new model

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "vocab-transformers/msmarco-distilbert-word2vec256k-MLM_785k_emb_updated",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "vocab_size": 256000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c4d028c2f0d0a04ae76a3b852cd69672ec1974978a6a6c448ed95d47584841
+size 961553007

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 96,
+  "do_lower_case": false
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "model_input_names": ["input_ids", "attention_mask"], "special_tokens_map_file": "/home/ukp-reimers/.cache/huggingface/transformers/fe09c361189d8238b9e387f10a088e93f70620bfe74b82036baff1fed512a153.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "vocab-transformers/msmarco-distilbert-word2vec256k-MLM_785k_emb_updated", "tokenizer_class": "PreTrainedTokenizerFast"}