farshadafx
commited on
Commit
•
749c8bc
1
Parent(s):
cbc4dcd
End of training
Browse files- README.md +56 -1
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +55 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +413 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +1 -0
README.md
CHANGED
@@ -1,3 +1,58 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
base_model: gpt2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: leda-v1
|
8 |
+
results: []
|
9 |
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# leda-v1
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0005
|
36 |
+
- train_batch_size: 16
|
37 |
+
- eval_batch_size: 16
|
38 |
+
- seed: 42
|
39 |
+
- gradient_accumulation_steps: 8
|
40 |
+
- total_train_batch_size: 128
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: cosine
|
43 |
+
- lr_scheduler_warmup_steps: 1000
|
44 |
+
- num_epochs: 1
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| No log | 1.0 | 939 | 1.1382 |
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- Transformers 4.33.0
|
56 |
+
- Pytorch 2.0.0
|
57 |
+
- Datasets 2.1.0
|
58 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
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 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.33.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 311
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.33.0"
|
6 |
+
}
|
merges.txt
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#version: 0.2
|
2 |
+
b o
|
3 |
+
d o
|
4 |
+
d y
|
5 |
+
u p
|
6 |
+
w n
|
7 |
+
bo dy
|
8 |
+
do wn
|
9 |
+
Ġ b
|
10 |
+
l l
|
11 |
+
u ll
|
12 |
+
ull body
|
13 |
+
Ġb ullbody
|
14 |
+
a r
|
15 |
+
e ar
|
16 |
+
ear body
|
17 |
+
Ġb earbody
|
18 |
+
1 0
|
19 |
+
i n
|
20 |
+
in f
|
21 |
+
1 5
|
22 |
+
2 5
|
23 |
+
5 0
|
24 |
+
2 0
|
25 |
+
4 0
|
26 |
+
3 0
|
27 |
+
3 5
|
28 |
+
up inf
|
29 |
+
upinf down
|
30 |
+
down inf
|
31 |
+
inf up
|
32 |
+
Ġbullbody infup
|
33 |
+
7 0
|
34 |
+
6 5
|
35 |
+
upinfdown inf
|
36 |
+
8 0
|
37 |
+
9 0
|
38 |
+
9 5
|
39 |
+
Ġbullbody inf
|
40 |
+
Ġbearbody infup
|
41 |
+
b ullbody
|
42 |
+
Ġbullbodyinf upinfdown
|
43 |
+
b earbody
|
44 |
+
Ġbullbodyinf upinfdowninf
|
45 |
+
Ġbearbody inf
|
46 |
+
Ġbearbodyinf upinfdown
|
47 |
+
bullbody infup
|
48 |
+
Ġbearbodyinf upinfdowninf
|
49 |
+
bullbody inf
|
50 |
+
bearbody infup
|
51 |
+
bullbodyinf upinfdown
|
52 |
+
bullbodyinf upinfdowninf
