initial commit

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "add_marker_tokens": false,
+  "architectures": [
+    "SpladeBertModel"
+  ],
+  "attend_to_doc_expanded_tokens": [
+    false
+  ],
+  "attend_to_query_expanded_tokens": false,
+  "attention_probs_dropout_prob": 0.1,
+  "backbone_model_type": "bert",
+  "classifier_dropout": null,
+  "doc_expansion": false,
+  "doc_length": 256,
+  "doc_pooling_strategy": "max",
+  "embedding_dim": 30522,
+  "gradient_checkpointing": false,
+  "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": 512,
+  "model_type": "splade",
+  "normalize": false,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "projection": "mlm",
+  "query_aggregation_function": "sum",
+  "query_expansion": false,
+  "query_length": 32,
+  "query_pooling_strategy": "max",
+  "save_step": 49009,
+  "similarity_function": "dot",
+  "sparsification": "relu_log",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

mask_scoring_tokens.json

@@ -0,0 +1 @@
+{"query": null, "doc": null}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b251142e71ba419cab97f7ae0f69cdd04108e5c1f5fb5a45cec1322446eaeb5b
+size 438079848

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "add_marker_tokens": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "attend_to_doc_expanded_tokens": [
+    false
+  ],
+  "attend_to_query_expanded_tokens": false,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "doc_expansion": false,
+  "doc_length": 256,
+  "doc_token": "[DOC]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "query_expansion": false,
+  "query_length": 32,
+  "query_token": "[QUE]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}