ArthurZ HF staff commited on
Commit
18f1ad8
1 Parent(s): bd43e2c

Upload TFT5ForConditionalGeneration

Browse files
README.md CHANGED
@@ -1,310 +1,47 @@
1
  ---
2
- language:
3
- - en
4
- - sp
5
- - ja
6
- - pe
7
- - hi
8
- - fr
9
- - ch
10
- - be
11
- - gu
12
- - ge
13
- - te
14
- - it
15
- - ar
16
- - po
17
- - ta
18
- - ma
19
- - ma
20
- - or
21
- - pa
22
- - po
23
- - ur
24
- - ga
25
- - he
26
- - ko
27
- - ca
28
- - th
29
- - du
30
- - in
31
- - vi
32
- - bu
33
- - fi
34
- - ce
35
- - la
36
- - tu
37
- - ru
38
- - cr
39
- - sw
40
- - yo
41
- - ku
42
- - bu
43
- - ma
44
- - cz
45
- - fi
46
- - so
47
- - ta
48
- - sw
49
- - si
50
- - ka
51
- - zh
52
- - ig
53
- - xh
54
- - ro
55
- - ha
56
- - es
57
- - sl
58
- - li
59
- - gr
60
- - ne
61
- - as
62
- - no
63
-
64
  tags:
65
- - text2text-generation
66
-
67
- datasets:
68
- - svakulenk0/qrecc
69
- - taskmaster2
70
- - djaym7/wiki_dialog
71
- - deepmind/code_contests
72
- - lambada
73
- - gsm8k
74
- - aqua_rat
75
- - esnli
76
- - quasc
77
- - qed
78
-
79
-
80
- license: apache-2.0
81
  ---
82
 