|
53 |
+
bearbody inf
|
54 |
+
bearbodyinf upinfdown
|
55 |
+
bearbodyinf upinfdowninf
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6315e7e408e67d02a0df393184e2979a539e90b9c9c96caabb834e77d0d94a02
|
3 |
+
size 344373085
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,413 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<|endoftext|>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
}
|
15 |
+
],
|
16 |
+
"normalizer": null,
|
17 |
+
"pre_tokenizer": {
|
18 |
+
"type": "ByteLevel",
|
19 |
+
"add_prefix_space": false,
|
20 |
+
"trim_offsets": true,
|
21 |
+
"use_regex": true
|
22 |
+
},
|
23 |
+
"post_processor": {
|
24 |
+
"type": "ByteLevel",
|
25 |
+
"add_prefix_space": true,
|
26 |
+
"trim_offsets": false,
|
27 |
+
"use_regex": true
|
28 |
+
},
|
29 |
+
"decoder": {
|
30 |
+
"type": "ByteLevel",
|
31 |
+
"add_prefix_space": true,
|
32 |
+
"trim_offsets": true,
|
33 |
+
"use_regex": true
|
34 |
+
},
|
35 |
+
"model": {
|
36 |
+
"type": "BPE",
|
37 |
+
"dropout": null,
|
38 |
+
"unk_token": null,
|
39 |
+
"continuing_subword_prefix": "",
|
40 |
+
"end_of_word_suffix": "",
|
41 |
+
"fuse_unk": false,
|
42 |
+
"byte_fallback": false,
|
43 |
+
"vocab": {
|
44 |
+
"<|endoftext|>": 0,
|
45 |
+
"!": 1,
|
46 |
+
"\"": 2,
|
47 |
+
"#": 3,
|
48 |
+
"$": 4,
|
49 |
+
"%": 5,
|
50 |
+
"&": 6,
|
51 |
+
"'": 7,
|
52 |
+
"(": 8,
|
53 |
+
")": 9,
|
54 |
+
"*": 10,
|
55 |
+
"+": 11,
|
56 |
+
",": 12,
|
57 |
+
"-": 13,
|
58 |
+
".": 14,
|
59 |
+
"/": 15,
|
60 |
+
"0": 16,
|
61 |
+
"1": 17,
|
62 |
+
"2": 18,
|
63 |
+
"3": 19,
|
64 |
+
"4": 20,
|
65 |
+
"5": 21,
|
66 |
+
"6": 22,
|
67 |
+
"7": 23,
|
68 |
+
"8": 24,
|
69 |
+
"9": 25,
|
70 |
+
":": 26,
|
71 |
+
";": 27,
|
72 |
+
"<": 28,
|
73 |
+
"=": 29,
|
74 |
+
">": 30,
|
75 |
+
"?": 31,
|
76 |
+
"@": 32,
|
77 |
+
"A": 33,
|
78 |
+
"B": 34,
|
79 |
+
"C": 35,
|
80 |
+
"D": 36,
|
81 |
+
"E": 37,
|
82 |
+
"F": 38,
|
83 |
+
"G": 39,
|
84 |
+
"H": 40,
|
85 |
+
"I": 41,
|
86 |
+
"J": 42,
|
87 |
+
"K": 43,
|
88 |
+
"L": 44,
|
89 |
+
"M": 45,
|
90 |
+
"N": 46,
|
91 |
+
"O": 47,
|
92 |
+
"P": 48,
|
93 |
+
"Q": 49,
|
94 |
+
"R": 50,
|
95 |
+
"S": 51,
|
96 |
+
"T": 52,
|
97 |
+
"U": 53,
|
98 |
+
"V": 54,
|
99 |
+
"W": 55,
|
100 |
+
"X": 56,
|
101 |
+
"Y": 57,
|
102 |
+
"Z": 58,
|
103 |
+
"[": 59,
|
104 |
+
"\\": 60,
|
105 |
+
"]": 61,
|
106 |
+
"^": 62,
|
107 |
+
"_": 63,
|
108 |
+
"`": 64,
|
109 |
+
"a": 65,
|
110 |
+
"b": 66,
|
111 |
+
"c": 67,
|
112 |
+
"d": 68,
|
113 |
+
"e": 69,
|
114 |
+
"f": 70,
|
115 |
+
"g": 71,
|
116 |
+
"h": 72,
|
117 |
+
"i": 73,
|
118 |
+
"j": 74,
|
119 |
+
"k": 75,
|
120 |
+
"l": 76,
|
121 |
+
"m": 77,
|
122 |
+
"n": 78,
|
123 |
+
"o": 79,
|
124 |
+
"p": 80,
|
125 |
+
"q": 81,
|
126 |
+
"r": 82,
|
127 |
+
"s": 83,
|
128 |
+
"t": 84,
|
129 |
+
"u": 85,
|
130 |
+
"v": 86,
|
131 |
+
"w": 87,
|
132 |
+
"x": 88,
|
133 |
+
"y": 89,
|
134 |
+
"z": 90,
|
135 |
+
"{": 91,
|
136 |
+
"|": 92,
|
137 |
+
"}": 93,
|
138 |
+
"~": 94,
|
139 |
+
"¡": 95,
|
140 |
+
"¢": 96,
|
141 |
+
"£": 97,
|
142 |
+
"¤": 98,
|
143 |
+
"¥": 99,
|
144 |
+
"¦": 100,
|
145 |
+
"§": 101,
|
146 |
+
"¨": 102,
|
147 |
+
"©": 103,
|
148 |
+
"ª": 104,
|
149 |
+
"«": 105,
|
150 |
+
"¬": 106,
|
151 |
+
"®": 107,
|
152 |
+
"¯": 108,
|
153 |
+
"°": 109,
|
154 |
+
"±": 110,
|
155 |
+
"²": 111,
|
156 |
+
"³": 112,
|
157 |
+
"´": 113,
|
158 |
+
"µ": 114,
|
159 |
+
"¶": 115,
|
160 |
+
"·": 116,
|
161 |
+
"¸": 117,
|
162 |
+
"¹": 118,
|
163 |
+
"º": 119,
|
164 |
+
"»": 120,
|
165 |
+
"¼": 121,
|
166 |
+
"½": 122,
|
167 |
+
"¾": 123,
|
168 |
+
"¿": 124,
|
169 |
+
"À": 125,
|
170 |
+
"Á": 126,
|
171 |
+
"Â": 127,
|
172 |
+
"Ã": 128,
|
173 |
+
"Ä": 129,
|
174 |
+
"Å": 130,
|
175 |
+
"Æ": 131,
|
176 |
+
"Ç": 132,
|
177 |
+
"È": 133,
|
178 |
+
"É": 134,
|
179 |
+
"Ê": 135,
|
180 |
+
"Ë": 136,
|
181 |
+
"Ì": 137,
|
182 |
+
"Í": 138,
|
183 |
+
"Î": 139,
|
184 |
+
"Ï": 140,
|
185 |
+
"Ð": 141,
|
186 |
+
"Ñ": 142,
|
187 |
+
"Ò": 143,
|
188 |
+
"Ó": 144,
|
189 |
+
"Ô": 145,
|
190 |
+
"Õ": 146,
|
191 |
+
"Ö": 147,
|
192 |
+
"×": 148,
|
193 |
+
"Ø": 149,
|
194 |
+
"Ù": 150,
|
195 |
+
"Ú": 151,
|
196 |
+
"Û": 152,
|
197 |
+
"Ü": 153,
|
198 |
+
"Ý": 154,
|
199 |
+
"Þ": 155,
|
200 |
+
"ß": 156,
|
201 |
+
"à": 157,
|
202 |
+
"á": 158,
|
203 |
+
"â": 159,
|
204 |
+
"ã": 160,
|
205 |
+
"ä": 161,
|
206 |
+
"å": 162,
|
207 |
+
"æ": 163,
|
208 |
+
"ç": 164,
|
209 |
+
"è": 165,
|
210 |
+
"é": 166,
|
211 |
+
"ê": 167,
|
212 |
+
"ë": 168,
|
213 |
+
"ì": 169,
|
214 |
+
"í": 170,
|
215 |
+
"î": 171,
|
216 |
+
"ï": 172,
|
217 |
+
"ð": 173,
|
218 |
+
"ñ": 174,
|
219 |
+
"ò": 175,
|
220 |
+
"ó": 176,
|
221 |
+
"ô": 177,
|
222 |
+
"õ": 178,
|
223 |
+
"ö": 179,
|
224 |
+
"÷": 180,
|
225 |
+
"ø": 181,
|
226 |
+
"ù": 182,
|
227 |
+
"ú": 183,
|
228 |
+
"û": 184,
|
229 |
+
"ü": 185,
|
230 |
+
"ý": 186,
|
231 |
+
"þ": 187,
|
232 |
+
"ÿ": 188,
|
233 |
+
"Ā": 189,
|
234 |
+
"ā": 190,
|
235 |
+
"Ă": 191,
|
236 |
+
"ă": 192,
|
237 |
+
"Ą": 193,
|
238 |
+
"ą": 194,
|
239 |
+
"Ć": 195,
|
240 |
+
"ć": 196,
|
241 |
+
"Ĉ": 197,
|
242 |
+
"ĉ": 198,
|
243 |
+
"Ċ": 199,
|
244 |
+
"ċ": 200,
|
245 |
+
"Č": 201,
|
246 |
+
"č": 202,
|
247 |
+
"Ď": 203,
|
248 |
+
"ď": 204,
|
249 |
+
"Đ": 205,
|
250 |
+
"đ": 206,
|
251 |
+
"Ē": 207,
|
252 |
+
"ē": 208,
|
253 |
+
"Ĕ": 209,
|
254 |
+
"ĕ": 210,
|
255 |
+
"Ė": 211,
|
256 |
+
"ė": 212,
|
257 |
+
"Ę": 213,
|
258 |
+
"ę": 214,
|
259 |
+
"Ě": 215,
|
260 |
+
"ě": 216,
|
261 |
+
"Ĝ": 217,
|
262 |
+
"ĝ": 218,
|
263 |
+
"Ğ": 219,
|
264 |
+
"ğ": 220,
|
265 |
+
"Ġ": 221,
|
266 |
+
"ġ": 222,
|
267 |
+
"Ģ": 223,
|
268 |
+
"ģ": 224,
|
269 |
+
"Ĥ": 225,
|
270 |
+
"ĥ": 226,
|
271 |
+
"Ħ": 227,
|
272 |
+
"ħ": 228,
|
273 |
+
"Ĩ": 229,
|
274 |
+
"ĩ": 230,
|
275 |
+
"Ī": 231,
|
276 |
+
"ī": 232,
|
277 |
+
"Ĭ": 233,
|
278 |
+
"ĭ": 234,
|
279 |
+
"Į": 235,
|
280 |
+
"į": 236,
|
281 |
+
"İ": 237,
|
282 |
+
"ı": 238,
|
283 |
+
"IJ": 239,
|
284 |
+
"ij": 240,
|
285 |
+
"Ĵ": 241,
|
286 |
+
"ĵ": 242,
|
287 |
+
"Ķ": 243,
|
288 |
+
"ķ": 244,
|
289 |
+
"ĸ": 245,
|
290 |
+
"Ĺ": 246,
|
291 |
+
"ĺ": 247,
|
292 |
+
"Ļ": 248,
|
293 |
+
"ļ": 249,
|
294 |
+
"Ľ": 250,
|
295 |
+
"ľ": 251,
|
296 |
+
"Ŀ": 252,
|
297 |
+
"ŀ": 253,
|
298 |
+
"Ł": 254,
|
299 |
+
"ł": 255,
|
300 |
+
"Ń": 256,
|
301 |
+
"bo": 257,
|
302 |
+
"do": 258,
|
303 |
+
"dy": 259,
|
304 |
+
"up": 260,
|
305 |
+
"wn": 261,
|
306 |
+
"body": 262,
|
307 |
+
"down": 263,
|
308 |
+
"Ġb": 264,
|
309 |
+
"ll": 265,
|
310 |
+
"ull": 266,
|
311 |
+
"ullbody": 267,
|
312 |
+
"Ġbullbody": 268,
|
313 |
+
"ar": 269,
|
314 |
+
"ear": 270,
|
315 |
+
"earbody": 271,
|
316 |
+
"Ġbearbody": 272,
|
317 |
+
"10": 273,
|
318 |
+
"in": 274,
|
319 |
+
"inf": 275,
|
320 |
+
"15": 276,
|
321 |
+
"25": 277,
|
322 |
+
"50": 278,
|
323 |
+
"20": 279,
|
324 |
+
"40": 280,
|
325 |
+
"30": 281,
|
326 |
+
"35": 282,
|
327 |
+
"upinf": 283,
|
328 |
+
"upinfdown": 284,
|
329 |
+
"downinf": 285,
|
330 |
+
"infup": 286,
|
331 |
+
"Ġbullbodyinfup": 287,
|
332 |
+
"70": 288,
|
333 |
+
"65": 289,
|
334 |
+
"upinfdowninf": 290,
|
335 |
+
"80": 291,
|
336 |
+
"90": 292,
|
337 |
+
"95": 293,
|
338 |
+
"Ġbullbodyinf": 294,
|
339 |
+
"Ġbearbodyinfup": 295,
|
340 |
+
"bullbody": 296,
|
341 |
+
"Ġbullbodyinfupinfdown": 297,
