| "transformers_version": "5.13.1", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 30522 |
| } |
|
|
