Hugging Face's logo

dq158
/
coqui

Safetensors
Model card Files
xet
Community
dq158 commited on
Commit
91deccb
·
1 Parent(s): 894f5e2

WIPE IT ALL OUT

Browse files
Files changed (18) hide show
  1. .gitattributes +0 -35
  2. README.md +0 -58
  3. config.json +0 -62
  4. generation_config.json +0 -6
  5. last-checkpoint/config.json +0 -62
  6. last-checkpoint/generation_config.json +0 -6
  7. last-checkpoint/optimizer.pt +0 -3
  8. last-checkpoint/pytorch_model.bin +0 -3
  9. last-checkpoint/rng_state.pth +0 -3
  10. last-checkpoint/scheduler.pt +0 -3
  11. last-checkpoint/trainer_state.json +0 -336
  12. last-checkpoint/training_args.bin +0 -3
  13. pytorch_model.bin +0 -3
  14. tokenizer (1).json +0 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config (1).json +0 -10
  17. tokenizer_config.json +0 -10
  18. training_args.bin +0 -3
.gitattributes DELETED
@@ -1,35 +0,0 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
README.md DELETED
@@ -1,58 +0,0 @@
1
- ---
2
- tags:
3
- - generated_from_trainer
4
- model-index:
5
- - name: coqui
6
- results: []
7
- ---
8
-
9
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
- should probably proofread and complete it, then remove this comment. -->
11
-
12
- # coqui
13
-
14
- This model was trained from scratch on an unknown dataset.
15
- It achieves the following results on the evaluation set:
16
- - eval_loss: 2.3637
17
- - eval_bleu: 1.0
18
- - eval_precisions: [1.0, 1.0, 1.0, 1.0]
19
- - eval_brevity_penalty: 1.0
20
- - eval_length_ratio: 1.0
21
- - eval_translation_length: 3779
22
- - eval_reference_length: 3779
23
- - eval_runtime: 35.8058
24
- - eval_samples_per_second: 5.586
25
- - eval_steps_per_second: 0.475
26
- - step: 0
27
-
28
- ## Model description
29
-
30
- More information needed
31
-
32
- ## Intended uses & limitations
33
-
34
- More information needed
35
-
36
- ## Training and evaluation data
37
-
38
- More information needed
39
-
40
- ## Training procedure
41
-
42
- ### Training hyperparameters
43
-
44
- The following hyperparameters were used during training:
45
- - learning_rate: 5e-05
46
- - train_batch_size: 12
47
- - eval_batch_size: 12
48
- - seed: 42
49
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
- - lr_scheduler_type: linear
51
- - num_epochs: 5
52
-
53
- ### Framework versions
54
-
55
- - Transformers 4.34.1
56
- - Pytorch 2.1.0+cu118
57
- - Datasets 2.14.5
58
- - Tokenizers 0.14.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,62 +0,0 @@
1
- {
2
- "_name_or_path": "google/flan-t5-base",
3
- "architectures": [
4
- "T5ForConditionalGeneration"
5
- ],
6
- "classifier_dropout": 0.0,
7
- "d_ff": 2048,
8
- "d_kv": 64,
9
- "d_model": 768,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
- "initializer_factor": 1.0,
16
- "is_encoder_decoder": true,
17
- "is_gated_act": true,
18
- "layer_norm_epsilon": 1e-06,
19
- "model_type": "t5",
20
- "n_positions": 512,
21
- "num_decoder_layers": 12,
22
- "num_heads": 12,
23
- "num_layers": 12,
24
- "output_past": true,
25
- "pad_token_id": 0,
26
- "relative_attention_max_distance": 128,
27
- "relative_attention_num_buckets": 32,
28
- "task_specific_params": {
29
- "summarization": {
30
- "early_stopping": true,
31
- "length_penalty": 2.0,
32
- "max_length": 200,
33
- "min_length": 30,
34
- "no_repeat_ngram_size": 3,
35
- "num_beams": 4,
36
- "prefix": "summarize: "
37
- },
38
- "translation_en_to_de": {
39
- "early_stopping": true,
40
- "max_length": 300,
41
- "num_beams": 4,
42
- "prefix": "translate English to German: "
43
- },
44
- "translation_en_to_fr": {
45
- "early_stopping": true,
46
- "max_length": 300,
47
- "num_beams": 4,
48
- "prefix": "translate English to French: "
49
- },
50
- "translation_en_to_ro": {
51
- "early_stopping": true,
52
- "max_length": 300,
53
- "num_beams": 4,
54
- "prefix": "translate English to Romanian: "
55
- }
56
- },
57
- "tie_word_embeddings": false,
58
- "torch_dtype": "float32",
59
- "transformers_version": "4.34.1",
60
- "use_cache": true,
61
- "vocab_size": 32128
62
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "decoder_start_token_id": 0,
3
- "eos_token_id": 1,
4
- "pad_token_id": 0,
5
- "transformers_version": "4.34.1"
6
- }
 
