Upload RobertaForSequenceClassification

config.json

@@ -1,34 +1,35 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/40-49 My PhD/PhD/3. My Research Topics/ReferencEsTractor/models/type/distilbert-base-multilingual-cased_BEST",
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": false,
     "1": true
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "false": 0,
     "true": 1
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
-  "pad_token_id": 0,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.48.3",
-  "vocab_size": 119547
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e6214f0d92094f47a6ca6a53594a4f5a785df2b4823a4ea043d05c6e0aa517
-size 541317368
+oid sha256:d153e1d565b4cf8a5fc4f582158e334a78b1f76a0d7a0768c57b90993efe6b26
+size 498612824