draj
commited on
Commit
•
0aef232
1
Parent(s):
2af2919
Morisien-English model.
Browse files- added_tokens.json +1 -0
- config.json +30 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 16000, "</s>": 16001, "<2cr>": 16002, "<2fr>": 16003, "<2en>": 16004}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.2,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"attention_dropout": 0.2,
|
5 |
+
"bos_token_id": 16000,
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_model": 1024,
|
8 |
+
"decoder_attention_heads": 16,
|
9 |
+
"decoder_ffn_dim": 4096,
|
10 |
+
"decoder_layerdrop": 0.0,
|
11 |
+
"decoder_layers": 6,
|
12 |
+
"dropout": 0.2,
|
13 |
+
"encoder_attention_heads": 16,
|
14 |
+
"encoder_ffn_dim": 4096,
|
15 |
+
"encoder_layerdrop": 0.0,
|
16 |
+
"encoder_layers": 6,
|
17 |
+
"eos_token_id": 16001,
|
18 |
+
"gradient_checkpointing": false,
|
19 |
+
"init_std": 0.02,
|
20 |
+
"is_encoder_decoder": true,
|
21 |
+
"max_position_embeddings": 1024,
|
22 |
+
"model_type": "mbart",
|
23 |
+
"num_hidden_layers": 6,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"scale_embedding": false,
|
26 |
+
"tokenizer_class": "AlbertTokenizer",
|
27 |
+
"transformers_version": "4.3.2",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 16005
|
30 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:420737f369a4bd37e1befaf27c09c8c50d6845d4b02cd191a13cf9d8c4b81e51
|
3 |
+
size 779590093
|
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>", "<2cr>", "<2fr>", "<2en>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a608c2eb1ba9b47dd083f0fb8b40c9c7d659c8e4a5bb040a34c6a27c4ce63a0
|
3 |
+
size 512174
|
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": "/share03/draj/data/parallel_corpora/creole/albert-enfrcr16k/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/share03/draj/data/parallel_corpora/creole/albert-enfrcr16k"}
|