|
342 |
+
"bearbody": 298,
|
343 |
+
"Ġbullbodyinfupinfdowninf": 299,
|
344 |
+
"Ġbearbodyinf": 300,
|
345 |
+
"Ġbearbodyinfupinfdown": 301,
|
346 |
+
"bullbodyinfup": 302,
|
347 |
+
"Ġbearbodyinfupinfdowninf": 303,
|
348 |
+
"bullbodyinf": 304,
|
349 |
+
"bearbodyinfup": 305,
|
350 |
+
"bullbodyinfupinfdown": 306,
|
351 |
+
"bullbodyinfupinfdowninf": 307,
|
352 |
+
"bearbodyinf": 308,
|
353 |
+
"bearbodyinfupinfdown": 309,
|
354 |
+
"bearbodyinfupinfdowninf": 310
|
355 |
+
},
|
356 |
+
"merges": [
|
357 |
+
"b o",
|
358 |
+
"d o",
|
359 |
+
"d y",
|
360 |
+
"u p",
|
361 |
+
"w n",
|
362 |
+
"bo dy",
|
363 |
+
"do wn",
|
364 |
+
"Ġ b",
|
365 |
+
"l l",
|
366 |
+
"u ll",
|
367 |
+
"ull body",
|
368 |
+
"Ġb ullbody",
|
369 |
+
"a r",
|
370 |
+
"e ar",
|
371 |
+
"ear body",
|
372 |
+
"Ġb earbody",
|
373 |
+
"1 0",
|
374 |
+
"i n",
|
375 |
+
"in f",
|
376 |
+
"1 5",
|
377 |
+
"2 5",
|
378 |
+
"5 0",
|
379 |
+
"2 0",
|
380 |
+
"4 0",
|
381 |
+
"3 0",
|
382 |
+
"3 5",
|
383 |
+
"up inf",
|
384 |
+
"upinf down",
|
385 |
+
"down inf",
|
386 |
+
"inf up",
|
387 |
+
"Ġbullbody infup",
|
388 |
+
"7 0",
|
389 |
+
"6 5",
|
390 |
+
"upinfdown inf",
|
391 |
+
"8 0",
|
392 |
+
"9 0",
|
393 |
+
"9 5",
|
394 |
+
"Ġbullbody inf",
|
395 |
+
"Ġbearbody infup",
|
396 |
+
"b ullbody",
|
397 |
+
"Ġbullbodyinf upinfdown",
|
398 |
+
"b earbody",
|
399 |
+
"Ġbullbodyinf upinfdowninf",
|
400 |
+
"Ġbearbody inf",
|
401 |
+
"Ġbearbodyinf upinfdown",
|
402 |
+
"bullbody infup",
|
403 |
+
"Ġbearbodyinf upinfdowninf",
|
404 |
+
"bullbody inf",
|
405 |
+
"bearbody infup",
|
406 |
+
"bullbodyinf upinfdown",
|
407 |
+
"bullbodyinf upinfdowninf",
|
408 |
+
"bearbody inf",
|
409 |
+
"bearbodyinf upinfdown",
|
410 |
+
"bearbodyinf upinfdowninf"
|
411 |
+
]
|
412 |
+
}
|
413 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1024,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4ccc7a25611ffaa7b134b6dc3eaf0092bb44fc6ae3f5f4f7a3eddad4733c8b3
|
3 |
+
size 4027
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<|endoftext|>":0,"!":1,"\"":2,"#":3,"$":4,"%":5,"&":6,"'":7,"(":8,")":9,"*":10,"+":11,",":12,"-":13,".":14,"/":15,"0":16,"1":17,"2":18,"3":19,"4":20,"5":21,"6":22,"7":23,"8":24,"9":25,":":26,";":27,"<":28,"=":29,">":30,"?":31,"@":32,"A":33,"B":34,"C":35,"D":36,"E":37,"F":38,"G":39,"H":40,"I":41,"J":42,"K":43,"L":44,"M":45,"N":46,"O":47,"P":48,"Q":49,"R":50,"S":51,"T":52,"U