tardigrade-doc commited on
Commit
0253097
·
verified ·
1 Parent(s): b6d5934

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,8 +1,28 @@
1
  ---
2
- library_name: transformers
3
  tags: []
 
 
 
4
  ---
5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  # Model Card for Model ID
7
 
8
  <!-- Provide a quick summary of what the model is/does. -->
@@ -196,4 +216,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
196
 
197
  ## Model Card Contact
198
 
199
- [More Information Needed]
 
1
  ---
2
+ library_name: transformers.js
3
  tags: []
4
+ base_model:
5
+ - tardigrade-doc/chinese-ambiguous-chars-model
6
+ pipeline_tag: fill-mask
7
  ---
8
 
9
+
10
+
11
+ # chinese-ambiguous-chars-model (ONNX)
12
+
13
+
14
+ This is an ONNX version of [tardigrade-doc/chinese-ambiguous-chars-model](https://huggingface.co/tardigrade-doc/chinese-ambiguous-chars-model). It was automatically converted and uploaded using [this Hugging Face Space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
15
+
16
+
17
+ ## Usage with Transformers.js
18
+
19
+
20
+ See the pipeline documentation for `fill-mask`: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.FillMaskPipeline
21
+
22
+
23
+ ---
24
+
25
+
26
  # Model Card for Model ID
27
 
28
  <!-- Provide a quick summary of what the model is/does. -->
 
216
 
217
  ## Model Card Contact
218
 
219
+ [More Information Needed]
config.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
- "add_cross_attention": false,
 
3
  "architectures": [
4
  "BertForMaskedLM"
5
  ],
@@ -14,7 +15,6 @@
14
  "hidden_size": 768,
15
  "initializer_range": 0.02,
16
  "intermediate_size": 3072,
17
- "is_decoder": false,
18
  "layer_norm_eps": 1e-12,
19
  "max_position_embeddings": 512,
20
  "model_type": "bert",
@@ -27,8 +27,9 @@
27
  "pooler_num_fc_layers": 3,
28
  "pooler_size_per_head": 128,
29
  "pooler_type": "first_token_transform",
30
- "tie_word_embeddings": true,
31
- "transformers_version": "5.0.0",
 
32
  "type_vocab_size": 2,
33
  "use_cache": false,
34
  "vocab_size": 21128
 
1
  {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "tardigrade-doc/chinese-ambiguous-chars-model",
4
  "architectures": [
5
  "BertForMaskedLM"
6
  ],
 
15
  "hidden_size": 768,
16
  "initializer_range": 0.02,
17
  "intermediate_size": 3072,
 
18
  "layer_norm_eps": 1e-12,
19
  "max_position_embeddings": 512,
20
  "model_type": "bert",
 
27
  "pooler_num_fc_layers": 3,
28
  "pooler_size_per_head": 128,
29
  "pooler_type": "first_token_transform",
30
+ "position_embedding_type": "absolute",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.49.0",
33
  "type_vocab_size": 2,
34
  "use_cache": false,
35
  "vocab_size": 21128
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d066adac34006f58e6387e0066e4a2aac76af32e9d2dcbc9894a17411ffa51f
3
+ size 409474412
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae34b5ff942cc39ecc1abff949f164c3fa0cceb63965e76e02a05ffb3b6c2af
3
+ size 115495369
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00892970e609e2479ac5e84dafd5ea62f0f96e1a16057145fba1779125e230b
3
+ size 204894066
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b31653ea31ea2d4003a6090ea83eca277f1f5d67be282b9d5bf066a9d421fd
3
+ size 103551774
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dc18510004fb52b704768d0c97d80ee74a480d57572e82436b90916ba0b04d8
3
+ size 120840114
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c87cd71eb966e29f43f3acd499acb53119baaf2ff076860ec646804c1763a4
3
+ size 81963547
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b31653ea31ea2d4003a6090ea83eca277f1f5d67be282b9d5bf066a9d421fd
3
+ size 103551774
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a06bb2588139f76be91a1a35f835dc2c44ee8ade430c56aada8a56abecb02e1b
3
+ size 103551774
quantize_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modes": [
3
+ "fp16",
4
+ "q8",
5
+ "int8",
6
+ "uint8",
7
+ "q4",
8
+ "q4f16",
9
+ "bnb4"
10
+ ],
11
+ "per_channel": true,
12
+ "reduce_range": true,
13
+ "block_size": null,
14
+ "is_symmetric": true,
15
+ "accuracy_level": null,
16
+ "quant_type": 1,
17
+ "op_block_list": null
18
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json CHANGED
@@ -1,14 +1,65 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "backend": "tokenizers",
 
3
  "cls_token": "[CLS]",
4
  "do_lower_case": false,
 
5
  "is_local": false,
6
  "mask_token": "[MASK]",
 
7
  "model_max_length": 1000000000000000019884624838656,
 
8
  "pad_token": "[PAD]",
 
 
9
  "sep_token": "[SEP]",
 
10
  "strip_accents": null,
11
  "tokenize_chinese_chars": true,
12
  "tokenizer_class": "BertTokenizer",
 
 
13
  "unk_token": "[UNK]"
14
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
  "backend": "tokenizers",
45
+ "clean_up_tokenization_spaces": false,
46
  "cls_token": "[CLS]",
47
  "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
  "is_local": false,
50
  "mask_token": "[MASK]",
51
+ "max_length": 128,
52
  "model_max_length": 1000000000000000019884624838656,
53
+ "pad_to_multiple_of": null,
54
  "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
  "sep_token": "[SEP]",
58
+ "stride": 0,
59
  "strip_accents": null,
60
  "tokenize_chinese_chars": true,
61
  "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
  "unk_token": "[UNK]"
65
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff