Commit
•
f45f67e
1
Parent(s):
1ede857
from Google Colab
Browse files- config.json +55 -0
- modules.json +14 -0
- pooling_config.json +7 -0
- pytorch_model.bin +3 -0
- sentence_bert_config.json +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_num_labels": 2,
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bad_words_ids": null,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"decoder_start_token_id": null,
|
10 |
+
"do_sample": false,
|
11 |
+
"early_stopping": false,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"finetuning_task": null,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 1024,
|
17 |
+
"id2label": {
|
18 |
+
"0": "LABEL_0",
|
19 |
+
"1": "LABEL_1"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 4096,
|
23 |
+
"is_decoder": false,
|
24 |
+
"is_encoder_decoder": false,
|
25 |
+
"label2id": {
|
26 |
+
"LABEL_0": 0,
|
27 |
+
"LABEL_1": 1
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-05,
|
30 |
+
"length_penalty": 1.0,
|
31 |
+
"max_length": 20,
|
32 |
+
"max_position_embeddings": 514,
|
33 |
+
"min_length": 0,
|
34 |
+
"model_type": "xlm-roberta",
|
35 |
+
"no_repeat_ngram_size": 0,
|
36 |
+
"num_attention_heads": 16,
|
37 |
+
"num_beams": 1,
|
38 |
+
"num_hidden_layers": 24,
|
39 |
+
"num_return_sequences": 1,
|
40 |
+
"output_attentions": false,
|
41 |
+
"output_hidden_states": false,
|
42 |
+
"output_past": true,
|
43 |
+
"pad_token_id": 1,
|
44 |
+
"prefix": null,
|
45 |
+
"pruned_heads": {},
|
46 |
+
"repetition_penalty": 1.0,
|
47 |
+
"task_specific_params": null,
|
48 |
+
"temperature": 1.0,
|
49 |
+
"top_k": 50,
|
50 |
+
"top_p": 1.0,
|
51 |
+
"torchscript": false,
|
52 |
+
"type_vocab_size": 1,
|
53 |
+
"use_bfloat16": false,
|
54 |
+
"vocab_size": 250002
|
55 |
+
}
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "0_Transformer",
|
6 |
+
"type": "transquest.algo.siamese_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "transquest.algo.siamese_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
pooling_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 1024,
|
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 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89df001bcf6d904267c37d1ba35409b01f402bcfbf2a8cfa137970cad4d46920
|
3 |
+
size 2239653011
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": "0.2.6"
|
3 |
+
}
|
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
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"max_len": 512}
|