Upload 9 files
Browse files- config.json +213 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-small",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 1024,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"length_penalty": 0.6,
|
17 |
+
"max_length": 84,
|
18 |
+
"model_type": "mt5",
|
19 |
+
"num_beams": 4,
|
20 |
+
"num_decoder_layers": 8,
|
21 |
+
"num_heads": 6,
|
22 |
+
"num_layers": 8,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_num_buckets": 32,
|
25 |
+
"task_specific_params": {
|
26 |
+
"langid_map": {
|
27 |
+
"amharic": [
|
28 |
+
35,
|
29 |
+
"\u2581<extra_id_64>"
|
30 |
+
],
|
31 |
+
"arabic": [
|
32 |
+
4,
|
33 |
+
"\u2581<extra_id_95>"
|
34 |
+
],
|
35 |
+
"azerbaijani": [
|
36 |
+
7,
|
37 |
+
"\u2581<extra_id_92>"
|
38 |
+
],
|
39 |
+
"bengali": [
|
40 |
+
42,
|
41 |
+
"\u2581<extra_id_57>"
|
42 |
+
],
|
43 |
+
"burmese": [
|
44 |
+
33,
|
45 |
+
"\u2581<extra_id_66>"
|
46 |
+
],
|
47 |
+
"chinese_simplified": [
|
48 |
+
40,
|
49 |
+
"\u2581<extra_id_59>"
|
50 |
+
],
|
51 |
+
"chinese_traditional": [
|
52 |
+
44,
|
53 |
+
"\u2581<extra_id_55>"
|
54 |
+
],
|
55 |
+
"english": [
|
56 |
+
30,
|
57 |
+
"\u2581<extra_id_69>"
|
58 |
+
],
|
59 |
+
"french": [
|
60 |
+
10,
|
61 |
+
"\u2581<extra_id_89>"
|
62 |
+
],
|
63 |
+
"gujarati": [
|
64 |
+
27,
|
65 |
+
"\u2581<extra_id_72>"
|
66 |
+
],
|
67 |
+
"hausa": [
|
68 |
+
43,
|
69 |
+
"\u2581<extra_id_56>"
|
70 |
+
],
|
71 |
+
"hindi": [
|
72 |
+
21,
|
73 |
+
"\u2581<extra_id_78>"
|
74 |
+
],
|
75 |
+
"igbo": [
|
76 |
+
9,
|
77 |
+
"\u2581<extra_id_90>"
|
78 |
+
],
|
79 |
+
"indonesian": [
|
80 |
+
1,
|
81 |
+
"\u2581<extra_id_98>"
|
82 |
+
],
|
83 |
+
"japanese": [
|
84 |
+
37,
|
85 |
+
"\u2581<extra_id_62>"
|
86 |
+
],
|
87 |
+
"kirundi": [
|
88 |
+
0,
|
89 |
+
"\u2581<extra_id_99>"
|
90 |
+
],
|
91 |
+
"korean": [
|
92 |
+
29,
|
93 |
+
"\u2581<extra_id_70>"
|
94 |
+
],
|
95 |
+
"kyrgyz": [
|
96 |
+
5,
|
97 |
+
"\u2581<extra_id_94>"
|
98 |
+
],
|
99 |
+
"marathi": [
|
100 |
+
13,
|
101 |
+
"\u2581<extra_id_86>"
|
102 |
+
],
|
103 |
+
"nepali": [
|
104 |
+
20,
|
105 |
+
"\u2581<extra_id_79>"
|
106 |
+
],
|
107 |
+
"oromo": [
|
108 |
+
41,
|
109 |
+
"\u2581<extra_id_58>"
|
110 |
+
],
|
111 |
+
"pashto": [
|
112 |
+
34,
|
113 |
+
"\u2581<extra_id_65>"
|
114 |
+
],
|
115 |
+
"persian": [
|
116 |
+
23,
|
117 |
+
"\u2581<extra_id_76>"
|
118 |
+
],
|
119 |
+
"pidgin": [
|
120 |
+
14,
|
121 |
+
"\u2581<extra_id_85>"
|
122 |
+
],
|
123 |
+
"portuguese": [
|
124 |
+
39,
|
125 |
+
"\u2581<extra_id_60>"
|
126 |
+
],
|
127 |
+
"punjabi": [
|
