Xenova HF staff commited on
Commit
e4b9f85
1 Parent(s): f90e5c6

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -44,7 +44,7 @@
44
  "output_past": false,
45
  "pad_token_id": 1,
46
  "scale_embedding": false,
47
- "transformers_version": "4.27.3",
48
  "use_cache": true,
49
  "vocab_size": 50265
50
  }
 
44
  "output_past": false,
45
  "pad_token_id": 1,
46
  "scale_embedding": false,
47
+ "transformers_version": "4.29.2",
48
  "use_cache": true,
49
  "vocab_size": 50265
50
  }
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
 
1
+ #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13076f39cd0ff9c61aa05977097fda4815f90681f57fdc71a6e8c69e425b303f
3
+ size 1630252125
onnx/model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3256c9cdb48b43b3fe46b072a07fb807654ffd37cda50592bbbddabb00178d23
3
- size 411300214
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79264bca2141db256976b7a53657bf2ef6162b48924f3c6aa84ad6b02401c9e
3
+ size 409942730
tokenizer.json CHANGED
@@ -82,6 +82,7 @@
82
  "continuing_subword_prefix": "",
83
  "end_of_word_suffix": "",
84
  "fuse_unk": false,
 
85
  "vocab": {
86
  "<s>": 0,
87
  "<pad>": 1,
 
82
  "continuing_subword_prefix": "",
83
  "end_of_word_suffix": "",
84
  "fuse_unk": false,
85
+ "byte_fallback": false,
86
  "vocab": {
87
  "<s>": 0,
88
  "<pad>": 1,
tokenizer_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "add_prefix_space": false,
3
  "bos_token": "<s>",
 
4
  "cls_token": "<s>",
5
  "eos_token": "</s>",
6
  "errors": "replace",
@@ -8,7 +9,6 @@
8
  "model_max_length": 1024,
9
  "pad_token": "<pad>",
10
  "sep_token": "</s>",
11
- "special_tokens_map_file": null,
12
  "tokenizer_class": "BartTokenizer",
13
  "trim_offsets": true,
14
  "unk_token": "<unk>"
 
1
  {
2
  "add_prefix_space": false,
3
  "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
  "errors": "replace",
 
9
  "model_max_length": 1024,
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
 
12
  "tokenizer_class": "BartTokenizer",
13
  "trim_offsets": true,
14
  "unk_token": "<unk>"