83
- # Model Card for FLAN-T5 large
84
-
85
- ![model image](https://s3.amazonaws.com/moonup/production/uploads/1666363435475-62441d1d9fdefb55a0b7d12c.png)
86
-
87
- # Table of Contents
88
-
89
- 0. [TL;DR](#TL;DR)
90
- 1. [Model Details](#model-details)
91
- 2. [Usage](#usage)
92
- 3. [Uses](#uses)
93
- 4. [Bias, Risks, and Limitations](#bias-risks-and-limitations)
94
- 5. [Training Details](#training-details)
95
- 6. [Evaluation](#evaluation)
96
- 7. [Environmental Impact](#environmental-impact)
97
- 8. [Citation](#citation)
98
-
99
- # TL;DR
100
-
101
- If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages.
102
- As mentioned in the first few lines of the abstract :
103
- > Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints,1 which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.
104
-
105
- **Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the [T5 model card](https://huggingface.co/t5-large).
106
-
107
- # Model Details
108
-
109
- ## Model Description
110
-
111
-
112
- - **Model type:** Language model
113
- - **Language(s) (NLP):** English, Spanish, Japanese, Persian, Hindi, French, Chinese, Bengali, Gujarati, German, Telugu, Italian, Arabic, Polish, Tamil, Marathi, Malayalam, Oriya, Panjabi, Portuguese, Urdu, Galician, Hebrew, Korean, Catalan, Thai, Dutch, Indonesian, Vietnamese, Bulgarian, Filipino, Central Khmer, Lao, Turkish, Russian, Croatian, Swedish, Yoruba, Kurdish, Burmese, Malay, Czech, Finnish, Somali, Tagalog, Swahili, Sinhala, Kannada, Zhuang, Igbo, Xhosa, Romanian, Haitian, Estonian, Slovak, Lithuanian, Greek, Nepali, Assamese, Norwegian
114
- - **License:** Apache 2.0
115
- - **Related Models:** [All FLAN-T5 Checkpoints](https://huggingface.co/models?search=flan-t5)
116
- - **Original Checkpoints:** [All Original FLAN-T5 Checkpoints](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-t5-checkpoints)
117
- - **Resources for more information:**
118
- - [Research paper](https://arxiv.org/pdf/2210.11416.pdf)
119
- - [GitHub Repo](https://github.com/google-research/t5x)
120
- - [Hugging Face FLAN-T5 Docs (Similar to T5) ](https://huggingface.co/docs/transformers/model_doc/t5)
121
-
122
- # Usage
123
-
124
- Find below some example scripts on how to use the model in `transformers`:
125
-
126
- ## Using the Pytorch model
127
-
128
- ### Running the model on a CPU
129
-
130
- <details>
131
- <summary> Click to expand </summary>
132
-
133
- ```python
134
-
135
- from transformers import T5Tokenizer, T5ForConditionalGeneration
136
-
137
- tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
138
- model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large")
139
-
140
- input_text = "translate English to German: How old are you?"
141
- input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids
142
-
143
- outputs = model.generate(input_ids)
144
- print(tokenizer.decode(outputs[0]))
145
- ```
146
-
147
- </details>
148
-
149
- ### Running the model on a GPU
150
-
151
- <details>
152
- <summary> Click to expand </summary>
153
-
154
- ```python
155
- # pip install accelerate
156
- from transformers import T5Tokenizer, T5ForConditionalGeneration
157
-
158
- tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
159
- model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto")
160
-
161
- input_text = "translate English to German: How old are you?"
162
- input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids.to("cuda")
163
-
164
- outputs = model.generate(input_ids)
165
- print(tokenizer.decode(outputs[0]))
166
- ```
167
-
168
- </details>
169
-
170
- ### Running the model on a GPU using different precisions
171
-
172
- #### FP16
173
-
174
- <details>
175
- <summary> Click to expand </summary>
176
-
177
- ```python
178
- # pip install accelerate
179
- import torch
180
- from transformers import T5Tokenizer, T5ForConditionalGeneration
181
-
182
- tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
183
- model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto", torch_dtype=torch.float16)
184
-
185
- input_text = "translate English to German: How old are you?"
186
- input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids.to("cuda")
187
-
188
- outputs = model.generate(input_ids)
189
- print(tokenizer.decode(outputs[0]))
190
- ```
191
-
192
- </details>
193
-
194
- #### INT8
195
-
196
- <details>
197
- <summary> Click to expand </summary>
198
-
199
- ```python
200
- # pip install bitsandbytes accelerate
201
- from transformers import T5Tokenizer, T5ForConditionalGeneration
202
-
203
- tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
204
- model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto", load_in_8bit=True)
205
-
206
- input_text = "translate English to German: How old are you?"
207
- input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids.to("cuda")
208
-
209
- outputs = model.generate(input_ids)
210
- print(tokenizer.decode(outputs[0]))
211
- ```
212
-
213
- </details>
214
-
215
- # Uses
216
-
217
- ## Direct Use and Downstream Use
218
-
219
- The authors write in [the original paper's model card](https://arxiv.org/pdf/2210.11416.pdf) that:
220
-
221
- > The primary use is research on language models, including: research on zero-shot NLP tasks and in-context few-shot learning NLP tasks, such as reasoning, and question answering; advancing fairness and safety research, and understanding limitations of current large language models
222
-
223
- See the [research paper](https://arxiv.org/pdf/2210.11416.pdf) for further details.
224
-
225
- ## Out-of-Scope Use
226
-
227
- More information needed.
228
-
229
- # Bias, Risks, and Limitations
230
-
231
- The information below in this section are copied from the model's [official model card](https://arxiv.org/pdf/2210.11416.pdf):
232
-
233
- > Language models, including Flan-T5, can potentially be used for language generation in a harmful way, according to Rae et al. (2021). Flan-T5 should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application.
234
-
235
- ## Ethical considerations and risks
236
-
237
- > Flan-T5 is fine-tuned on a large corpus of text data that was not filtered for explicit content or assessed for existing biases. As a result the model itself is potentially vulnerable to generating equivalently inappropriate content or replicating inherent biases in the underlying data.
238
-
239
- ## Known Limitations
240
-
241
- > Flan-T5 has not been tested in real world applications.
242
-
243
- ## Sensitive Use:
244
-
245
- > Flan-T5 should not be applied for any unacceptable use cases, e.g., generation of abusive speech.
246
-
247
- # Training Details
248
-
249
- ## Training Data
250
-
251
- The model was trained on a mixture of tasks, that includes the tasks described in the table below (from the original paper, figure 2):
252
-
253
- ![table.png](https://s3.amazonaws.com/moonup/production/uploads/1666363265279-62441d1d9fdefb55a0b7d12c.png)
254
-
255
 