128 |
+
17,
|
129 |
+
"\u2581<extra_id_82>"
|
130 |
+
],
|
131 |
+
"russian": [
|
132 |
+
36,
|
133 |
+
"\u2581<extra_id_63>"
|
134 |
+
],
|
135 |
+
"scottish_gaelic": [
|
136 |
+
24,
|
137 |
+
"\u2581<extra_id_75>"
|
138 |
+
],
|
139 |
+
"serbian_cyrillic": [
|
140 |
+
28,
|
141 |
+
"\u2581<extra_id_71>"
|
142 |
+
],
|
143 |
+
"serbian_latin": [
|
144 |
+
11,
|
145 |
+
"\u2581<extra_id_88>"
|
146 |
+
],
|
147 |
+
"sinhala": [
|
148 |
+
31,
|
149 |
+
"\u2581<extra_id_68>"
|
150 |
+
],
|
151 |
+
"somali": [
|
152 |
+
19,
|
153 |
+
"\u2581<extra_id_80>"
|
154 |
+
],
|
155 |
+
"spanish": [
|
156 |
+
3,
|
157 |
+
"\u2581<extra_id_96>"
|
158 |
+
],
|
159 |
+
"swahili": [
|
160 |
+
18,
|
161 |
+
"\u2581<extra_id_81>"
|
162 |
+
],
|
163 |
+
"tamil": [
|
164 |
+
32,
|
165 |
+
"\u2581<extra_id_67>"
|
166 |
+
],
|
167 |
+
"telugu": [
|
168 |
+
22,
|
169 |
+
"\u2581<extra_id_77>"
|
170 |
+
],
|
171 |
+
"thai": [
|
172 |
+
6,
|
173 |
+
"\u2581<extra_id_93>"
|
174 |
+
],
|
175 |
+
"tigrinya": [
|
176 |
+
16,
|
177 |
+
"\u2581<extra_id_83>"
|
178 |
+
],
|
179 |
+
"turkish": [
|
180 |
+
15,
|
181 |
+
"\u2581<extra_id_84>"
|
182 |
+
],
|
183 |
+
"ukrainian": [
|
184 |
+
2,
|
185 |
+
"\u2581<extra_id_97>"
|
186 |
+
],
|
187 |
+
"urdu": [
|
188 |
+
38,
|
189 |
+
"\u2581<extra_id_61>"
|
190 |
+
],
|
191 |
+
"uzbek": [
|
192 |
+
8,
|
193 |
+
"\u2581<extra_id_91>"
|
194 |
+
],
|
195 |
+
"vietnamese": [
|
196 |
+
12,
|
197 |
+
"\u2581<extra_id_87>"
|
198 |
+
],
|
199 |
+
"welsh": [
|
200 |
+
26,
|
201 |
+
"\u2581<extra_id_73>"
|
202 |
+
],
|
203 |
+
"yoruba": [
|
204 |
+
25,
|
205 |
+
"\u2581<extra_id_74>"
|
206 |
+
]
|
207 |
+
}
|
208 |
+
},
|
209 |
+
"tie_word_embeddings": false,
|
210 |
+
"tokenizer_class": "T5Tokenizer",
|
211 |
+
"use_cache": true,
|
212 |
+
"vocab_size": 250112
|
213 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5576e8b895c0b7aa2b8813b5150880c0b484b6cebd05bfba9ea2e389867df480
|
3 |
+
size 2890175
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb5bd466548741738acf2f7ceb57873c8f1f6295abbe7c746d5dbbac374745b2
|
3 |
+
size 1200775901
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:194f99651e01b7fa05f3cfa059c2c1bf703f0d19875ba0a453e62b1f2683c8fe
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "mirror": null, "special_tokens_map_file": "/home/oem/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "tokenizer_file": null, "name_or_path": "google/mt5-small"}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21a57f837daff1187d6399ae80a1acb9b8d442cd6e63e9c3654acb6686df3488
|
3 |
+
size 2223
|