Upload BertForMaskedLM

config.json

@@ -1,28 +1,26 @@
 {
-  "_name_or_path": "imta-ai/tech-roberta",
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
   "architectures": [
-    "XLMRobertaForMaskedLM"
+    "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.33.0",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 250037
 }

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.0"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:048f76974a7c1865de0bd91662c8f7e3201ff5c3c726fd84f1e97503371b08cb
-size 1113250229
+oid sha256:7ac4f5ffbe4318706f861f73b2d24167fdbb9663b3bef56da98651873a1322f7
+size 471687285