256
- ## Training Procedure
257
 
258
- According to the model card from the [original paper](https://arxiv.org/pdf/2210.11416.pdf):
 
259
 
260
- > These models are based on pretrained T5 (Raffel et al., 2020) and fine-tuned with instructions for better zero-shot and few-shot performance. There is one fine-tuned Flan model per T5 model size.
261
 
262
- The model has been trained on TPU v3 or TPU v4 pods, using [`t5x`](https://github.com/google-research/t5x) codebase together with [`jax`](https://github.com/google/jax).
263
 
 
264
 
265
- # Evaluation
266
 
267
- ## Testing Data, Factors & Metrics
268
 
269
- The authors evaluated the model on various tasks covering several languages (1836 in total). See the table below for some quantitative evaluation:
270
- ![image.png](https://s3.amazonaws.com/moonup/production/uploads/1666361983550-62441d1d9fdefb55a0b7d12c.png)
271
- For full details, please check the [research paper](https://arxiv.org/pdf/2210.11416.pdf).
272
 
273
- ## Results
274
 
275
- For full results for FLAN-T5-Large, see the [research paper](https://arxiv.org/pdf/2210.11416.pdf), Table 3.
276
 
277
- # Environmental Impact
278
 
279
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
 
280
 
281
- - **Hardware Type:** Google Cloud TPU Pods - TPU v3 or TPU v4 | Number of chips ≥ 4.
282
- - **Hours used:** More information needed
283
- - **Cloud Provider:** GCP
284
- - **Compute Region:** More information needed
285
- - **Carbon Emitted:** More information needed
286
 
287
- # Citation
288
 
289
- **BibTeX:**
290
 
291
- ```bibtex
292
- @misc{https://doi.org/10.48550/arxiv.2210.11416,
293
- doi = {10.48550/ARXIV.2210.11416},
294
-
295
- url = {https://arxiv.org/abs/2210.11416},
296
-
297
- author = {Chung, Hyung Won and Hou, Le and Longpre, Shayne and Zoph, Barret and Tay, Yi and Fedus, William and Li, Eric and Wang, Xuezhi and Dehghani, Mostafa and Brahma, Siddhartha and Webson, Albert and Gu, Shixiang Shane and Dai, Zhuyun and Suzgun, Mirac and Chen, Xinyun and Chowdhery, Aakanksha and Narang, Sharan and Mishra, Gaurav and Yu, Adams and Zhao, Vincent and Huang, Yanping and Dai, Andrew and Yu, Hongkun and Petrov, Slav and Chi, Ed H. and Dean, Jeff and Devlin, Jacob and Roberts, Adam and Zhou, Denny and Le, Quoc V. and Wei, Jason},
298
-
299
- keywords = {Machine Learning (cs.LG), Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
300
-
301
- title = {Scaling Instruction-Finetuned Language Models},
302
-
303
- publisher = {arXiv},
304
-
305
- year = {2022},
306
-
307
- copyright = {Creative Commons Attribution 4.0 International}
308
- }
309
- ```
310
 
 
 
 
 
1
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  tags:
3
+ - generated_from_keras_callback
4
+ model-index:
5
+ - name: t5-xxl
6
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
7
  ---
8
 
9
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
10
+ probably proofread and complete it, then remove this comment. -->
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
 
12
+ # t5-xxl
13
 
14
+ This model was trained from scratch on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
 
 
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
+ - optimizer: None
36
+ - training_precision: float32
37
 
38
+ ### Training results
 
 
 
 
39
 
 
40
 
 
41
 
42
+ ### Framework versions
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
 
44
+ - Transformers 4.24.0.dev0
45
+ - TensorFlow 2.10.0
46
+ - Datasets 2.6.1
47
+ - Tokenizers 0.13.1
tf_model-00001-of-00005.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b26cdb4f6a728ad7d7ac8ab74100ceb9988f27119a4c58e96c781baa9cb9f6a
3
+ size 9989362864
tf_model-00002-of-00005.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22f1007bc7f7df18cd01258ca980ed570f3ef9c0d0d2e7dfaf214693e92b28c
3
+ size 9932810536
tf_model-00003-of-00005.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f8c1b2e49c147718deeaf0562bc46f9ca1bca52e38f66fe25c6271a67c3b92b
3
+ size 9999968760
tf_model-00004-of-00005.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0096154c641dba8fdc3d87fabbdf2346693b45d81711ca9913a13b4734c44540
3
+ size 9999964640
tf_model-00005-of-00005.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020b93b1bb89dbbdf61fec1184c342e78ec06294c52708efda40a7fee0edbae8
3
+ size 4620350264
tf_model.h5.index.json ADDED
@@ -0,0 +1,565 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 44541329408
4
+ },
5
+ "weight_map": {
6
+ "shared/shared/embeddings:0": "tf_model-00001-of-00005.h5",
7
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
8
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
9
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
10
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/relative_attention_bias/embeddings:0": "tf_model-00002-of-00005.h5",
11
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
12
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
13
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
14
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
15
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
16
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
17
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
18
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
19
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
20
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
21
+ "tft5_for_conditional_generation_1/decoder/block_._0/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
22
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
23
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
24
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
25
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
26
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
27
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
28
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
29
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
30
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
31
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
32
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
33
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
34
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
35
+ "tft5_for_conditional_generation_1/decoder/block_._1/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
36
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
37
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
38
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
39
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
40
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
41
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
42
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
43
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
44
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
45
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
46
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
47
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
48
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
49
+ "tft5_for_conditional_generation_1/decoder/block_._10/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
50
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
51
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
52
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
53
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
54
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
55
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
56
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
57
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
58
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
59
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
60
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
61
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
62
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
63
+ "tft5_for_conditional_generation_1/decoder/block_._11/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
64
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
65
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
66
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
67
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
68
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
69
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
70
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
71
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
72
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
73
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
74
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
75
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
76
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
77
+ "tft5_for_conditional_generation_1/decoder/block_._12/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
78
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
79
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
80
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
81
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
82
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
83
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
84
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
85
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
86
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
87
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
88
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
89
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
90
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
91
+ "tft5_for_conditional_generation_1/decoder/block_._13/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
92
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
93
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
94
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
95
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
96
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
97
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
98
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
99
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
100
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
101
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
102
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
103
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
104
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
105
+ "tft5_for_conditional_generation_1/decoder/block_._14/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
106
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
107
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
108
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
109
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
110
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
111
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
112
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
113
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
114
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
115
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
116
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
117
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
118
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
119
+ "tft5_for_conditional_generation_1/decoder/block_._15/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
120
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
121
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
122
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
123
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
124
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
125
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
126
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
127
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
128
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
129
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
130
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
131
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
132
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
133
+ "tft5_for_conditional_generation_1/decoder/block_._16/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
134
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
135
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
136
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
137
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
138
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
139
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
140
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
141
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
142
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
143
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
144
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
145
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
146
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
147
+ "tft5_for_conditional_generation_1/decoder/block_._17/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
148
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
149
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
150
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
151
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
152
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
153
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
154
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
155
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
156
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
157
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
