Hugging Face's logo

intfloat
/
multilingual-e5-base

Sentence Similarity
sentence-transformers
PyTorch
ONNX
Safetensors
OpenVINO
xlm-roberta
mteb
Sentence Transformers
Eval Results
text-embeddings-inference
Model card Files
xet
Community
30

Adding ONNX file of this model

#28
by ra1f - opened
base: refs/heads/main
←
from: refs/pr/28
Discussion Files changed
+509
-541
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. README.md +0 -0
  3. onnx/config.json +4 -2
  4. onnx/model.onnx +2 -2
  5. onnx/special_tokens_map.json +42 -6
  6. onnx/tokenizer.json +2 -2
  7. onnx/tokenizer_config.json +44 -8
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
36
+ onnx/tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
The diff for this file is too large to render. See raw diff
 
onnx/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "intfloat/multilingual-e5-base",
3
  "architectures": [
4
  "XLMRobertaModel"
5
  ],
@@ -7,6 +7,7 @@
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
  "eos_token_id": 2,
 
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
@@ -20,7 +21,8 @@
20
  "output_past": true,
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
- "transformers_version": "4.30.2",
 
24
  "type_vocab_size": 1,
25
  "use_cache": true,
26
  "vocab_size": 250002
 
1
  {
2
+ "_attn_implementation_autoset": true,
3
  "architectures": [
4
  "XLMRobertaModel"
5
  ],
 
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
  "eos_token_id": 2,
10
+ "export_model_type": "transformer",
11
  "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
13
  "hidden_size": 768,
 
21
  "output_past": true,
22
  "pad_token_id": 1,
23
  "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.51.3",
26
  "type_vocab_size": 1,
27
  "use_cache": true,
28
  "vocab_size": 250002
onnx/model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84a4d426f7e87a6bf5bf195f0bae2c4a7d15f675b23ca96f42fab8326d7a77aa
3
- size 1110059084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05d4c52ff670b68f2968c36ab33d3196d4a5f4e34957f78336f23231da026d5
3
+ size 1110158366
onnx/special_tokens_map.json CHANGED
@@ -1,7 +1,25 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
@@ -9,7 +27,25 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
  "content": "<mask>",
25
  "lstrip": true,
 
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
onnx/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
- size 17082660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
3
+ size 17082734
onnx/tokenizer_config.json CHANGED
@@ -1,16 +1,52 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
  "cls_token": "<s>",
5
  "eos_token": "</s>",
6
- "mask_token": {
7
- "__type": "AddedToken",
8
- "content": "<mask>",
9
- "lstrip": true,
10
- "normalized": true,
11
- "rstrip": false,
12
- "single_word": false
13
- },
14
  "model_max_length": 512,
15
  "pad_token": "<pad>",
16
  "sep_token": "</s>",
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
  "bos_token": "<s>",
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
 
 
 
 
 
 
50
  "model_max_length": 512,
51
  "pad_token": "<pad>",
52
  "sep_token": "</s>",