Upload 9 files

data/config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "bhavikardeshna/xlm-roberta-base-vietnamese",
+  "_name_or_path": "vinai/phobert-base",
   "architectures": [
-    "XLMRobertaForQuestionAnswering"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -11,21 +11,86 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "id2label": {
+    "0": "Th\u1ea9m_quy\u1ec1n_tuy\u1ec3n,_qu",
+    "1": "Ng\u01b0\u1eddi_lao_\u0111\u1ed9ng_v\u00e0_do",
+    "2": "C\u00e1c_quy_\u0111\u1ecbnh_v\u1ec1_tuy\u1ec3",
+    "3": "V\u0103n_ph\u00f2ng_\u0111\u1ea1i_di\u1ec7n_c",
+    "4": "Tr\u01b0\u1eddng_h\u1ee3p_gi\u1ea3i_th\u1ec3",
+    "5": "H\u1ee3p_\u0111\u1ed3ng_lao_\u0111\u1ed9ng_c\u00f3",
+    "6": "Doanh_nghi\u1ec7p_ph\u1ea3i_cu",
+    "7": "H\u00e0nh_vi_ng\u01b0\u1eddi_s\u1eed_d\u1ee5n",
+    "8": "Ng\u01b0\u1eddi_s\u1eed_d\u1ee5ng_lao_\u0111\u1ed9",
+    "9": "Doanh_nghi\u1ec7p_c\u00f3_\u0111\u01b0\u1ee3c",
+    "10": "Doanh_nghi\u1ec7p_ph\u1ea3i_l\u00e0",
+    "11": "intent_12_Th\u1ea9m_quy\u1ec1n_giao_k\u1ebft",
+    "12": "Gi\u00e1m_\u0111\u1ed1c_nh\u00e2n_s\u1ef1_c\u00f3",
+    "13": "Ng\u01b0\u1eddi_lao_\u0111\u1ed9ng_c\u00f3_th",
+    "14": "N\u1ebfu_ng\u01b0\u1eddi_lao_\u0111\u1ed9ng_k",
+    "15": "C\u00e1c_tr\u01b0\u1eddng_h\u1ee3p_t\u1ea1m_h",
+    "16": "M\u1ed9t_ng\u01b0\u1eddi_lao_\u0111\u1ed9ng_c",
+    "17": "C\u00f3_c\u00e1c_lo\u1ea1i_h\u1ee3p_\u0111\u1ed3ng",
+    "18": "Khi_c\u00f3_nhu_c\u1ea7u_s\u1eed_d\u1ee5",
+    "19": "H\u1ee3p_\u0111\u1ed3ng_lao_\u0111\u1ed9ng_kh",
+    "20": "C\u00e1c_ch\u1ebf_\u0111\u1ed9_v\u1ec1_l\u01b0\u01a1ng,",
+    "21": "Khi_h\u1ee3p_\u0111\u1ed3ng_lao_\u0111\u1ed9n",
+    "22": "Th\u1eddi_h\u1ea1n_t\u1ea1m_ho\u00e3n_h\u1ee3",
+    "23": "C\u00f3_\u0111\u01b0\u1ee3c_k\u00fd_nhi\u1ec1u_h\u1ee3p",
+    "24": "H\u1ee3p_\u0111\u1ed3ng_lao_\u0111\u1ed9ng_b\u1eaf",
+    "25": "Ph\u1ee5_l\u1ee5c_H\u1ee3p_\u0111\u1ed3ng_lao",
+    "26": "Ph\u1ee5_l\u1ee5c_h\u1ee3p_\u0111\u1ed3ng_c\u1ea7n",
+    "27": "N\u1ebfu_c\u00f3_n\u1ed9i_dung_kh\u00e1c",
+    "28": "Hi\u1ec7u_l\u1ef1c_c\u1ee7a_h\u1ee3p_\u0111\u1ed3n",
+    "29": "Th\u1eddi_h\u1ea1n_b\u00e1o_tr\u01b0\u1edbc_t",
+    "30": "NSDL\u0110_c\u00f3_th\u1ec3_k\u00fd_ph\u1ee5"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "language": "english",
+  "label2id": {
+    "C\u00e1c_ch\u1ebf_\u0111\u1ed9_v\u1ec1_l\u01b0\u01a1ng,": 20,
+    "C\u00e1c_quy_\u0111\u1ecbnh_v\u1ec1_tuy\u1ec3": 2,
+    "C\u00e1c_tr\u01b0\u1eddng_h\u1ee3p_t\u1ea1m_h": 15,
