Revert "Upload pytorch_model.bin"

This reverts commit fc3d7f0e5c7096492a8e3b8ee8ca76c7db4aa06d.

config.json

@@ -1,35 +1,36 @@
 {
-  "_name_or_path": "jinaai/jina-bert-implementation",
-  "model_max_length": 8192,
+  "_name_or_path": "jinaai/jina-bert-v2-qk-post-norm",
   "architectures": [
     "JinaBertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.0,
+  "attn_implementation": "torch",
   "auto_map": {
-    "AutoConfig": "jinaai/jina-bert-implementation--configuration_bert.JinaBertConfig",
-    "AutoModelForMaskedLM": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForMaskedLM",
-    "AutoModel": "jinaai/jina-bert-implementation--modeling_bert.JinaBertModel",
-    "AutoModelForSequenceClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForSequenceClassification"
+    "AutoConfig": "jinaai/jina-bert-v2-qk-post-norm--configuration_bert.JinaBertConfig",
+    "AutoModel": "jinaai/jina-bert-v2-qk-post-norm--modeling_bert.JinaBertModel",
+    "AutoModelForMaskedLM": "jinaai/jina-bert-v2-qk-post-norm--modeling_bert.JinaBertForMaskedLM",
+    "AutoModelForSequenceClassification": "jinaai/jina-bert-v2-qk-post-norm--modeling_bert.JinaBertForSequenceClassification"
   },
   "classifier_dropout": null,
+  "emb_pooler": "mean",
+  "feed_forward_type": "geglu",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 8192,
+  "model_max_length": 8192,
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "alibi",
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30528,
-  "feed_forward_type": "geglu",
-  "emb_pooler": "mean"
-}
+  "vocab_size": 61056
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba0500574381615fddd725196787c59d69c39da1a4992573168949e57193814
-size 274773562
+oid sha256:1c28fb0a8bc930d79b2b29091674a8a0ce0e983489e88b0e863efb1ad4444b01
+size 321787514

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,15 +1,22 @@
 {
+  "add_prefix_space": false,
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 2147483648,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }