Győző Yang Zijian
commited on
Commit
•
3ef4f47
1
Parent(s):
5c34e2a
add files
Browse files- config.json +47 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/data/users/fragata/mt/models/bart/enhu-base-170000",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"BartForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classif_dropout": 0.1,
|
11 |
+
"classifier_dropout": 0.1,
|
12 |
+
"d_model": 768,
|
13 |
+
"decoder_attention_heads": 12,
|
14 |
+
"decoder_ffn_dim": 3072,
|
15 |
+
"decoder_layerdrop": 0.0,
|
16 |
+
"decoder_layers": 6,
|
17 |
+
"decoder_start_token_id": 2,
|
18 |
+
"dropout": 0.1,
|
19 |
+
"encoder_attention_heads": 12,
|
20 |
+
"encoder_ffn_dim": 3072,
|
21 |
+
"encoder_layerdrop": 0.0,
|
22 |
+
"encoder_layers": 6,
|
23 |
+
"eos_token_id": 2,
|
24 |
+
"forced_eos_token_id": 2,
|
25 |
+
"gradient_checkpointing": false,
|
26 |
+
"id2label": {
|
27 |
+
"0": "LABEL_0",
|
28 |
+
"1": "LABEL_1",
|
29 |
+
"2": "LABEL_2"
|
30 |
+
},
|
31 |
+
"init_std": 0.02,
|
32 |
+
"is_encoder_decoder": true,
|
33 |
+
"label2id": {
|
34 |
+
"LABEL_0": 0,
|
35 |
+
"LABEL_1": 1,
|
36 |
+
"LABEL_2": 2
|
37 |
+
},
|
38 |
+
"max_position_embeddings": 1024,
|
39 |
+
"model_type": "bart",
|
40 |
+
"num_hidden_layers": 6,
|
41 |
+
"pad_token_id": 1,
|
42 |
+
"scale_embedding": false,
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.9.0.dev0",
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 40000
|
47 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc2cbdf8f9ad26fb539242aa7939cad42599049d244dee8b90110b4e15ed8e05
|
3 |
+
size 526410579
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "/data/users/fragata/mt/models/bart/enhu-base-170000", "tokenizer_class": "BartTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|