+    "C\u00f3_c\u00e1c_lo\u1ea1i_h\u1ee3p_\u0111\u1ed3ng": 17,
+    "C\u00f3_\u0111\u01b0\u1ee3c_k\u00fd_nhi\u1ec1u_h\u1ee3p": 23,
+    "Doanh_nghi\u1ec7p_c\u00f3_\u0111\u01b0\u1ee3c": 9,
+    "Doanh_nghi\u1ec7p_ph\u1ea3i_cu": 6,
+    "Doanh_nghi\u1ec7p_ph\u1ea3i_l\u00e0": 10,
+    "Gi\u00e1m_\u0111\u1ed1c_nh\u00e2n_s\u1ef1_c\u00f3": 12,
+    "Hi\u1ec7u_l\u1ef1c_c\u1ee7a_h\u1ee3p_\u0111\u1ed3n": 28,
+    "H\u00e0nh_vi_ng\u01b0\u1eddi_s\u1eed_d\u1ee5n": 7,
+    "H\u1ee3p_\u0111\u1ed3ng_lao_\u0111\u1ed9ng_b\u1eaf": 24,
+    "H\u1ee3p_\u0111\u1ed3ng_lao_\u0111\u1ed9ng_c\u00f3": 5,
+    "H\u1ee3p_\u0111\u1ed3ng_lao_\u0111\u1ed9ng_kh": 19,
+    "Khi_c\u00f3_nhu_c\u1ea7u_s\u1eed_d\u1ee5": 18,
+    "Khi_h\u1ee3p_\u0111\u1ed3ng_lao_\u0111\u1ed9n": 21,
+    "M\u1ed9t_ng\u01b0\u1eddi_lao_\u0111\u1ed9ng_c": 16,
+    "NSDL\u0110_c\u00f3_th\u1ec3_k\u00fd_ph\u1ee5": 30,
+    "Ng\u01b0\u1eddi_lao_\u0111\u1ed9ng_c\u00f3_th": 13,
+    "Ng\u01b0\u1eddi_lao_\u0111\u1ed9ng_v\u00e0_do": 1,
+    "Ng\u01b0\u1eddi_s\u1eed_d\u1ee5ng_lao_\u0111\u1ed9": 8,
+    "N\u1ebfu_c\u00f3_n\u1ed9i_dung_kh\u00e1c": 27,
+    "N\u1ebfu_ng\u01b0\u1eddi_lao_\u0111\u1ed9ng_k": 14,
+    "Ph\u1ee5_l\u1ee5c_H\u1ee3p_\u0111\u1ed3ng_lao": 25,
+    "Ph\u1ee5_l\u1ee5c_h\u1ee3p_\u0111\u1ed3ng_c\u1ea7n": 26,
+    "Th\u1ea9m_quy\u1ec1n_tuy\u1ec3n,_qu": 0,
+    "Th\u1eddi_h\u1ea1n_b\u00e1o_tr\u01b0\u1edbc_t": 29,
+    "Th\u1eddi_h\u1ea1n_t\u1ea1m_ho\u00e3n_h\u1ee3": 22,
+    "Tr\u01b0\u1eddng_h\u1ee3p_gi\u1ea3i_th\u1ec3": 4,
+    "V\u0103n_ph\u00f2ng_\u0111\u1ea1i_di\u1ec7n_c": 3,
+    "intent_12_Th\u1ea9m_quy\u1ec1n_giao_k\u1ebft": 11
+  },
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "name": "XLMRoberta",
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "PhobertTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.30.1",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 64001
 }

data/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e1c7209cd9cbaa524adce4c46e717cfb7675d98f0c91e56892a1041c0797a4
-size 1109888810
+oid sha256:a244b641283ecdac7b4a49ec0a1df37814257960d3bdb8fd7b4ac5f69b3836ba
+size 540157426

data/tokenizer_config.json

@@ -2,21 +2,11 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
-  "do_lower_case": false,
   "eos_token": "</s>",
-  "full_tokenizer_file": null,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 512,
+  "mask_token": "<mask>",
+  "model_max_length": 256,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "tokenizer_class": "PhobertTokenizer",
   "unk_token": "<unk>"
 }