158
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
159
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
160
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
161
+ "tft5_for_conditional_generation_1/decoder/block_._18/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
162
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
163
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
164
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
165
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
166
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
167
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
168
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
169
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
170
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
171
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
172
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
173
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
174
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
175
+ "tft5_for_conditional_generation_1/decoder/block_._19/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
176
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
177
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
178
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
179
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
180
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
181
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
182
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
183
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
184
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
185
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
186
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
187
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
188
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
189
+ "tft5_for_conditional_generation_1/decoder/block_._2/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
190
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/SelfAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
191
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/SelfAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
192
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
193
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/SelfAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
194
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
195
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
196
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
197
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
198
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
199
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
200
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00005-of-00005.h5",
201
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00005-of-00005.h5",
202
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00005-of-00005.h5",
203
+ "tft5_for_conditional_generation_1/decoder/block_._20/layer_._2/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
204
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/SelfAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
205
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/SelfAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
206
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/SelfAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
207
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/SelfAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
208
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
209
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
210
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
211
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
212
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
213
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
214
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00005-of-00005.h5",
215
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00005-of-00005.h5",
216
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00005-of-00005.h5",
217
+ "tft5_for_conditional_generation_1/decoder/block_._21/layer_._2/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
218
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/SelfAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
219
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/SelfAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
220
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/SelfAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
221
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/SelfAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
222
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
223
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
224
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
225
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
226
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
227
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
228
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00005-of-00005.h5",
229
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00005-of-00005.h5",
230
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00005-of-00005.h5",
231
+ "tft5_for_conditional_generation_1/decoder/block_._22/layer_._2/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
232
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/SelfAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
233
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/SelfAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
234
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/SelfAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
235
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/SelfAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
236
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
237
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
238
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
239
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
240
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
241
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
242
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00005-of-00005.h5",
243
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00005-of-00005.h5",
244
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00005-of-00005.h5",
245
+ "tft5_for_conditional_generation_1/decoder/block_._23/layer_._2/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
246
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
247
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
248
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
249
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
250
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
251
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
252
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
253
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
254
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
255
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
256
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
257
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
258
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
259
+ "tft5_for_conditional_generation_1/decoder/block_._3/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
260
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
261
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
262
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
263
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
264
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
265
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
266
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
267
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
268
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
269
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
270
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
271
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
272
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
273
+ "tft5_for_conditional_generation_1/decoder/block_._4/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
274
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
275
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
276
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
277
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
278
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
279
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
280
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
281
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
282
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
283
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
284
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
285
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
286
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
287
+ "tft5_for_conditional_generation_1/decoder/block_._5/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
288
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
289
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
290
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
291
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
292
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
293
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
294
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
295
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
296
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
297
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
298
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
299
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
300
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
301
+ "tft5_for_conditional_generation_1/decoder/block_._6/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
302
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
303
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
304
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
305
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
306
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
307
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
308
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
309
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
310
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
311
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
312
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
313
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
314
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
315
+ "tft5_for_conditional_generation_1/decoder/block_._7/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
316
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
317
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
318
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
319
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
320
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
321
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
322
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
323
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
324
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
325
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
326
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
327
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
328
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
329
+ "tft5_for_conditional_generation_1/decoder/block_._8/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
330
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
331
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
332
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
333
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
334
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
335
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
336
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
337
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
338
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
339
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
340
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
341
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
342
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
343
+ "tft5_for_conditional_generation_1/decoder/block_._9/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
344
+ "tft5_for_conditional_generation_1/decoder/final_layer_norm/weight:0": "tf_model-00005-of-00005.h5",
345
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
346
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
347
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
348
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/relative_attention_bias/embeddings:0": "tf_model-00001-of-00005.h5",
349
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
350
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
351
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
352
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
353
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
354
+ "tft5_for_conditional_generation_1/encoder/block_._0/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
355
+ "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
356
+ "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
357
+ "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
358
+ "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
359
+ "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
360
+ "tft5_for_conditional_generation_1/encoder/block_._1/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
361
+ "tft5_for_conditional_generation_1/encoder/block_._1/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
362
+ "tft5_for_conditional_generation_1/encoder/block_._1/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
363
+ "tft5_for_conditional_generation_1/encoder/block_._1/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
364
+ "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
365
+ "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
366
+ "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
367
+ "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
368
+ "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
369
+ "tft5_for_conditional_generation_1/encoder/block_._10/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
370
+ "tft5_for_conditional_generation_1/encoder/block_._10/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
371
+ "tft5_for_conditional_generation_1/encoder/block_._10/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
372
+ "tft5_for_conditional_generation_1/encoder/block_._10/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
373
+ "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
374
+ "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
375
+ "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
376
+ "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
377
+ "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
378
+ "tft5_for_conditional_generation_1/encoder/block_._11/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
379
+ "tft5_for_conditional_generation_1/encoder/block_._11/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
380
+ "tft5_for_conditional_generation_1/encoder/block_._11/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
381
+ "tft5_for_conditional_generation_1/encoder/block_._11/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
382
+ "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
383
+ "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
384
+ "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
385
+ "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
386
+ "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
387
+ "tft5_for_conditional_generation_1/encoder/block_._12/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
388
+ "tft5_for_conditional_generation_1/encoder/block_._12/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
389
+ "tft5_for_conditional_generation_1/encoder/block_._12/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
390
+ "tft5_for_conditional_generation_1/encoder/block_._12/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
391
+ "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
392
+ "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
393
+ "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
394
+ "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
395
+ "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
396
+ "tft5_for_conditional_generation_1/encoder/block_._13/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
397
+ "tft5_for_conditional_generation_1/encoder/block_._13/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
398
+ "tft5_for_conditional_generation_1/encoder/block_._13/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
399
+ "tft5_for_conditional_generation_1/encoder/block_._13/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
400
+ "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
401
+ "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
402
+ "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
403
+ "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
404
+ "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
405
+ "tft5_for_conditional_generation_1/encoder/block_._14/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
406
+ "tft5_for_conditional_generation_1/encoder/block_._14/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
407
+ "tft5_for_conditional_generation_1/encoder/block_._14/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
408
+ "tft5_for_conditional_generation_1/encoder/block_._14/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
409
+ "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
410
+ "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
411
+ "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
412
+ "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
413
+ "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
414
+ "tft5_for_conditional_generation_1/encoder/block_._15/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
415
+ "tft5_for_conditional_generation_1/encoder/block_._15/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
416
+ "tft5_for_conditional_generation_1/encoder/block_._15/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
417
+ "tft5_for_conditional_generation_1/encoder/block_._15/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
418
+ "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
419
+ "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
420
+ "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
421
+ "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
422
+ "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
423
+ "tft5_for_conditional_generation_1/encoder/block_._16/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
424
+ "tft5_for_conditional_generation_1/encoder/block_._16/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
425
+ "tft5_for_conditional_generation_1/encoder/block_._16/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
426
+ "tft5_for_conditional_generation_1/encoder/block_._16/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
427
+ "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
428
+ "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
429
+ "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
430
+ "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
431
+ "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
432
+ "tft5_for_conditional_generation_1/encoder/block_._17/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
433
+ "tft5_for_conditional_generation_1/encoder/block_._17/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
434
+ "tft5_for_conditional_generation_1/encoder/block_._17/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
435
+ "tft5_for_conditional_generation_1/encoder/block_._17/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
436
+ "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
437
+ "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
438
+ "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
439
+ "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
440
+ "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
441
+ "tft5_for_conditional_generation_1/encoder/block_._18/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
442
+ "tft5_for_conditional_generation_1/encoder/block_._18/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
443
+ "tft5_for_conditional_generation_1/encoder/block_._18/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
444
+ "tft5_for_conditional_generation_1/encoder/block_._18/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
445
+ "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
446
+ "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
447
+ "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
448
+ "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
449
+ "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
450
+ "tft5_for_conditional_generation_1/encoder/block_._19/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
451
+ "tft5_for_conditional_generation_1/encoder/block_._19/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
452
+ "tft5_for_conditional_generation_1/encoder/block_._19/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
453
+ "tft5_for_conditional_generation_1/encoder/block_._19/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
454
+ "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
455
+ "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
456
+ "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
457
+ "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
458
+ "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
459
+ "tft5_for_conditional_generation_1/encoder/block_._2/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
460
+ "tft5_for_conditional_generation_1/encoder/block_._2/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
461
+ "tft5_for_conditional_generation_1/encoder/block_._2/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
462
+ "tft5_for_conditional_generation_1/encoder/block_._2/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
463
+ "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
464
+ "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
465
+ "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
466
+ "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
467
+ "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
468
+ "tft5_for_conditional_generation_1/encoder/block_._20/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
469
+ "tft5_for_conditional_generation_1/encoder/block_._20/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
470
+ "tft5_for_conditional_generation_1/encoder/block_._20/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
471
+ "tft5_for_conditional_generation_1/encoder/block_._20/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
472
+ "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
473
+ "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
474
+ "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
475
+ "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
476
+ "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
477
+ "tft5_for_conditional_generation_1/encoder/block_._21/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
478
+ "tft5_for_conditional_generation_1/encoder/block_._21/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
479
+ "tft5_for_conditional_generation_1/encoder/block_._21/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
480
+ "tft5_for_conditional_generation_1/encoder/block_._21/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
481
+ "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
482
+ "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
483
+ "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
484
+ "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
485
+ "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
486
+ "tft5_for_conditional_generation_1/encoder/block_._22/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
487
+ "tft5_for_conditional_generation_1/encoder/block_._22/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
488
+ "tft5_for_conditional_generation_1/encoder/block_._22/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
489
+ "tft5_for_conditional_generation_1/encoder/block_._22/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
490
+ "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
491
+ "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
492
+ "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
493
+ "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
494
+ "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
495
+ "tft5_for_conditional_generation_1/encoder/block_._23/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
496
+ "tft5_for_conditional_generation_1/encoder/block_._23/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
497
+ "tft5_for_conditional_generation_1/encoder/block_._23/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
498
+ "tft5_for_conditional_generation_1/encoder/block_._23/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
499
+ "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
500
+ "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
501
+ "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
502
+ "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
503
+ "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
504
+ "tft5_for_conditional_generation_1/encoder/block_._3/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
505
+ "tft5_for_conditional_generation_1/encoder/block_._3/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
506
+ "tft5_for_conditional_generation_1/encoder/block_._3/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
507
+ "tft5_for_conditional_generation_1/encoder/block_._3/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
508
+ "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
509
+ "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
510
+ "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
511
+ "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
512
+ "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
513
+ "tft5_for_conditional_generation_1/encoder/block_._4/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
514
+ "tft5_for_conditional_generation_1/encoder/block_._4/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
515
+ "tft5_for_conditional_generation_1/encoder/block_._4/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
516
+ "tft5_for_conditional_generation_1/encoder/block_._4/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
517
+ "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
518
+ "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
519
+ "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
520
+ "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
521
+ "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
522
+ "tft5_for_conditional_generation_1/encoder/block_._5/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
523
+ "tft5_for_conditional_generation_1/encoder/block_._5/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
524
+ "tft5_for_conditional_generation_1/encoder/block_._5/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
525
+ "tft5_for_conditional_generation_1/encoder/block_._5/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
526
+ "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
527
+ "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
528
+ "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
529
+ "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
530
+ "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
531
+ "tft5_for_conditional_generation_1/encoder/block_._6/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
532
+ "tft5_for_conditional_generation_1/encoder/block_._6/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
533
+ "tft5_for_conditional_generation_1/encoder/block_._6/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
534
+ "tft5_for_conditional_generation_1/encoder/block_._6/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
535
+ "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
536
+ "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
537
+ "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
538
+ "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
539
+ "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
540
+ "tft5_for_conditional_generation_1/encoder/block_._7/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
541
+ "tft5_for_conditional_generation_1/encoder/block_._7/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
542
+ "tft5_for_conditional_generation_1/encoder/block_._7/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
543
+ "tft5_for_conditional_generation_1/encoder/block_._7/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
544
+ "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
545
+ "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
546
+ "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
547
+ "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
548
+ "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
549
+ "tft5_for_conditional_generation_1/encoder/block_._8/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
550
+ "tft5_for_conditional_generation_1/encoder/block_._8/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
551
+ "tft5_for_conditional_generation_1/encoder/block_._8/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
552
+ "tft5_for_conditional_generation_1/encoder/block_._8/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
553
+ "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
554
+ "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
555
+ "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
556
+ "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
557
+ "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
558
+ "tft5_for_conditional_generation_1/encoder/block_._9/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
559
+ "tft5_for_conditional_generation_1/encoder/block_._9/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
560
+ "tft5_for_conditional_generation_1/encoder/block_._9/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
561
+ "tft5_for_conditional_generation_1/encoder/block_._9/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
562
+ "tft5_for_conditional_generation_1/encoder/final_layer_norm/weight:0": "tf_model-00002-of-00005.h5",
563
+ "tft5_for_conditional_generation_1/lm_head/kernel:0": "tf_model-00005-of-00005.h5"
564
+ }
565
+ }