Hugging Face's logo

eclec
/
patentClassificationLongFormerTextrank

Text Classification
Transformers
PyTorch
longformer
Generated from Trainer
Model card Files
xet
 Community
eclec commited on
Commit
6ed6ba5
·
1 Parent(s): 269d556

Training in progress, epoch 0

Browse files
Files changed (6) hide show
  1. config.json +1 -1
  2. merges.txt +1 -1
  3. pytorch_model.bin +1 -1
  4. tokenizer.json +0 -1
  5. tokenizer_config.json +4 -0
  6. training_args.bin +2 -2
config.json CHANGED
@@ -58,7 +58,7 @@
58
  "problem_type": "single_label_classification",
59
  "sep_token_id": 2,
60
  "torch_dtype": "float32",
61
- "transformers_version": "4.31.0",
62
  "type_vocab_size": 1,
63
  "vocab_size": 50265
64
  }
 
58
  "problem_type": "single_label_classification",
59
  "sep_token_id": 2,
60
  "torch_dtype": "float32",
61
+ "transformers_version": "4.32.1",
62
  "type_vocab_size": 1,
63
  "vocab_size": 50265
64
  }
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
 
1
+ #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b64a58226715da13b54da10024e47ac40d1c8e99b1cbd4fbcc3c718363ed4d82
3
  size 1738600369
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f683fc518a14964be2d614e020755bece4ff3a2bdb75cdb030c8db3b474fb2
3
  size 1738600369
tokenizer.json CHANGED
@@ -87,7 +87,6 @@
87
  "continuing_subword_prefix": "",
88
  "end_of_word_suffix": "",
89
  "fuse_unk": false,
90
- "byte_fallback": false,
91
  "vocab": {
92
  "<s>": 0,
93
  "<pad>": 1,
 
87
  "continuing_subword_prefix": "",
88
  "end_of_word_suffix": "",
89
  "fuse_unk": false,
 
90
  "vocab": {
91
  "<s>": 0,
92
  "<pad>": 1,
tokenizer_config.json CHANGED
@@ -6,10 +6,14 @@
6
  "eos_token": "</s>",
7
  "errors": "replace",
8
  "mask_token": "<mask>",
 
9
  "model_max_length": 4096,
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
 
12
  "tokenizer_class": "LongformerTokenizer",
13
  "trim_offsets": true,
 
 
14
  "unk_token": "<unk>"
15
  }
 
6
  "eos_token": "</s>",
7
  "errors": "replace",
8
  "mask_token": "<mask>",
9
+ "max_length": 4096,
10
  "model_max_length": 4096,
11
  "pad_token": "<pad>",
12
  "sep_token": "</s>",
13
+ "stride": 0,
14
  "tokenizer_class": "LongformerTokenizer",
15
  "trim_offsets": true,
16
+ "truncation_side": "right",
17
+ "truncation_strategy": "longest_first",
18
  "unk_token": "<unk>"
19
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c56b156863bd64d0f35e44b3de6a0e05f3cde94719e4f41cc8ce1e1467826e27
3
- size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e26e62b16a293407814f49e54f624e85ab2cf305273143011cce6cc47beb000
3
+ size 4091