Upload 13 files
Browse files- 1_Pooling/config.json +7 -0
- 2_Dense/config.json +1 -0
- 2_Dense/pytorch_model.bin +3 -0
- config.json +26 -0
- config_sentence_transformers.json +7 -0
- eval/similarity_evaluation_results.csv +6 -0
- modules.json +20 -0
- pytorch_model.bin +3 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
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 |
+
}
|
2_Dense/config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"in_features": 768, "out_features": 512, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}
|
2_Dense/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29b4dde113e1ac96597c4637486cd73f6f63a124318eb0d63fe8c81d0693e10b
|
3 |
+
size 1575975
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/pauloricardo/.var/app/com.visualstudio.code/cache/torch/sentence_transformers/sentence-transformers_distiluse-base-multilingual-cased-v2/",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"output_hidden_states": true,
|
17 |
+
"output_past": true,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"qa_dropout": 0.1,
|
20 |
+
"seq_classif_dropout": 0.2,
|
21 |
+
"sinusoidal_pos_embds": false,
|
22 |
+
"tie_weights_": true,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.10.0",
|
25 |
+
"vocab_size": 119547
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.0.0",
|
4 |
+
"transformers": "4.7.0",
|
5 |
+
"pytorch": "1.9.0+cu102"
|
6 |
+
}
|
7 |
+
}
|
eval/similarity_evaluation_results.csv
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
|
2 |
+
0,-1,0.5174875039139956,0.5248372027622699,0.33798642190433126,0.35170439900624056,0.3349767017088718,0.3490700920606528,0.4902855640715832,0.48015906508482875
|
3 |
+
1,-1,0.7193973811569867,0.678597375114273,0.4871835211597779,0.46643216968298906,0.48339328767405376,0.46309528592638083,0.6820348903144621,0.6256142740959134
|
4 |
+
2,-1,0.8112572676165254,0.7475208685429895,0.5154964388567129,0.4713152386095507,0.5123794370478965,0.4679777501787965,0.7641307826555603,0.6797402101641478
|
5 |
+
3,-1,0.8624412122195104,0.7994695821932087,0.5711897645943975,0.5167928586551885,0.5681872677194924,0.5133831675640919,0.8157594828650556,0.7285320607381383
|
6 |
+
4,-1,0.8782243830126404,0.8097415694008141,0.5689031276827549,0.5102694029308016,0.5663245012837022,0.5073961519261122,0.8253645521788804,0.7289143842641042
|
modules.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
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_Dense",
|
18 |
+
"type": "sentence_transformers.models.Dense"
|
19 |
+
}
|
20 |
+
]
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d2e302d1aea7bac966016630e60883b2384a8e3f6420c638c874fe43ab4b97d
|
3 |
+
size 538972985
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 128,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "/home/reimers/.cache/torch/sentence_transformers/sbert.net_models_distiluse-base-multilingual-cased/0_DistilBERT/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "/home/pauloricardo/.var/app/com.visualstudio.code/cache/torch/sentence_transformers/sentence-transformers_distiluse-base-multilingual-cased-v2/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|