Upload 5 files
Browse files- config.json +35 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +20 -0
- tokenizer_config.json +87 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "uclanlp/plbart-csnet",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"PLBartModel"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 768,
|
12 |
+
"decoder_attention_heads": 12,
|
13 |
+
"decoder_ffn_dim": 3072,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 6,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 12,
|
18 |
+
"encoder_ffn_dim": 3072,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_layers": 6,
|
21 |
+
"eos_token_id": 2,
|
22 |
+
"forced_eos_token_id": 2,
|
23 |
+
"gradient_checkpointing": false,
|
24 |
+
"init_std": 0.02,
|
25 |
+
"is_encoder_decoder": true,
|
26 |
+
"max_position_embeddings": 1024,
|
27 |
+
"model_type": "plbart",
|
28 |
+
"num_hidden_layers": 6,
|
29 |
+
"pad_token_id": 1,
|
30 |
+
"scale_embedding": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.40.1",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 50009
|
35 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb5f5da9c28e2200560fb827e67eb7988592e2b4ff996b4b82334e7f6dcaf365
|
3 |
+
size 556923488
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f72f5d040a176945623a255484d24066f8c0da89a294359154e226efbe494b80
|
3 |
+
size 985833
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"__java__",
|
4 |
+
"__python__",
|
5 |
+
"__en_XX__"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"cls_token": "<s>",
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"mask_token": {
|
11 |
+
"content": "<mask>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"sep_token": "</s>",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"50001": {
|
36 |
+
"content": "__java__",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"50002": {
|
44 |
+
"content": "__python__",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"50003": {
|
52 |
+
"content": "__en_XX__",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"50004": {
|
60 |
+
"content": "<mask>",
|
61 |
+
"lstrip": true,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"additional_special_tokens": [
|
69 |
+
"__java__",
|
70 |
+
"__python__",
|
71 |
+
"__en_XX__"
|
72 |
+
],
|
73 |
+
"bos_token": "<s>",
|
74 |
+
"clean_up_tokenization_spaces": true,
|
75 |
+
"cls_token": "<s>",
|
76 |
+
"eos_token": "</s>",
|
77 |
+
"language_codes": "base",
|
78 |
+
"mask_token": "<mask>",
|
79 |
+
"model_max_length": 1000000000000000019884624838656,
|
80 |
+
"pad_token": "<pad>",
|
81 |
+
"sep_token": "</s>",
|
82 |
+
"sp_model_kwargs": {},
|
83 |
+
"src_lang": null,
|
84 |
+
"tgt_lang": null,
|
85 |
+
"tokenizer_class": "PLBartTokenizer",
|
86 |
+
"unk_token": "<unk>"
|
87 |
+
}
|