Upload 6 files
Browse files- .gitattributes +5 -32
- README.md +28 -3
- config.json +36 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -1,35 +1,8 @@
|
|
1 |
-
*.
|
2 |
-
*.
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
-
*.
|
31 |
-
*.
|
32 |
-
*.
|
33 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
4 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
README.md
CHANGED
@@ -1,3 +1,28 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
license: apache-2.0
|
4 |
+
---
|
5 |
+
|
6 |
+
# longformer-base-8192
|
7 |
+
[Longformer](https://arxiv.org/abs/2004.05150) is a transformer model for long documents.
|
8 |
+
|
9 |
+
`longformer-base-8192` is a BERT-like model started from the RoBERTa checkpoint and pretrained for MLM on long documents. It supports sequences of length up to 8,192.
|
10 |
+
|
11 |
+
Longformer uses a combination of a sliding window (local) attention and global attention. Global attention is user-configured based on the task to allow the model to learn task-specific representations.
|
12 |
+
Please refer to the examples in `modeling_longformer.py` and the paper for more details on how to set global attention.
|
13 |
+
|
14 |
+
|
15 |
+
### Citing
|
16 |
+
|
17 |
+
If you use `Longformer` in your research, please cite [Longformer: The Long-Document Transformer](https://arxiv.org/abs/2004.05150).
|
18 |
+
```
|
19 |
+
@article{Beltagy2020Longformer,
|
20 |
+
title={Longformer: The Long-Document Transformer},
|
21 |
+
author={Iz Beltagy and Matthew E. Peters and Arman Cohan},
|
22 |
+
journal={arXiv:2004.05150},
|
23 |
+
year={2020},
|
24 |
+
}
|
25 |
+
```
|
26 |
+
|
27 |
+
`Longformer` is an open-source project developed by [the Allen Institute for Artificial Intelligence (AI2)](http://www.allenai.org).
|
28 |
+
AI2 is a non-profit institute with the mission to contribute to humanity through high-impact AI research and engineering.
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_mode": "longformer",
|
3 |
+
"attention_probs_dropout_prob": 0.1,
|
4 |
+
"attention_window": [
|
5 |
+
512,
|
6 |
+
512,
|
7 |
+
512,
|
8 |
+
512,
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512
|
17 |
+
],
|
18 |
+
"bos_token_id": 0,
|
19 |
+
"eos_token_id": 2,
|
20 |
+
"gradient_checkpointing": false,
|
21 |
+
"hidden_act": "gelu",
|
22 |
+
"hidden_dropout_prob": 0.1,
|
23 |
+
"hidden_size": 768,
|
24 |
+
"ignore_attention_mask": false,
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"layer_norm_eps": 1e-05,
|
28 |
+
"max_position_embeddings": 8196,
|
29 |
+
"model_type": "longformer",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"pad_token_id": 1,
|
33 |
+
"sep_token_id": 2,
|
34 |
+
"type_vocab_size": 1,
|
35 |
+
"vocab_size": 50265
|
36 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e11897b4a675e16f1b9debb4dfefba472fe4121eebb5ccae5b2c5c0f27409f71
|
3 |
+
size 607329734
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|