Spaces:
Build error
Build error
saved models to lfs
Browse files- saved_models/embedder/1_Pooling/config.json +7 -0
- saved_models/embedder/README.md +107 -0
- saved_models/embedder/config.json +26 -0
- saved_models/embedder/config_sentence_transformers.json +7 -0
- saved_models/embedder/modules.json +14 -0
- saved_models/embedder/pytorch_model.bin +3 -0
- saved_models/embedder/sentence_bert_config.json +4 -0
- saved_models/embedder/special_tokens_map.json +1 -0
- saved_models/embedder/tokenizer.json +0 -0
- saved_models/embedder/tokenizer_config.json +1 -0
- saved_models/embedder/vocab.txt +0 -0
- saved_models/ledmodel/config.json +66 -0
- saved_models/ledmodel/pytorch_model.bin +3 -0
- saved_models/summ_model/config.json +26 -0
- saved_models/summ_model/pytorch_model.bin +3 -0
- saved_models/title_model/config.json +177 -0
- saved_models/title_model/pytorch_model.bin +3 -0
saved_models/embedder/1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
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 |
+
}
|
saved_models/embedder/README.md
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: sentence-similarity
|
3 |
+
license: apache-2.0
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- feature-extraction
|
7 |
+
- sentence-similarity
|
8 |
+
- transformers
|
9 |
+
---
|
10 |
+
|
11 |
+
# sentence-transformers/paraphrase-MiniLM-L6-v2
|
12 |
+
|
13 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
14 |
+
|
15 |
+
|
16 |
+
|
17 |
+
## Usage (Sentence-Transformers)
|
18 |
+
|
19 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
20 |
+
|
21 |
+
```
|
22 |
+
pip install -U sentence-transformers
|
23 |
+
```
|
24 |
+
|
25 |
+
Then you can use the model like this:
|
26 |
+
|
27 |
+
```python
|
28 |
+
from sentence_transformers import SentenceTransformer
|
29 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
30 |
+
|
31 |
+
model = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L6-v2')
|
32 |
+
embeddings = model.encode(sentences)
|
33 |
+
print(embeddings)
|
34 |
+
```
|
35 |
+
|
36 |
+
|
37 |
+
|
38 |
+
## Usage (HuggingFace Transformers)
|
39 |
+
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
|
40 |
+
|
41 |
+
```python
|
42 |
+
from transformers import AutoTokenizer, AutoModel
|
43 |
+
import torch
|
44 |
+
|
45 |
+
|
46 |
+
#Mean Pooling - Take attention mask into account for correct averaging
|
47 |
+
def mean_pooling(model_output, attention_mask):
|
48 |
+
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
|
49 |
+
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
|
50 |
+
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
|
51 |
+
|
52 |
+
|
53 |
+
# Sentences we want sentence embeddings for
|
54 |
+
sentences = ['This is an example sentence', 'Each sentence is converted']
|
55 |
+
|
56 |
+
# Load model from HuggingFace Hub
|
57 |
+
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
|
58 |
+
model = AutoModel.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
|
59 |
+
|
60 |
+
# Tokenize sentences
|
61 |
+
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
62 |
+
|
63 |
+
# Compute token embeddings
|
64 |
+
with torch.no_grad():
|
65 |
+
model_output = model(**encoded_input)
|
66 |
+
|
67 |
+
# Perform pooling. In this case, max pooling.
|
68 |
+
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
|
69 |
+
|
70 |
+
print("Sentence embeddings:")
|
71 |
+
print(sentence_embeddings)
|
72 |
+
```
|
73 |
+
|
74 |
+
|
75 |
+
|
76 |
+
## Evaluation Results
|
77 |
+
|
78 |
+
|
79 |
+
|
80 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/paraphrase-MiniLM-L6-v2)
|
81 |
+
|
82 |
+
|
83 |
+
|
84 |
+
## Full Model Architecture
|
85 |
+
```
|
86 |
+
SentenceTransformer(
|
87 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
88 |
+
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
|
89 |
+
)
|
90 |
+
```
|
91 |
+
|
92 |
+
## Citing & Authors
|
93 |
+
|
94 |
+
This model was trained by [sentence-transformers](https://www.sbert.net/).
