Commit
•
a96d8eb
1
Parent(s):
07c3dd8
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +1 -1
- README.md +5 -5
- config.json +15 -12
- model.safetensors +2 -2
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +20 -6
- tokenizer.json +0 -0
- tokenizer_config.json +18 -19
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"word_embedding_dimension":
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
|
|
1 |
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
README.md
CHANGED
@@ -10,7 +10,7 @@ tags:
|
|
10 |
|
11 |
# {MODEL_NAME}
|
12 |
|
13 |
-
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a
|
14 |
|
15 |
<!--- Describe your model here -->
|
16 |
|
@@ -47,9 +47,9 @@ The model was trained with the parameters:
|
|
47 |
|
48 |
**DataLoader**:
|
49 |
|
50 |
-
`torch.utils.data.dataloader.DataLoader` of length
|
51 |
```
|
52 |
-
{'batch_size':
|
53 |
```
|
54 |
|
55 |
**Loss**:
|
@@ -81,8 +81,8 @@ Parameters of the fit()-Method:
|
|
81 |
## Full Model Architecture
|
82 |
```
|
83 |
SentenceTransformer(
|
84 |
-
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model:
|
85 |
-
(1): Pooling({'word_embedding_dimension':
|
86 |
(2): Normalize()
|
87 |
)
|
88 |
```
|
|
|
10 |
|
11 |
# {MODEL_NAME}
|
12 |
|
13 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
14 |
|
15 |
<!--- Describe your model here -->
|
16 |
|
|
|
47 |
|
48 |
**DataLoader**:
|
49 |
|
50 |
+
`torch.utils.data.dataloader.DataLoader` of length 1459 with parameters:
|
51 |
```
|
52 |
+
{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
53 |
```
|
54 |
|
55 |
**Loss**:
|
|
|
81 |
## Full Model Architecture
|
82 |
```
|
83 |
SentenceTransformer(
|
84 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
|
85 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
86 |
(2): Normalize()
|
87 |
)
|
88 |
```
|
config.json
CHANGED
@@ -1,25 +1,28 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "intfloat/e5-
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
-
"hidden_size":
|
11 |
"initializer_range": 0.02,
|
12 |
-
"intermediate_size":
|
13 |
-
"layer_norm_eps": 1e-
|
14 |
-
"max_position_embeddings":
|
15 |
-
"model_type": "
|
16 |
-
"num_attention_heads":
|
17 |
-
"num_hidden_layers":
|
18 |
-
"
|
|
|
19 |
"position_embedding_type": "absolute",
|
20 |
"torch_dtype": "float32",
|
21 |
"transformers_version": "4.38.2",
|
22 |
-
"type_vocab_size":
|
23 |
"use_cache": true,
|
24 |
-
"vocab_size":
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "intfloat/multilingual-e5-base",
|
3 |
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
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,
|
13 |
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
"position_embedding_type": "absolute",
|
23 |
"torch_dtype": "float32",
|
24 |
"transformers_version": "4.38.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7ce78e564d187d8e28a5446cea2e9a7b3037b4e860e4d04879473780e321d7b
|
3 |
+
size 1112197096
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
CHANGED
@@ -1,34 +1,48 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
-
"
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
"sep_token": {
|
24 |
-
"content": "
|
25 |
"lstrip": false,
|
26 |
"normalized": false,
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
"unk_token": {
|
31 |
-
"content": "
|
32 |
"lstrip": false,
|
33 |
"normalized": false,
|
34 |
"rstrip": false,
|
|
|
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,
|
26 |
+
"normalized": false,
|
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,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,55 +1,54 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
37 |
-
"lstrip":
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "
|
46 |
-
"
|
47 |
-
"mask_token": "
|
48 |
"model_max_length": 512,
|
49 |
-
"pad_token": "
|
50 |
-
"sep_token": "
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"tokenizer_class": "BertTokenizer",
|
54 |
-
"unk_token": "[UNK]"
|
55 |
}
|
|
|
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 |
+
"mask_token": "<mask>",
|
49 |
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
|
|
|
|
54 |
}
|