Upload 7 files
Browse files- config.json +34 -0
- gitattributes.txt +27 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BigBirdForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"attention_type": "block_sparse",
|
7 |
+
"block_size": 64,
|
8 |
+
"bos_token_id": 5,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 6,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu_new",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"layer_norm_eps": 1e-12,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "big_bird",
|
20 |
+
"num_attention_heads": 12,
|
21 |
+
"num_hidden_layers": 12,
|
22 |
+
"num_random_blocks": 3,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"position_embedding_type": "absolute",
|
25 |
+
"rescale_embeddings": false,
|
26 |
+
"sep_token_id": 3,
|
27 |
+
"tokenizer_class": "BertTokenizer",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.11.3",
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"use_bias": true,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 32500
|
34 |
+
}
|
gitattributes.txt
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.bz2 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 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
20 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd199d542a025e877a76dc95f26e07a6d4e6d45b339e37a4268672b0d1219ffa
|
3 |
+
size 455178351
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"unk_token": "[UNK]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"cls_token": "[CLS]",
|
8 |
+
"mask_token": "[MASK]"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": false,
|
3 |
+
"unk_token": "[UNK]",
|
4 |
+
"sep_token": "[SEP]",
|
5 |
+
"pad_token": "[PAD]",
|
6 |
+
"cls_token": "[CLS]",
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"tokenize_chinese_chars": true,
|
9 |
+
"strip_accents": null,
|
10 |
+
"do_basic_tokenize": true,
|
11 |
+
"never_split": null,
|
12 |
+
"bos_token": "<s>",
|
13 |
+
"eos_token": "</s>",
|
14 |
+
"model_max_length": 4096,
|
15 |
+
"tokenizer_class": "BertTokenizer"
|
16 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|