|
95 |
+
|
96 |
+
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
|
97 |
+
```bibtex
|
98 |
+
@inproceedings{reimers-2019-sentence-bert,
|
99 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
100 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
101 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
102 |
+
month = "11",
|
103 |
+
year = "2019",
|
104 |
+
publisher = "Association for Computational Linguistics",
|
105 |
+
url = "http://arxiv.org/abs/1908.10084",
|
106 |
+
}
|
107 |
+
```
|
saved_models/embedder/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/codespace/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-MiniLM-L6-v2/",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.17.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
saved_models/embedder/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 |
+
}
|
saved_models/embedder/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_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
saved_models/embedder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5603e0a1c8f32e681811954e368ab69434bdecb49b0e5dc176ad748433362311
|
3 |
+
size 90895537
|
saved_models/embedder/sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 128,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
saved_models/embedder/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
saved_models/embedder/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
saved_models/embedder/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "name_or_path": "/home/codespace/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-MiniLM-L6-v2/", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/home/codespace/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-MiniLM-L6-v2/special_tokens_map.json", "tokenizer_class": "BertTokenizer"}
|
saved_models/embedder/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
saved_models/ledmodel/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/led-large-16384-arxiv",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"architectures": [
|
7 |
+
"LEDForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"attention_window": [
|
11 |
+
1024,
|
12 |
+
1024,
|
13 |
+
1024,
|
14 |
+
1024,
|
15 |
+
1024,
|
16 |
+
1024,
|
17 |
+
1024,
|
18 |
+
1024,
|
19 |
+
1024,
|
20 |
+
1024,
|
21 |
+
1024,
|
22 |
+
1024
|
23 |
+
],
|
24 |
+
"bos_token_id": 0,
|
25 |
+
"classif_dropout": 0.0,
|
26 |
+
"classifier_dropout": 0.0,
|
27 |
+
"d_model": 1024,
|
28 |
+
"decoder_attention_heads": 16,
|
29 |
+
"decoder_ffn_dim": 4096,
|
30 |
+
"decoder_layerdrop": 0.0,
|
31 |
+
"decoder_layers": 12,
|
32 |
+
"decoder_start_token_id": 2,
|
33 |
+
"dropout": 0.1,
|
34 |
+
"encoder_attention_heads": 16,
|
35 |
+
"encoder_ffn_dim": 4096,
|
36 |
+
"encoder_layerdrop": 0.0,
|
37 |
+
"encoder_layers": 12,
|
38 |
+
"eos_token_id": 2,
|
39 |
+
"gradient_checkpointing": false,
|
40 |
+
"id2label": {
|
41 |
+
"0": "LABEL_0",
|
42 |
+
"1": "LABEL_1",
|
43 |
+
"2": "LABEL_2"
|
44 |
+
},
|
45 |
+
"init_std": 0.02,
|
46 |
+
"is_encoder_decoder": true,
|
47 |
+
"label2id": {
|
48 |
+
"LABEL_0": 0,
|
49 |
+
"LABEL_1": 1,
|
50 |
+
"LABEL_2": 2
|
51 |
+
},
|
52 |
+
"max_decoder_position_embeddings": 1024,
|
53 |
+
"max_encoder_position_embeddings": 16384,
|
54 |
+
"max_length": 512,
|
55 |
+
"max_position_embeddings": 1024,
|
56 |
+
"model_type": "led",
|
57 |
+
"num_beams": 4,
|
58 |
+
"num_hidden_layers": 12,
