Commit
•
29db279
1
Parent(s):
5a2ac04
Add Model with custom pooling layer
Browse files- .DS_Store +0 -0
- 1_WKPooling/config.json +5 -0
- config.json +57 -0
- modules.json +14 -0
- pytorch_model.bin +3 -0
- sentence_bert_config.json +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
.DS_Store
ADDED
Binary file (8.2 kB). View file
|
|
1_WKPooling/config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"layer_start": 4,
|
4 |
+
"context_window_size": 2
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_num_labels": 2,
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bad_words_ids": null,
|
9 |
+
"bos_token_id": null,
|
10 |
+
"decoder_start_token_id": null,
|
11 |
+
"dim": 768,
|
12 |
+
"do_sample": false,
|
13 |
+
"dropout": 0.1,
|
14 |
+
"early_stopping": false,
|
15 |
+
"eos_token_id": null,
|
16 |
+
"finetuning_task": null,
|
17 |
+
"hidden_dim": 3072,
|
18 |
+
"id2label": {
|
19 |
+
"0": "LABEL_0",
|
20 |
+
"1": "LABEL_1"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"is_decoder": false,
|
24 |
+
"is_encoder_decoder": false,
|
25 |
+
"label2id": {
|
26 |
+
"LABEL_0": 0,
|
27 |
+
"LABEL_1": 1
|
28 |
+
},
|
29 |
+
"length_penalty": 1.0,
|
30 |
+
"max_length": 20,
|
31 |
+
"max_position_embeddings": 512,
|
32 |
+
"min_length": 0,
|
33 |
+
"model_type": "distilbert",
|
34 |
+
"n_heads": 12,
|
35 |
+
"n_layers": 6,
|
36 |
+
"no_repeat_ngram_size": 0,
|
37 |
+
"num_beams": 1,
|
38 |
+
"num_return_sequences": 1,
|
39 |
+
"output_attentions": false,
|
40 |
+
"output_hidden_states": true,
|
41 |
+
"output_past": true,
|
42 |
+
"pad_token_id": 0,
|
43 |
+
"prefix": null,
|
44 |
+
"pruned_heads": {},
|
45 |
+
"qa_dropout": 0.1,
|
46 |
+
"repetition_penalty": 1.0,
|
47 |
+
"seq_classif_dropout": 0.2,
|
48 |
+
"sinusoidal_pos_embds": false,
|
49 |
+
"task_specific_params": null,
|
50 |
+
"temperature": 1.0,
|
51 |
+
"tie_weights_": true,
|
52 |
+
"top_k": 50,
|
53 |
+
"top_p": 1.0,
|
54 |
+
"torchscript": false,
|
55 |
+
"use_bfloat16": false,
|
56 |
+
"vocab_size": 30522
|
57 |
+
}
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_WKPooling",
|
12 |
+
"type": "sentence_transformers.models.WKPooling"
|
13 |
+
}
|
14 |
+
]
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e9f8b1e85657b209941057dd15542e5b85d18f110ad5edf8500163dec9bf8c1
|
3 |
+
size 265472230
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 128
|
3 |
+
}
|
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_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "max_len": 512, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|