":53,"V":54,"W":55,"X":56,"Y":57,"Z":58,"[":59,"\\":60,"]":61,"^":62,"_":63,"`":64,"a":65,"b":66,"c":67,"d":68,"e":69,"f":70,"g":71,"h":72,"i":73,"j":74,"k":75,"l":76,"m":77,"n":78,"o":79,"p":80,"q":81,"r":82,"s":83,"t":84,"u":85,"v":86,"w":87,"x":88,"y":89,"z":90,"{":91,"|":92,"}":93,"~":94,"¡":95,"¢":96,"£":97,"¤":98,"¥":99,"¦":100,"§":101,"¨":102,"©":103,"ª":104,"«":105,"¬":106,"®":107,"¯":108,"°":109,"±":110,"²":111,"³":112,"´":113,"µ":114,"¶":115,"·":116,"¸":117,"¹":118,"º":119,"»":120,"¼":121,"½":122,"¾":123,"¿":124,"À":125,"Á":126,"Â":127,"Ã":128,"Ä":129,"Å":130,"Æ":131,"Ç":132,"È":133,"É":134,"Ê":135,"Ë":136,"Ì":137,"Í":138,"Î":139,"Ï":140,"Ð":141,"Ñ":142,"Ò":143,"Ó":144,"Ô":145,"Õ":146,"Ö":147,"×":148,"Ø":149,"Ù":150,"Ú":151,"Û":152,"Ü":153,"Ý":154,"Þ":155,"ß":156,"à":157,"á":158,"â":159,"ã":160,"ä":161,"å":162,"æ":163,"ç":164,"è":165,"é":166,"ê":167,"ë":168,"ì":169,"í":170,"î":171,"ï":172,"ð":173,"ñ":174,"ò":175,"ó":176,"ô":177,"õ":178,"ö":179,"÷":180,"ø":181,"ù":182,"ú":183,"û":184,"ü":185,"ý":186,"þ":187,"ÿ":188,"Ā":189,"ā":190,"Ă":191,"ă":192,"Ą":193,"ą":194,"Ć":195,"ć":196,"Ĉ":197,"ĉ":198,"Ċ":199,"ċ":200,"Č":201,"č":202,"Ď":203,"ď":204,"Đ":205,"đ":206,"Ē":207,"ē":208,"Ĕ":209,"ĕ":210,"Ė":211,"ė":212,"Ę":213,"ę":214,"Ě":215,"ě":216,"Ĝ":217,"ĝ":218,"Ğ":219,"ğ":220,"Ġ":221,"ġ":222,"Ģ":223,"ģ":224,"Ĥ":225,"ĥ":226,"Ħ":227,"ħ":228,"Ĩ":229,"ĩ":230,"Ī":231,"ī":232,"Ĭ":233,"ĭ":234,"Į":235,"į":236,"İ":237,"ı":238,"IJ":239,"ij":240,"Ĵ":241,"ĵ":242,"Ķ":243,"ķ":244,"ĸ":245,"Ĺ":246,"ĺ":247,"Ļ":248,"ļ":249,"Ľ":250,"ľ":251,"Ŀ":252,"ŀ":253,"Ł":254,"ł":255,"Ń":256,"bo":257,"do":258,"dy":259,"up":260,"wn":261,"body":262,"down":263,"Ġb":264,"ll":265,"ull":266,"ullbody":267,"Ġbullbody":268,"ar":269,"ear":270,"earbody":271,"Ġbearbody":272,"10":273,"in":274,"inf":275,"15":276,"25":277,"50":278,"20":279,"40":280,"30":281,"35":282,"upinf":283,"upinfdown":284,"downinf":285,"infup":286,"Ġbullbodyinfup":287,"70":288,"65":289,"upinfdowninf":290,"80":291,"90":292,"95":293,"Ġbullbodyinf":294,"Ġbearbodyinfup":295,"bullbody":296,"Ġbullbodyinfupinfdown":297,"bearbody":298,"Ġbullbodyinfupinfdowninf":299,"Ġbearbodyinf":300,"Ġbearbodyinfupinfdown":301,"bullbodyinfup":302,"Ġbearbodyinfupinfdowninf":303,"bullbodyinf":304,"bearbodyinfup":305,"bullbodyinfupinfdown":306,"bullbodyinfupinfdowninf":307,"bearbodyinf":308,"bearbodyinfupinfdown":309,"bearbodyinfupinfdowninf":310}
|