|
59 |
+
"output_past": false,
|
60 |
+
"pad_token_id": 1,
|
61 |
+
"prefix": " ",
|
62 |
+
"torch_dtype": "float32",
|
63 |
+
"transformers_version": "4.17.0",
|
64 |
+
"use_cache": true,
|
65 |
+
"vocab_size": 50265
|
66 |
+
}
|
saved_models/ledmodel/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b234b625a7155e8186e4e6995f8861e70835cb18b900405787f48364346efef1
|
3 |
+
size 1839621489
|
saved_models/summ_model/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/scibert_scivocab_uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"output_hidden_states": true,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.17.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 31090
|
26 |
+
}
|
saved_models/summ_model/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7f5cd6403f79e20de7dd1b0858f8bd9bf161918b2373b7096aa5593611a4639
|
3 |
+
size 439753265
|
saved_models/title_model/config.json
ADDED
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Callidior/bert2bert-base-arxiv-titlegen",
|
3 |
+
"architectures": [
|
4 |
+
"EncoderDecoderModel"
|
5 |
+
],
|
6 |
+
"decoder": {
|
7 |
+
"_name_or_path": "bert-base-uncased",
|
8 |
+
"add_cross_attention": true,
|
9 |
+
"architectures": [
|
10 |
+
"BertForMaskedLM"
|
11 |
+
],
|
12 |
+
"attention_probs_dropout_prob": 0.1,
|
13 |
+
"bad_words_ids": null,
|
14 |
+
"bos_token_id": null,
|
15 |
+
"chunk_size_feed_forward": 0,
|
16 |
+
"classifier_dropout": null,
|
17 |
+
"cross_attention_hidden_size": null,
|
18 |
+
"decoder_start_token_id": null,
|
19 |
+
"diversity_penalty": 0.0,
|
20 |
+
"do_sample": false,
|
21 |
+
"early_stopping": false,
|
22 |
+
"encoder_no_repeat_ngram_size": 0,
|
23 |
+
"eos_token_id": null,
|
24 |
+
"finetuning_task": null,
|
25 |
+
"forced_bos_token_id": null,
|
26 |
+
"forced_eos_token_id": null,
|
27 |
+
"gradient_checkpointing": false,
|
28 |
+
"hidden_act": "gelu",
|
29 |
+
"hidden_dropout_prob": 0.1,
|
30 |
+
"hidden_size": 768,
|
31 |
+
"id2label": {
|
32 |
+
"0": "LABEL_0",
|
33 |
+
"1": "LABEL_1"
|
34 |
+
},
|
35 |
+
"initializer_range": 0.02,
|
36 |
+
"intermediate_size": 3072,
|
37 |
+
"is_decoder": true,
|
38 |
+
"is_encoder_decoder": false,
|
39 |
+
"label2id": {
|
40 |
+
"LABEL_0": 0,
|
41 |
+
"LABEL_1": 1
|
42 |
+
},
|
43 |
+
"layer_norm_eps": 1e-12,
|
44 |
+
"length_penalty": 1.0,
|
45 |
+
"max_length": 20,
|
46 |
+
"max_position_embeddings": 512,
|
47 |
+
"min_length": 0,
|
48 |
+
"model_type": "bert",
|
49 |
+
"no_repeat_ngram_size": 0,
|
50 |
+
"num_attention_heads": 12,
|
51 |
+
"num_beam_groups": 1,
|
52 |
+
"num_beams": 1,
|
53 |
+
"num_hidden_layers": 12,
|
54 |
+
"num_return_sequences": 1,
|
55 |
+
"output_attentions": false,
|
56 |
+
"output_hidden_states": false,
|
57 |
+
"output_scores": false,
|
58 |
+
"pad_token_id": 0,
|
59 |
+
"position_embedding_type": "absolute",
|
60 |
+
"prefix": null,
|
61 |
+
"problem_type": null,
|
62 |
+
"pruned_heads": {},
|
63 |
+
"remove_invalid_values": false,
|
64 |
+
"repetition_penalty": 1.0,
|
65 |
+
"return_dict": true,
|
66 |
+
"return_dict_in_generate": false,
|
67 |
+
"sep_token_id": null,
|
68 |
+
"task_specific_params": null,
|
69 |
+
"temperature": 1.0,
|
70 |
+
"tie_encoder_decoder": false,
|
71 |
+
"tie_word_embeddings": true,
|
72 |
+
"tokenizer_class": null,
|
73 |
+
"top_k": 50,
|
74 |
+
"top_p": 1.0,
|
75 |
+
"torch_dtype": null,
|
76 |
+
"torchscript": false,
|
77 |
+
"transformers_version": "4.17.0",
