Upload multilingual fake news detector

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

classification_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa043c4645f0a09c829465df10ae37621f05ee7ad175c7822a1875954258f88
+size 1190693

config.json

@@ -0,0 +1,38 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.25,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.25,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "FAKE",
+    "1": "REAL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "FAKE": 0,
+    "REAL": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

inference_config.json

@@ -0,0 +1,34 @@
+{
+  "backbone": "xlm-roberta-base",
+  "num_labels": 2,
+  "max_length": 160,
+  "dropout": 0.25,
+  "id2label": {
+    "0": "FAKE",
+    "1": "REAL"
+  },
+  "label2id": {
+    "FAKE": 0,
+    "REAL": 1
+  },
+  "decision_threshold": 0.52,
+  "task": "binary-classification",
+  "problem_type": "Multilingual Fake News Detection",
+  "datasets": [
+    "LIAR",
+    "utahnlp/x-fact"
+  ],
+  "languages": "25 languages",
+  "metrics": {
+    "val_f1_macro": 0.6825,
+    "test_accuracy": 0.6843,
+    "test_f1_macro": 0.6818,
+    "test_f1_tuned": 0.6894,
+    "test_f1_weighted": 0.6798
+  },
+  "architecture": {
+    "base": "xlm-roberta-base",
+    "pooling": "AttentionPooling (all tokens, not just CLS)",
+    "head": "Linear(768\u2192384) + GELU + Dropout + Linear(384\u21922)"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f0314d08a9c232eaeae6b0b3fdaae722b1bb27592deaf23aa51b2c431959ec
+size 1112197064

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5840e663fc18bac1cff418f8eb449bec4ae95d2091c7e2d69d53248e6e49dc
+size 16781739

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}