l3cube-pune
commited on
Commit
•
d1f86bb
1
Parent(s):
7393682
Update model files
Browse files- added_tokens.json +16 -0
- config.json +36 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +31 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +25 -0
added_tokens.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 64001,
|
3 |
+
"<2as>": 64002,
|
4 |
+
"<2bn>": 64003,
|
5 |
+
"<2en>": 64004,
|
6 |
+
"<2gu>": 64005,
|
7 |
+
"<2hi>": 64006,
|
8 |
+
"<2kn>": 64007,
|
9 |
+
"<2ml>": 64008,
|
10 |
+
"<2mr>": 64009,
|
11 |
+
"<2or>": 64010,
|
12 |
+
"<2pa>": 64011,
|
13 |
+
"<2ta>": 64012,
|
14 |
+
"<2te>": 64013,
|
15 |
+
"<s>": 64000
|
16 |
+
}
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "l3cube-pune/hindi-bart-summary",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"MBartForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 64000,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 1024,
|
12 |
+
"decoder_attention_heads": 16,
|
13 |
+
"decoder_ffn_dim": 4096,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 6,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 16,
|
18 |
+
"encoder_ffn_dim": 4096,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_layers": 6,
|
21 |
+
"eos_token_id": 64001,
|
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": "mbart",
|
28 |
+
"num_hidden_layers": 6,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"scale_embedding": false,
|
31 |
+
"tokenizer_class": "AlbertTokenizer",
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.25.1",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 64014
|
36 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fbd3c2d9ad801d050f56d97901bd61639fa6265dc966ce01de391e0eee1eceb
|
3 |
+
size 976410669
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>",
|
4 |
+
"</s>",
|
5 |
+
"<2as>",
|
6 |
+
"<2bn>",
|
7 |
+
"<2en>",
|
8 |
+
"<2gu>",
|
9 |
+
"<2hi>",
|
10 |
+
"<2kn>",
|
11 |
+
"<2ml>",
|
12 |
+
"<2mr>",
|
13 |
+
"<2or>",
|
14 |
+
"<2pa>",
|
15 |
+
"<2ta>",
|
16 |
+
"<2te>"
|
17 |
+
],
|
18 |
+
"bos_token": "[CLS]",
|
19 |
+
"cls_token": "[CLS]",
|
20 |
+
"eos_token": "[SEP]",
|
21 |
+
"mask_token": {
|
22 |
+
"content": "[MASK]",
|
23 |
+
"lstrip": true,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"pad_token": "<pad>",
|
29 |
+
"sep_token": "[SEP]",
|
30 |
+
"unk_token": "<unk>"
|
31 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d924c4e4e0d7a073e8289c20e29cd27657629064f2571fb18ab82008cf79a72
|
3 |
+
size 1898704
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"keep_accents": true,
|
7 |
+
"mask_token": {
|
8 |
+
"__type": "AddedToken",
|
9 |
+
"content": "[MASK]",
|
10 |
+
"lstrip": true,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"model_max_length": 1000000000000000019884624838656,
|
16 |
+
"name_or_path": "l3cube-pune/hindi-bart-summary",
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"remove_space": true,
|
19 |
+
"sep_token": "[SEP]",
|
20 |
+
"sp_model_kwargs": {},
|
21 |
+
"special_tokens_map_file": "albert-indicunified64k/special_tokens_map.json",
|
22 |
+
"tokenizer_class": "AlbertTokenizer",
|
23 |
+
"unk_token": "<unk>",
|
24 |
+
"use_fast": false
|
25 |
+
}
|