mymodel-classify-category-news

.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

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B\u1ea5t \u0111\u1ed9ng s\u1ea3n",
+    "1": "Du l\u1ecbch",
+    "2": "Gi\u00e1o d\u1ee5c",
+    "3": "Gi\u1ea3i tr\u00ed",
+    "4": "Kinh doanh",
+    "5": "Ph\u00e1p lu\u1eadt",
+    "6": "S\u1ee9c kh\u1ecfe",
+    "7": "Th\u1ebf gi\u1edbi",
+    "8": "Th\u1ec3 thao",
+    "9": "Th\u1eddi s\u1ef1",
+    "10": "Xe",
+    "11": "\u0110\u1eddi s\u1ed1ng"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B\u1ea5t \u0111\u1ed9ng s\u1ea3n": 0,
+    "Du l\u1ecbch": 1,
+    "Gi\u00e1o d\u1ee5c": 2,
+    "Gi\u1ea3i tr\u00ed": 3,
+    "Kinh doanh": 4,
+    "Ph\u00e1p lu\u1eadt": 5,
+    "S\u1ee9c kh\u1ecfe": 6,
+    "Th\u1ebf gi\u1edbi": 7,
+    "Th\u1ec3 thao": 8,
+    "Th\u1eddi s\u1ef1": 9,
+    "Xe": 10,
+    "\u0110\u1eddi s\u1ed1ng": 11
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3918b09efe8e32320ed525fdb677bb9e11c7f1b5fdac141696b4c9b3f9ebb2
+size 1112280433

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7d585926000ffec2c828378ac39314f973f4f580a3be19026fe40f6690c66f
+size 17082925

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74ae9a8397ccd00acd09f3a3eb446159e19b87d44edd4556f0a69105339e73e
+size 3963