update model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "fnlp/bart-base-chinese",
+  "_name_or_path": "voidful/bart-base-chinese",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,
@@ -8,7 +8,7 @@
     "BartForConditionalGeneration"
   ],
   "attention_dropout": 0.1,
-  "bos_token_id": 101,
+  "bos_token_id": 0,
   "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
   "d_model": 768,
@@ -16,15 +16,15 @@
   "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
-  "decoder_start_token_id": 102,
+  "decoder_start_token_id": 2,
   "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,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
@@ -38,14 +38,14 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_position_embeddings": 512,
+  "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,
+  "pad_token_id": 1,
   "scale_embedding": false,
   "task_specific_params": {
     "summarization": {
@@ -71,5 +71,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.20.1",
   "use_cache": true,
-  "vocab_size": 21128
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd65ef78c7d5710b0bc7f3dd73a4b51d1051c310458da027585ca9a567bc146b
-size 530099703
+oid sha256:efb7d07f05269cbb346e9fc22e3290c3d1520a8323a39287104723a13e6e8e1c
+size 712379703

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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_config.json

@@ -1,15 +1,16 @@
 {
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "name_or_path": "fnlp/bart-base-chinese",
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "special_tokens_map_file": "/remote-home/yfshao/.cache/huggingface/transformers/d521373fc7ac35f63d56cf303de74a202403dcf1aaa792cd01f653694be59563.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "name_or_path": "voidful/bart-base-chinese",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }