added model files
Browse files- .gitattributes +1 -0
- added_tokens.json +1 -0
- config.json +33 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* 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
|
|
|
|
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
|
28 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 64000, "</s>": 64001, "<2as>": 64002, "<2bn>": 64003, "<2en>": 64004, "<2gu>": 64005, "<2hi>": 64006, "<2kn>": 64007, "<2ml>": 64008, "<2mr>": 64009, "<2or>": 64010, "<2pa>": 64011, "<2ta>": 64012, "<2te>": 64013}
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.1,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"MBartForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bos_token_id": 64000,
|
9 |
+
"d_model": 1024,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"decoder_attention_heads": 16,
|
12 |
+
"decoder_ffn_dim": 4096,
|
13 |
+
"decoder_layerdrop": 0.0,
|
14 |
+
"decoder_layers": 6,
|
15 |
+
"dropout": 0.1,
|
16 |
+
"encoder_attention_heads": 16,
|
17 |
+
"encoder_ffn_dim": 4096,
|
18 |
+
"encoder_layerdrop": 0.0,
|
19 |
+
"encoder_layers": 6,
|
20 |
+
"eos_token_id": 64001,
|
21 |
+
"gradient_checkpointing": false,
|
22 |
+
"init_std": 0.02,
|
23 |
+
"is_encoder_decoder": true,
|
24 |
+
"max_position_embeddings": 1024,
|
25 |
+
"model_type": "mbart",
|
26 |
+
"num_hidden_layers": 6,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"scale_embedding": false,
|
29 |
+
"transformers_version": "4.3.2",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 64014,
|
32 |
+
"tokenizer_class": "AlbertTokenizer"
|
33 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b85dde0bdfa2e7c0ca078dd4ecc0c7c27492ba61bb6d2048a1b299adc084c1d8
|
3 |
+
size 976422449
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<s>", "</s>", "<2as>", "<2bn>", "<2en>", "<2gu>", "<2hi>", "<2kn>", "<2ml>", "<2mr>", "<2or>", "<2pa>", "<2ta>", "<2te>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d924c4e4e0d7a073e8289c20e29cd27657629064f2571fb18ab82008cf79a72
|
3 |
+
size 1898704
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "use_fast": false, "special_tokens_map_file": "albert-indicunified64k/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "albert-indicunified64k"}
|