fix tokenizer https://github.com/huggingface/transformers/issues/9850#issue-795118067

config.json

@@ -1,64 +1,36 @@
 {
+  "_name_or_path": "wptoux/albert-chinese-large-qa",
   "_num_labels": 2,
   "architectures": [
     "AlbertForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0,
-  "bad_words_ids": null,
   "bos_token_id": 2,
   "classifier_dropout_prob": 0.1,
-  "decoder_start_token_id": null,
-  "do_sample": false,
   "down_scale_factor": 1,
-  "early_stopping": false,
   "embedding_size": 128,
   "eos_token_id": 3,
-  "finetuning_task": null,
   "gap_size": 0,
   "hidden_act": "relu",
   "hidden_dropout_prob": 0,
   "hidden_size": 1024,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1"
-  },
   "initializer_range": 0.02,
   "inner_group_num": 1,
   "intermediate_size": 4096,
-  "is_decoder": false,
-  "is_encoder_decoder": false,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1
-  },
   "layer_norm_eps": 1e-12,
   "layers_to_keep": [],
-  "length_penalty": 1.0,
-  "max_length": 20,
   "max_position_embeddings": 512,
-  "min_length": 0,
   "model_type": "albert",
   "net_structure_type": 0,
-  "no_repeat_ngram_size": 0,
   "num_attention_heads": 16,
-  "num_beams": 1,
   "num_hidden_groups": 1,
   "num_hidden_layers": 24,
   "num_memory_blocks": 0,
-  "num_return_sequences": 1,
-  "output_attentions": false,
-  "output_hidden_states": false,
   "output_past": true,
   "pad_token_id": 0,
-  "prefix": null,
-  "pruned_heads": {},
-  "repetition_penalty": 1.0,
-  "task_specific_params": null,
-  "temperature": 1.0,
-  "top_k": 50,
-  "top_p": 1.0,
-  "torchscript": false,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.2",
   "type_vocab_size": 2,
-  "use_bfloat16": false,
-  "vocab_size": 21128
+  "vocab_size": 21128,
+  "tokenizer_class": "BertTokenizer"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3b10626af99f4155b87a594b183fde039aff0a9a22c8ee8a507d3bb033f6ae
-size 66208204
+oid sha256:7ce291dd15f30272c28b1452326e50b1a921ddd763191693a9f2f4506adf163d
+size 62018265

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false}
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/1f536158f09966b7ddca1f2c06264b78535edb420d115380141a23361d136d78.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "wptoux/albert-chinese-large-qa"}