new
Browse files- added_tokens.json +11 -0
- config.json +73 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- special_tokens_map.json +62 -0
- tokenizer_config.json +64 -0
- training_args_action|context_gen.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|ACT|>": 50272,
|
3 |
+
"<|CSQ|>": 50273,
|
4 |
+
"<|ITN|>": 50267,
|
5 |
+
"<|I_ACT|>": 50269,
|
6 |
+
"<|I_CSQ|>": 50271,
|
7 |
+
"<|M_ACT|>": 50268,
|
8 |
+
"<|M_CSQ|>": 50270,
|
9 |
+
"<|NRM|>": 50265,
|
10 |
+
"<|SIT|>": 50266
|
11 |
+
}
|
config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 4096,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 12,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"finetuning_task": "action|context_gen",
|
28 |
+
"forced_bos_token_id": 0,
|
29 |
+
"forced_eos_token_id": 2,
|
30 |
+
"gradient_checkpointing": false,
|
31 |
+
"id2label": {
|
32 |
+
"0": "LABEL_0",
|
33 |
+
"1": "LABEL_1"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder_decoder": true,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1
|
40 |
+
},
|
41 |
+
"max_position_embeddings": 1024,
|
42 |
+
"model_type": "bart",
|
43 |
+
"no_repeat_ngram_size": 3,
|
44 |
+
"normalize_before": false,
|
45 |
+
"num_beams": 4,
|
46 |
+
"num_hidden_layers": 12,
|
47 |
+
"pad_token_id": 1,
|
48 |
+
"scale_embedding": false,
|
49 |
+
"task_specific_params": {
|
50 |
+
"summarization": {
|
51 |
+
"length_penalty": 1.0,
|
52 |
+
"max_length": 128,
|
53 |
+
"min_length": 12,
|
54 |
+
"num_beams": 4
|
55 |
+
},
|
56 |
+
"summarization_cnn": {
|
57 |
+
"length_penalty": 2.0,
|
58 |
+
"max_length": 142,
|
59 |
+
"min_length": 56,
|
60 |
+
"num_beams": 4
|
61 |
+
},
|
62 |
+
"summarization_xsum": {
|
63 |
+
"length_penalty": 1.0,
|
64 |
+
"max_length": 62,
|
65 |
+
"min_length": 11,
|
66 |
+
"num_beams": 6
|
67 |
+
}
|
68 |
+
},
|
69 |
+
"torch_dtype": "float32",
|
70 |
+
"transformers_version": "4.28.1",
|
71 |
+
"use_cache": true,
|
72 |
+
"vocab_size": 50274
|
73 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"early_stopping": true,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"forced_bos_token_id": 0,
|
8 |
+
"forced_eos_token_id": 2,
|
9 |
+
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 4,
|
11 |
+
"pad_token_id": 1,
|
12 |
+
"transformers_version": "4.28.1"
|
13 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|NRM|>",
|
4 |
+
"<|SIT|>",
|
5 |
+
"<|ITN|>",
|
6 |
+
"<|M_ACT|>",
|
7 |
+
"<|I_ACT|>",
|
8 |
+
"<|M_CSQ|>",
|
9 |
+
"<|I_CSQ|>",
|
10 |
+
"<|ACT|>",
|
11 |
+
"<|CSQ|>"
|
12 |
+
],
|
13 |
+
"bos_token": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"cls_token": {
|
21 |
+
"content": "<s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"eos_token": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
},
|
34 |
+
"mask_token": {
|
35 |
+
"content": "<mask>",
|
36 |
+
"lstrip": true,
|
37 |
+
"normalized": true,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
},
|
41 |
+
"pad_token": {
|
42 |
+
"content": "<pad>",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": true,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"sep_token": {
|
49 |
+
"content": "</s>",
|
50 |
+
"lstrip": false,
|
51 |
+
"normalized": true,
|
52 |
+
"rstrip": false,
|
53 |
+
"single_word": false
|
54 |
+
},
|
55 |
+
"unk_token": {
|
56 |
+
"content": "<unk>",
|
57 |
+
"lstrip": false,
|
58 |
+
"normalized": true,
|
59 |
+
"rstrip": false,
|
60 |
+
"single_word": false
|
61 |
+
}
|
62 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"do_lower_case": true,
|
21 |
+
"eos_token": {
|
22 |
+
"__type": "AddedToken",
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"errors": "replace",
|
30 |
+
"mask_token": {
|
31 |
+
"__type": "AddedToken",
|
32 |
+
"content": "<mask>",
|
33 |
+
"lstrip": true,
|
34 |
+
"normalized": true,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
"model_max_length": 1024,
|
39 |
+
"pad_token": {
|
40 |
+
"__type": "AddedToken",
|
41 |
+
"content": "<pad>",
|
42 |
+
"lstrip": false,
|
43 |
+
"normalized": true,
|
44 |
+
"rstrip": false,
|
45 |
+
"single_word": false
|
46 |
+
},
|
47 |
+
"sep_token": {
|
48 |
+
"__type": "AddedToken",
|
49 |
+
"content": "</s>",
|
50 |
+
"lstrip": false,
|
51 |
+
"normalized": true,
|
52 |
+
"rstrip": false,
|
53 |
+
"single_word": false
|
54 |
+
},
|
55 |
+
"tokenizer_class": "BartTokenizer",
|
56 |
+
"unk_token": {
|
57 |
+
"__type": "AddedToken",
|
58 |
+
"content": "<unk>",
|
59 |
+
"lstrip": false,
|
60 |
+
"normalized": true,
|
61 |
+
"rstrip": false,
|
62 |
+
"single_word": false
|
63 |
+
}
|
64 |
+
}
|
training_args_action|context_gen.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f313488e92c0860886f751d8a0e261fb8c4ae7e2326944ccd3e63520169f0324
|
3 |
+
size 2017
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|