nguyenthaibinh
commited on
Commit
•
fef0213
1
Parent(s):
14f5784
new model with pooler and normalizer
Browse files- config.json +2 -2
- config_sentence_transformers.json +7 -0
- model.onnx +2 -2
- model_descriptions.json +6 -0
- modules.json +0 -3
- special_tokens_map.json +35 -5
- tokenizer.json +2 -14
- tokenizer_config.json +48 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "llm-embedder",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
@@ -29,4 +29,4 @@
|
|
29 |
"type_vocab_size": 2,
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 30522
|
32 |
-
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "BAAI/llm-embedder",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
|
|
29 |
"type_vocab_size": 2,
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 30522
|
32 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.30.0",
|
5 |
+
"pytorch": "2.0.1+cu117"
|
6 |
+
}
|
7 |
+
}
|
model.onnx
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:d6a5c5cb2457a07733e95b8a1480560df251127722b572f85687eb773f80e13e
|
3 |
+
size 435917615
|
model_descriptions.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model": "BAAI/llm-embedder",
|
3 |
+
"embedding_dim": 768,
|
4 |
+
"max_seq_length": 512,
|
5 |
+
"model_file_size (GB)": 0.41
|
6 |
+
}
|
modules.json
CHANGED
@@ -2,19 +2,16 @@
|
|
2 |
{
|
3 |
"idx": 0,
|
4 |
"name": "0",
|
5 |
-
"path": "",
|
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 |
{
|
15 |
"idx": 2,
|
16 |
"name": "2",
|
17 |
-
"path": "2_Normalize",
|
18 |
"type": "sentence_transformers.models.Normalize"
|
19 |
}
|
20 |
]
|
|
|
2 |
{
|
3 |
"idx": 0,
|
4 |
"name": "0",
|
|
|
5 |
"type": "sentence_transformers.models.Transformer"
|
6 |
},
|
7 |
{
|
8 |
"idx": 1,
|
9 |
"name": "1",
|
|
|
10 |
"type": "sentence_transformers.models.Pooling"
|
11 |
},
|
12 |
{
|
13 |
"idx": 2,
|
14 |
"name": "2",
|
|
|
15 |
"type": "sentence_transformers.models.Normalize"
|
16 |
}
|
17 |
]
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,37 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
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.json
CHANGED
@@ -1,19 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 256,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": "BatchLongest",
|
11 |
-
"direction": "Right",
|
12 |
-
"pad_to_multiple_of": null,
|
13 |
-
"pad_id": 0,
|
14 |
-
"pad_type_id": 0,
|
15 |
-
"pad_token": "[PAD]"
|
16 |
-
},
|
17 |
"added_tokens": [
|
18 |
{
|
19 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -1,16 +1,64 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_basic_tokenize": true,
|
5 |
"do_lower_case": true,
|
6 |
"mask_token": "[MASK]",
|
|
|
7 |
"model_max_length": 512,
|
8 |
"never_split": null,
|
|
|
9 |
"pad_token": "[PAD]",
|
|
|
|
|
10 |
"sep_token": "[SEP]",
|
|
|
11 |
"strip_accents": null,
|
12 |
"tokenize_chinese_chars": true,
|
13 |
"tokenizer_class": "BertTokenizer",
|
14 |
"truncation_side": "right",
|
|
|
15 |
"unk_token": "[UNK]"
|
16 |
}
|
|
|
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 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
+
"max_length": 256,
|
50 |
"model_max_length": 512,
|
51 |
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
"strip_accents": null,
|
59 |
"tokenize_chinese_chars": true,
|
60 |
"tokenizer_class": "BertTokenizer",
|
61 |
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "[UNK]"
|
64 |
}
|