|
78 |
+
"type_vocab_size": 2,
|
79 |
+
"typical_p": 1.0,
|
80 |
+
"use_bfloat16": false,
|
81 |
+
"use_cache": true,
|
82 |
+
"vocab_size": 30522
|
83 |
+
},
|
84 |
+
"decoder_start_token_id": 101,
|
85 |
+
"do_sample": true,
|
86 |
+
"early_stopping": true,
|
87 |
+
"encoder": {
|
88 |
+
"_name_or_path": "bert-base-uncased",
|
89 |
+
"add_cross_attention": false,
|
90 |
+
"architectures": [
|
91 |
+
"BertForMaskedLM"
|
92 |
+
],
|
93 |
+
"attention_probs_dropout_prob": 0.1,
|
94 |
+
"bad_words_ids": null,
|
95 |
+
"bos_token_id": null,
|
96 |
+
"chunk_size_feed_forward": 0,
|
97 |
+
"classifier_dropout": null,
|
98 |
+
"cross_attention_hidden_size": null,
|
99 |
+
"decoder_start_token_id": null,
|
100 |
+
"diversity_penalty": 0.0,
|
101 |
+
"do_sample": false,
|
102 |
+
"early_stopping": false,
|
103 |
+
"encoder_no_repeat_ngram_size": 0,
|
104 |
+
"eos_token_id": null,
|
105 |
+
"finetuning_task": null,
|
106 |
+
"forced_bos_token_id": null,
|
107 |
+
"forced_eos_token_id": null,
|
108 |
+
"gradient_checkpointing": false,
|
109 |
+
"hidden_act": "gelu",
|
110 |
+
"hidden_dropout_prob": 0.1,
|
111 |
+
"hidden_size": 768,
|
112 |
+
"id2label": {
|
113 |
+
"0": "LABEL_0",
|
114 |
+
"1": "LABEL_1"
|
115 |
+
},
|
116 |
+
"initializer_range": 0.02,
|
117 |
+
"intermediate_size": 3072,
|
118 |
+
"is_decoder": false,
|
119 |
+
"is_encoder_decoder": false,
|
120 |
+
"label2id": {
|
121 |
+
"LABEL_0": 0,
|
122 |
+
"LABEL_1": 1
|
123 |
+
},
|
124 |
+
"layer_norm_eps": 1e-12,
|
125 |
+
"length_penalty": 1.0,
|
126 |
+
"max_length": 20,
|
127 |
+
"max_position_embeddings": 512,
|
128 |
+
"min_length": 0,
|
129 |
+
"model_type": "bert",
|
130 |
+
"no_repeat_ngram_size": 0,
|
131 |
+
"num_attention_heads": 12,
|
132 |
+
"num_beam_groups": 1,
|
133 |
+
"num_beams": 1,
|
134 |
+
"num_hidden_layers": 12,
|
135 |
+
"num_return_sequences": 1,
|
136 |
+
"output_attentions": false,
|
137 |
+
"output_hidden_states": false,
|
138 |
+
"output_scores": false,
|
139 |
+
"pad_token_id": 0,
|
140 |
+
"position_embedding_type": "absolute",
|
141 |
+
"prefix": null,
|
142 |
+
"problem_type": null,
|
143 |
+
"pruned_heads": {},
|
144 |
+
"remove_invalid_values": false,
|
145 |
+
"repetition_penalty": 1.0,
|
146 |
+
"return_dict": true,
|
147 |
+
"return_dict_in_generate": false,
|
148 |
+
"sep_token_id": null,
|
149 |
+
"task_specific_params": null,
|
150 |
+
"temperature": 1.0,
|
151 |
+
"tie_encoder_decoder": false,
|
152 |
+
"tie_word_embeddings": true,
|
153 |
+
"tokenizer_class": null,
|
154 |
+
"top_k": 50,
|
155 |
+
"top_p": 1.0,
|
156 |
+
"torch_dtype": null,
|
157 |
+
"torchscript": false,
|
158 |
+
"transformers_version": "4.17.0",
|
159 |
+
"type_vocab_size": 2,
|
160 |
+
"typical_p": 1.0,
|
161 |
+
"use_bfloat16": false,
|
162 |
+
"use_cache": true,
|
163 |
+
"vocab_size": 30522
|
164 |
+
},
|
165 |
+
"eos_token_id": 102,
|
166 |
+
"is_encoder_decoder": true,
|
167 |
+
"max_length": 32,
|
168 |
+
"min_length": 3,
|
169 |
+
"model_type": "encoder-decoder",
|
170 |
+
"no_repeat_ngram_size": 2,
|
171 |
+
"num_beams": 10,
|
172 |
+
"pad_token_id": 0,
|
173 |
+
"temperature": 1.5,
|
174 |
+
"torch_dtype": "float32",
|
175 |
+
"transformers_version": null,
|
176 |
+
"vocab_size": 30522
|
177 |
+
}
|
saved_models/title_model/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cec3d165dc46994942d506f58bd2acf607297d7ced0c1eda372c36344485d38
|
3 |
+
size 989673707
|