shahrukhx01
commited on
Commit
Β·
6a799e5
1
Parent(s):
34d92e0
add siamese smole bert
Browse files- 0_Transformer/config.json +31 -0
- pytorch_model.bin β 0_Transformer/pytorch_model.bin +0 -0
- sentence_bert_config.json β 0_Transformer/sentence_bert_config.json +0 -0
- special_tokens_map.json β 0_Transformer/special_tokens_map.json +0 -0
- tokenizer_config.json β 0_Transformer/tokenizer_config.json +0 -0
- vocab.txt β 0_Transformer/vocab.txt +0 -0
- 1_Pooling/config.json +7 -0
- config.json +2 -30
- modules.json +14 -0
0_Transformer/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "shahrukhx01/smole-bert",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 512,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 2048,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0,
|
20 |
+
"LABEL_1": 1,
|
21 |
+
"LABEL_2": 2
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 768,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 8,
|
27 |
+
"num_hidden_layers": 6,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"type_vocab_size": 5,
|
30 |
+
"vocab_size": 4096
|
31 |
+
}
|
pytorch_model.bin β 0_Transformer/pytorch_model.bin
RENAMED
File without changes
|
sentence_bert_config.json β 0_Transformer/sentence_bert_config.json
RENAMED
File without changes
|
special_tokens_map.json β 0_Transformer/special_tokens_map.json
RENAMED
File without changes
|
tokenizer_config.json β 0_Transformer/tokenizer_config.json
RENAMED
File without changes
|
vocab.txt β 0_Transformer/vocab.txt
RENAMED
File without changes
|
1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 512,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false
|
7 |
+
}
|
config.json
CHANGED
@@ -1,31 +1,3 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
"BertModel"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"gradient_checkpointing": false,
|
8 |
-
"hidden_act": "gelu",
|
9 |
-
"hidden_dropout_prob": 0.1,
|
10 |
-
"hidden_size": 512,
|
11 |
-
"id2label": {
|
12 |
-
"0": "LABEL_0",
|
13 |
-
"1": "LABEL_1",
|
14 |
-
"2": "LABEL_2"
|
15 |
-
},
|
16 |
-
"initializer_range": 0.02,
|
17 |
-
"intermediate_size": 2048,
|
18 |
-
"label2id": {
|
19 |
-
"LABEL_0": 0,
|
20 |
-
"LABEL_1": 1,
|
21 |
-
"LABEL_2": 2
|
22 |
-
},
|
23 |
-
"layer_norm_eps": 1e-12,
|
24 |
-
"max_position_embeddings": 768,
|
25 |
-
"model_type": "bert",
|
26 |
-
"num_attention_heads": 8,
|
27 |
-
"num_hidden_layers": 6,
|
28 |
-
"pad_token_id": 0,
|
29 |
-
"type_vocab_size": 5,
|
30 |
-
"vocab_size": 4096
|
31 |
-
}
|
|
|
1 |
{
|
2 |
+
"__version__": "1.0.4"
|
3 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "0_Transformer",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|