finiteautomata commited on
Commit
7765398
1 Parent(s): 2dff889

Non contextualized update

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
1
+ {"[EMOJI]": 31004, "[HASHTAG]": 31003, "[USER]": 31002}
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "./results/checkpoint-3417",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
@@ -29,5 +29,5 @@
29
  "transformers_version": "4.4.0",
30
  "type_vocab_size": 2,
31
  "use_cache": true,
32
- "vocab_size": 31002
33
  }
1
  {
2
+ "_name_or_path": "./results/checkpoint-6834",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
29
  "transformers_version": "4.4.0",
30
  "type_vocab_size": 2,
31
  "use_cache": true,
32
+ "vocab_size": 31005
33
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bb282c476fa09df3fec6c3dce5b7ebb0e5e8c68899c445d67c13230bb0a1edb
3
- size 439496979
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a222cb7abc90ebac6e0a7029e214d492e77521dae116dda2304e95f5e8c495d
3
+ size 439506198
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[USER]", "[HASHTAG]", "[EMOJI]"]}
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": false, "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": "/home/jmperez/.cache/huggingface/transformers/9848a00af462c42dfb4ec88ef438fbab5256330f7f6f50badc48d277f9367d49.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "dccuchile/bert-base-spanish-wwm-cased", "do_basic_tokenize": true, "never_split": null}
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/home/jmperez/.cache/huggingface/transformers/78141ed1e8dcc5ff370950397ca0d1c5c9da478f54ec14544187d8a93eff1a26.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66", "name_or_path": "dccuchile/bert-base-spanish-wwm-uncased"}
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff