Update config.json

config.json

@@ -1,36 +1,35 @@
 {
-  "_name_or_path": "jinaai/jina-bert-v2-qk-post-norm",
+  "_name_or_path": "jinaai/jina-bert-implementation",
+  "model_max_length": 8192,
   "architectures": [
     "JinaBertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "attn_implementation": "torch",
   "auto_map": {
-    "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"
+    "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"
   },
   "classifier_dropout": null,
-  "emb_pooler": "mean",
-  "feed_forward_type": "geglu",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
+  "hidden_dropout_prob": 0.1,
   "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": "float16",
-  "transformers_version": "4.35.2",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 61056
-}
+  "vocab_size": 30528,
+  "feed_forward_type": "geglu",
+  "emb_pooler": "mean"
+}