Model save

.gitignore

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

added_tokens.json

@@ -0,0 +1,104 @@
+{
+  "㓉": 51357,
+  "㔌": 51307,
+  "㔷": 51276,
+  "㔻": 51316,
+  "㕪": 51303,
+  "㖭": 51281,
+  "㗇": 51300,
+  "㗳": 51329,
+  "㗻": 51331,
+  "㗾": 51309,
+  "㘉": 51313,
+  "㘝": 51289,
+  "㠀": 51345,
+  "㡁": 51314,
+  "㢌": 51338,
+  "㢜": 51336,
+  "㣇": 51335,
+  "㤿": 51332,
+  "㧬": 51293,
+  "㨂": 51291,
+  "㨘": 51326,
+  "㨢": 51334,
+  "㬓": 51310,
+  "㬱": 51359,
+  "㭾": 51369,
+  "㰤": 51341,
+  "㱽": 51324,
+  "㺂": 51349,
+  "㽺": 51361,
+  "䀆": 51367,
+  "䂿": 51350,
+  "䅌": 51346,
+  "䉪": 51368,
+  "䉯": 51343,
+  "䉺": 51337,
+  "䊦": 51280,
+  "䋫": 51321,
+  "䑛": 51312,
+  "䘆": 51283,
+  "䘒": 51355,
+  "䤔": 51344,
+  "䤵": 51284,
+  "䦥": 51333,
+  "䧘": 51348,
+  "䫿": 51330,
+  "䭮": 51352,
+  "䯀": 51286,
+  "䰙": 51370,
+  "䶩": 51339,
+  "嘺": 51288,
+  "圖書館": 51371,
+  "地鐵站": 51372,
+  "𠍁": 51328,
+  "𠓼": 51318,
+  "𠯔": 51347,
+  "𠱁": 51285,
+  "𠲜": 51364,
+  "𠳏": 51358,
+  "𠴝": 51366,
+  "𠵿": 51274,
+  "𠹺": 51282,
+  "𠼮": 51305,
+  "𠼻": 51297,
+  "𡁯": 51317,
+  "𡁵": 51290,
+  "𡃈": 51351,
+  "𡲢": 51320,
+  "𡷹": 51304,
+  "𢫏": 51275,
+  "𢫕": 51327,
+  "𢬿": 51287,
+  "𢭃": 51325,
+  "𢯎": 51301,
+  "𢱕": 51295,
+  "𢲡": 51362,
+  "𢲩": 51353,
+  "𢴒": 51294,
+  "𣖕": 51315,
+  "𣚺": 51356,
+  "𣵷": 51323,
+  "𤗈": 51308,
+  "𤗲": 51271,
+  "𤘅": 51273,
+  "𤶸": 51298,
+  "𤺊": 51340,
+  "𥄫": 51277,
+  "𦉘": 51365,
+  "𦟌": 51299,
+  "𦢊": 51311,
+  "𧇣": 51278,
+  "𧊅": 51296,
+  "𧕴": 51363,
+  "𧜵": 51354,
+  "𨂽": 51306,
+  "𨂾": 51272,
+  "𨇣": 51302,
+  "𨈇": 51319,
+  "𨋍": 51360,
+  "𨛜": 51342,
+  "𩪷": 51322,
+  "𩰫": 51292,
+  "𪐀": 51279
+}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "notebooks/cantonese/bart-base-chinese",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 101,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 102,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 102,
+  "forced_eos_token_id": 102,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 51373
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 101,
+  "decoder_start_token_id": 102,
+  "early_stopping": true,
+  "eos_token_id": 102,
+  "forced_eos_token_id": 102,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17ededfa850831a31623f8900e1c7c8f1e729a7996e54cab1f2027b2fb70b71
+size 561379866

runs/Oct31_09-29-23_hkmustamd-Super-Server/1730338218.2067604/events.out.tfevents.1730338218.hkmustamd-Super-Server.1987719.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb56bf1589a87c69afb2fc9f0de0e5a97f0ac0ce77932509bc03d191135af36
+size 5971

runs/Oct31_09-29-23_hkmustamd-Super-Server/events.out.tfevents.1730338218.hkmustamd-Super-Server.1987719.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9333d1b37ed7e4a488b3f30d2765211f104453f9929fbe90c00ba01d68bdb6
+size 5889

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[EOS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]",
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8010a3b64dc447ffed2610144f31e35038e5252e208a993b96effb9a5e344f4d
+size 4152