ai-forever
commited on
Commit
•
1ccd312
1
Parent(s):
4a0e15e
Update tokenization config
Browse files- config.json +12 -7
- special_tokens_map.json +31 -0
- tokenizer_config.json +58 -0
config.json
CHANGED
@@ -1,26 +1,31 @@
|
|
1 |
{
|
2 |
"attn_pdrop": 0.1,
|
|
|
3 |
"embd_pdrop": 0.1,
|
4 |
-
"
|
|
|
|
|
|
|
5 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
6 |
"layer_norm_epsilon": 1e-05,
|
|
|
7 |
"n_ctx": 1024,
|
8 |
"n_embd": 1280,
|
9 |
"n_head": 20,
|
|
|
10 |
"n_layer": 36,
|
11 |
"n_positions": 1024,
|
12 |
-
"num_labels": 1,
|
13 |
-
"output_attentions": false,
|
14 |
-
"output_hidden_states": false,
|
15 |
"output_past": true,
|
16 |
-
"
|
17 |
"resid_pdrop": 0.1,
|
18 |
"summary_activation": null,
|
19 |
"summary_first_dropout": 0.1,
|
20 |
"summary_proj_to_labels": true,
|
21 |
"summary_type": "cls_index",
|
22 |
"summary_use_proj": true,
|
23 |
-
"
|
24 |
-
"use_bfloat16": false,
|
25 |
"vocab_size": 50257
|
26 |
}
|
|
|
1 |
{
|
2 |
"attn_pdrop": 0.1,
|
3 |
+
"bos_token_id": 1,
|
4 |
"embd_pdrop": 0.1,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"id2label": {
|
7 |
+
"0": "LABEL_0"
|
8 |
+
},
|
9 |
"initializer_range": 0.02,
|
10 |
+
"label2id": {
|
11 |
+
"LABEL_0": 0
|
12 |
+
},
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
"n_embd": 1280,
|
17 |
"n_head": 20,
|
18 |
+
"n_inner": null,
|
19 |
"n_layer": 36,
|
20 |
"n_positions": 1024,
|
|
|
|
|
|
|
21 |
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
"resid_pdrop": 0.1,
|
24 |
"summary_activation": null,
|
25 |
"summary_first_dropout": 0.1,
|
26 |
"summary_proj_to_labels": true,
|
27 |
"summary_type": "cls_index",
|
28 |
"summary_use_proj": true,
|
29 |
+
"use_cache": true,
|
|
|
30 |
"vocab_size": 50257
|
31 |
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"mask_token": "<mask>",
|
17 |
+
"pad_token": {
|
18 |
+
"content": "<pad>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"unk_token": {
|
25 |
+
"content": "<unk>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"4": {
|
38 |
+
"content": "<mask>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"bos_token": "<s>",
|
47 |
+
"clean_up_tokenization_spaces": true,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 1024,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"padding_side": "left",
|
54 |
+
"tokenizer_class": "GPT2Tokenizer",
|
55 |
+
"truncation_side": "left",
|
56 |
+
"trust_remote_code": false,
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|