 
 
 
 
 
 
last-checkpoint/config.json DELETED
@@ -1,62 +0,0 @@
1
- {
2
- "_name_or_path": "google/flan-t5-base",
3
- "architectures": [
4
- "T5ForConditionalGeneration"
5
- ],
6
- "classifier_dropout": 0.0,
7
- "d_ff": 2048,
8
- "d_kv": 64,
9
- "d_model": 768,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
- "initializer_factor": 1.0,
16
- "is_encoder_decoder": true,
17
- "is_gated_act": true,
18
- "layer_norm_epsilon": 1e-06,
19
- "model_type": "t5",
20
- "n_positions": 512,
21
- "num_decoder_layers": 12,
22
- "num_heads": 12,
23
- "num_layers": 12,
24
- "output_past": true,
25
- "pad_token_id": 0,
26
- "relative_attention_max_distance": 128,
27
- "relative_attention_num_buckets": 32,
28
- "task_specific_params": {
29
- "summarization": {
30
- "early_stopping": true,
31
- "length_penalty": 2.0,
32
- "max_length": 200,
33
- "min_length": 30,
34
- "no_repeat_ngram_size": 3,
35
- "num_beams": 4,
36
- "prefix": "summarize: "
37
- },
38
- "translation_en_to_de": {
39
- "early_stopping": true,
40
- "max_length": 300,
41
- "num_beams": 4,
42
- "prefix": "translate English to German: "
43
- },
44
- "translation_en_to_fr": {
45
- "early_stopping": true,
46
- "max_length": 300,
47
- "num_beams": 4,
48
- "prefix": "translate English to French: "
49
- },
50
- "translation_en_to_ro": {
51
- "early_stopping": true,
52
- "max_length": 300,
53
- "num_beams": 4,
54
- "prefix": "translate English to Romanian: "
55
- }
56
- },
57
- "tie_word_embeddings": false,
58
- "torch_dtype": "float32",
59
- "transformers_version": "4.34.1",
60
- "use_cache": true,
61
- "vocab_size": 32128
62
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "decoder_start_token_id": 0,
3
- "eos_token_id": 1,
4
- "pad_token_id": 0,
5
- "transformers_version": "4.34.1"
6
- }
 
 
 
 
 
 
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:095b3a1f6740c3523f4d618eb6e304dac8fadfe4f53deea6f89e7adff3341492
3
- size 2371770
 
 
 
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1a76fa844f3a3191566c354079a7f4bc5694f5240c5233e76e250c0f6fce96d
3
- size 990409330
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:443ad106e89f5c225106f610ada6104a4bdb83f20e5790a9a64bb3871f9500ee
3
- size 14244
 
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ff0f9f47b6a148ea17a10b4a36afba9e6cfc279b51fe048a45e8fbccd92f97e
3
- size 1064
 
 
 
 
last-checkpoint/trainer_state.json DELETED
@@ -1,336 +0,0 @@
1
- {
2
- "best_metric": 2.0005455017089844,
3
- "best_model_checkpoint": "dq158/coqui/checkpoint-9143",
4
- "epoch": 10.999097744360903,
5
- "eval_steps": 500,
6
- "global_step": 9143,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.6,
13
- "learning_rate": 9e-05,
14
- "loss": 3.0484,
15
- "step": 500
16
- },
17
- {
18
- "epoch": 1.0,
19
- "eval_bleu": 1.0,
20
- "eval_brevity_penalty": 1.0,
21
- "eval_length_ratio": 1.0,
22
- "eval_loss": 2.320953369140625,
23
- "eval_precisions": [
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0
28
- ],
29
- "eval_reference_length": 54898,
30
- "eval_runtime": 620.4093,
31
- "eval_samples_per_second": 4.765,
32
- "eval_steps_per_second": 0.596,
33
- "eval_translation_length": 54898,
34
- "step": 831
35
- },
36
- {
37
- "epoch": 1.2,
38
- "learning_rate": 8.978652426235755e-05,
39
- "loss": 2.5083,
40
- "step": 1000
41
- },
42
- {
43
- "epoch": 1.8,
44
- "learning_rate": 8.914812246678847e-05,
45
- "loss": 2.3881,
46
- "step": 1500
47
- },
48
- {
49
- "epoch": 2.0,
50
- "eval_bleu": 1.0,
51
- "eval_brevity_penalty": 1.0,
52
- "eval_length_ratio": 1.0,
53
- "eval_loss": 2.1850905418395996,
54
- "eval_precisions": [
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0
59
- ],
60
- "eval_reference_length": 55985,
61
- "eval_runtime": 613.0871,
62
- "eval_samples_per_second": 4.822,
63
- "eval_steps_per_second": 0.604,
64
- "eval_translation_length": 55985,
65
- "step": 1662
66
- },
67
- {
68
- "epoch": 2.41,
69
- "learning_rate": 8.809085164859153e-05,
70
- "loss": 2.2764,
71
- "step": 2000
72
- },
73
- {
74
- "epoch": 3.0,
75
- "eval_bleu": 1.0,
76
- "eval_brevity_penalty": 1.0,
77
- "eval_length_ratio": 1.0,
78
- "eval_loss": 2.1248879432678223,
79
- "eval_precisions": [
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0
84
- ],
85
- "eval_reference_length": 56111,
86
- "eval_runtime": 612.445,
87
- "eval_samples_per_second": 4.827,
88
- "eval_steps_per_second": 0.604,
89
- "eval_translation_length": 56111,
90
- "step": 2493
91
- },
92
- {
93
- "epoch": 3.01,
94
- "learning_rate": 8.662474299300236e-05,
95
- "loss": 2.2434,
96
- "step": 2500
97
- },
98
- {
99
- "epoch": 3.61,
100
- "learning_rate": 8.476370666120834e-05,
101
- "loss": 2.1919,
102
- "step": 3000
103
- },
104
- {
105
- "epoch": 4.0,
106
- "eval_bleu": 1.0,
107
- "eval_brevity_penalty": 1.0,
108
- "eval_length_ratio": 1.0,
109
- "eval_loss": 2.0848147869110107,
110
- "eval_precisions": [
111
- 1.0,
112
- 1.0,
113
- 1.0,
114
- 1.0
115
- ],
116
- "eval_reference_length": 56105,
117
- "eval_runtime": 610.0346,
118
- "eval_samples_per_second": 4.846,
119
- "eval_steps_per_second": 0.607,
120
- "eval_translation_length": 56105,
121
- "step": 3325
122
- },
123
- {
124
- "epoch": 4.21,
125
- "learning_rate": 8.252539981337433e-05,
126
- "loss": 2.1471,
127
- "step": 3500
128
- },
129
- {
130
- "epoch": 4.81,
131
- "learning_rate": 7.993105908085196e-05,
132
- "loss": 2.118,
133
- "step": 4000
134
- },
135
- {
136
- "epoch": 5.0,
137
- "eval_bleu": 1.0,
138
- "eval_brevity_penalty": 1.0,
139
- "eval_length_ratio": 1.0,
140
- "eval_loss": 2.0643346309661865,
141
- "eval_precisions": [
142
- 1.0,
143
- 1.0,
144
- 1.0,
145
- 1.0
146
- ],
147
- "eval_reference_length": 56093,
148
- "eval_runtime": 609.9445,
149
- "eval_samples_per_second": 4.846,
150
- "eval_steps_per_second": 0.607,
151
- "eval_translation_length": 56093,
152
- "step": 4156
153
- },
154
- {
155
- "epoch": 5.41,
156
- "learning_rate": 7.700529907704438e-05,
157
- "loss": 2.0902,
158
- "step": 4500
159
- },
160
- {
161
- "epoch": 6.0,
162
- "eval_bleu": 1.0,
163
- "eval_brevity_penalty": 1.0,
164
- "eval_length_ratio": 1.0,
165
- "eval_loss": 2.043013334274292,
166
- "eval_precisions": [
167
- 1.0,
168
- 1.0,
169
- 1.0,
170
- 1.0
171
- ],
172
- "eval_reference_length": 56093,
173
- "eval_runtime": 610.4388,
174
- "eval_samples_per_second": 4.842,
175
- "eval_steps_per_second": 0.606,
176
- "eval_translation_length": 56093,
177
- "step": 4987
178
- },
179
- {
180
- "epoch": 6.02,
181
- "learning_rate": 7.377587885861725e-05,
182
- "loss": 2.0863,
183
- "step": 5000
184
- },
185
- {
186
- "epoch": 6.62,
187
- "learning_rate": 7.027343855282776e-05,
188
- "loss": 2.0434,
189
- "step": 5500
190
- },
191
- {
192
- "epoch": 7.0,
193
- "eval_bleu": 1.0,
194
- "eval_brevity_penalty": 1.0,
195
- "eval_length_ratio": 1.0,
196
- "eval_loss": 2.028670310974121,
197
- "eval_precisions": [
198
- 1.0,
199
- 1.0,
200
- 1.0,
201
- 1.0
202
- ],
203
- "eval_reference_length": 56086,
204
- "eval_runtime": 610.2247,
205
- "eval_samples_per_second": 4.844,
206
- "eval_steps_per_second": 0.606,
207
- "eval_translation_length": 56086,
208
- "step": 5818
209
- },
210
- {
211
- "epoch": 7.22,
212
- "learning_rate": 6.653120864980153e-05,
213
- "loss": 2.0282,
214
- "step": 6000
215
- },
216
- {
217
- "epoch": 7.82,
218
- "learning_rate": 6.258469471793752e-05,
219
- "loss": 2.0107,
220
- "step": 6500
221
- },
222
- {
223
- "epoch": 8.0,
224
- "eval_bleu": 1.0,
225
- "eval_brevity_penalty": 1.0,
226
- "eval_length_ratio": 1.0,
227
- "eval_loss": 2.0178780555725098,
228
- "eval_precisions": [
229
- 1.0,
230
- 1.0,
231
- 1.0,
232
- 1.0
233
- ],
234
- "eval_reference_length": 56070,
235
- "eval_runtime": 609.3401,
236
- "eval_samples_per_second": 4.851,
237
- "eval_steps_per_second": 0.607,
238
- "eval_translation_length": 56070,
239
- "step": 6650
240
- },
241
- {
242
- "epoch": 8.42,
243
- "learning_rate": 5.8471340533801125e-05,
244
- "loss": 1.986,
245
- "step": 7000
246
- },
247
- {
248
- "epoch": 9.0,
249
- "eval_bleu": 1.0,
250
- "eval_brevity_penalty": 1.0,
251
- "eval_length_ratio": 1.0,
252
- "eval_loss": 2.0124728679656982,
253
- "eval_precisions": [
254
- 1.0,
255
- 1.0,
256
- 1.0,
257
- 1.0
258
- ],
259
- "eval_reference_length": 56071,
260
- "eval_runtime": 610.7638,
261
- "eval_samples_per_second": 4.84,
262
- "eval_steps_per_second": 0.606,
263
- "eval_translation_length": 56071,
264
- "step": 7481
265
- },
266
- {
267
- "epoch": 9.02,
268
- "learning_rate": 5.4230172822665325e-05,
269
- "loss": 1.983,
270
- "step": 7500
271
- },
272
- {
273
- "epoch": 9.62,
274
- "learning_rate": 4.9901430980334607e-05,
275
- "loss": 1.9669,
276
- "step": 8000
277
- },
278
- {
279
- "epoch": 10.0,
280
- "eval_bleu": 1.0,
281
- "eval_brevity_penalty": 1.0,
282
- "eval_length_ratio": 1.0,
283
- "eval_loss": 2.0042803287506104,
284
- "eval_precisions": [
285
- 1.0,
286
- 1.0,
287
- 1.0,
288
- 1.0
289
- ],
290
- "eval_reference_length": 55997,
291
- "eval_runtime": 611.382,
292
- "eval_samples_per_second": 4.835,
293
- "eval_steps_per_second": 0.605,
294
- "eval_translation_length": 55997,
295
- "step": 8312
296
- },
297
- {
298
- "epoch": 10.23,
299
- "learning_rate": 4.552618528938031e-05,
300
- "loss": 1.9494,
301
- "step": 8500
302
- },
303
- {
304
- "epoch": 10.83,
305
- "learning_rate": 4.114594725207993e-05,
306
- "loss": 1.9375,
307
- "step": 9000
308
- },
309
- {
310
- "epoch": 11.0,
311
- "eval_bleu": 1.0,
312
- "eval_brevity_penalty": 1.0,
313
- "eval_length_ratio": 1.0,
314
- "eval_loss": 2.0005455017089844,
315
- "eval_precisions": [
316
- 1.0,
317
- 1.0,
318
- 1.0,
319
- 1.0
320
- ],
321
- "eval_reference_length": 56078,
322
- "eval_runtime": 610.5262,
323
- "eval_samples_per_second": 4.842,
324
- "eval_steps_per_second": 0.606,
325
- "eval_translation_length": 56078,
326
- "step": 9143
327
- }
328
- ],
329
- "logging_steps": 500,
330
- "max_steps": 16620,
331
- "num_train_epochs": 20,
332
- "save_steps": 500,
333
- "total_flos": 2.0034493666453094e+17,
334
- "trial_name": null,
335
- "trial_params": null
336
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb979b12971fd8db8ac0c730868c028dff7eb6b6489e260350ad8e97e8318b11
3
- size 4664
 
 
 
 
pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1a76fa844f3a3191566c354079a7f4bc5694f5240c5233e76e250c0f6fce96d
3
- size 990409330
 
 
 
 
tokenizer (1).json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_config (1).json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "eos_token": "</s>",
3
- "extra_ids": 100,
4
- "model_max_length": 512,
5
- "name_or_path": "google/flan-t5-base",
6
- "pad_token": "<pad>",
7
- "sp_model_kwargs": {},
8
- "tokenizer_class": "T5Tokenizer",
9
- "unk_token": "<unk>"
10
- }
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "eos_token": "</s>",
3
- "extra_ids": 100,
4
- "model_max_length": 512,
5
- "name_or_path": "google/flan-t5-base",
6
- "pad_token": "<pad>",
7
- "sp_model_kwargs": {},
8
- "tokenizer_class": "T5Tokenizer",
9
- "unk_token": "<unk>"
10
- }
 
 
 
 
 
 
 
 
 
 
 
training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb979b12971fd8db8ac0c730868c028dff7eb6b6489e260350ad8e97e8318b11
3
- size 4664