Upload TFT5ForConditionalGeneration

Browse files

Files changed (7) hide show

README.md +26 -289
tf_model-00001-of-00005.h5 +3 -0
tf_model-00002-of-00005.h5 +3 -0
tf_model-00003-of-00005.h5 +3 -0
tf_model-00004-of-00005.h5 +3 -0
tf_model-00005-of-00005.h5 +3 -0
tf_model.h5.index.json +565 -0

README.md CHANGED Viewed

@@ -1,310 +1,47 @@
 ---
-language:
-- en
-- sp
-- ja
-- pe
-- hi
-- fr
-- ch
-- be
-- gu
-- ge
-- te
-- it
-- ar
-- po
-- ta
-- ma
-- ma
-- or
-- pa
-- po
-- ur
-- ga
-- he
-- ko
-- ca
-- th
-- du
-- in
-- vi
-- bu
-- fi
-- ce
-- la
-- tu
-- ru
-- cr
-- sw
-- yo
-- ku
-- bu
-- ma
-- cz
-- fi
-- so
-- ta
-- sw
-- si
-- ka
-- zh
-- ig
-- xh
-- ro
-- ha
-- es
-- sl
-- li
-- gr
-- ne
-- as
-- no
 tags:
-- text2text-generation
-datasets:
-- svakulenk0/qrecc
-- taskmaster2
-- djaym7/wiki_dialog
-- deepmind/code_contests
-- lambada
-- gsm8k
-- aqua_rat
-- esnli
-- quasc
-- qed
-license: apache-2.0
 ---
-# Model Card for FLAN-T5 large
-![model image](https://s3.amazonaws.com/moonup/production/uploads/1666363435475-62441d1d9fdefb55a0b7d12c.png)
-#  Table of Contents
-0. [TL;DR](#TL;DR)
-1. [Model Details](#model-details)
-2. [Usage](#usage)
-3. [Uses](#uses)
-4. [Bias, Risks, and Limitations](#bias-risks-and-limitations)
-5. [Training Details](#training-details)
-6. [Evaluation](#evaluation)
-7. [Environmental Impact](#environmental-impact)
-8. [Citation](#citation)
-# TL;DR
-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.
-As mentioned in the first few lines of the abstract :
->  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.
-**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).
-# Model Details
-## Model Description
-- **Model type:** Language model
-- **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
-- **License:** Apache 2.0
-- **Related Models:** [All FLAN-T5 Checkpoints](https://huggingface.co/models?search=flan-t5)
-- **Original Checkpoints:** [All Original FLAN-T5 Checkpoints](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-t5-checkpoints)
-- **Resources for more information:**
-  - [Research paper](https://arxiv.org/pdf/2210.11416.pdf)
-  - [GitHub Repo](https://github.com/google-research/t5x)
-  - [Hugging Face FLAN-T5 Docs (Similar to T5) ](https://huggingface.co/docs/transformers/model_doc/t5)
-# Usage
-Find below some example scripts on how to use the model in `transformers`:
-## Using the Pytorch model
-### Running the model on a CPU
-<details>
-<summary> Click to expand </summary>
-```python
-from transformers import T5Tokenizer, T5ForConditionalGeneration
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large")
-input_text = "translate English to German: How old are you?"
-input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids
-outputs = model.generate(input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-</details>
-### Running the model on a GPU
-<details>
-<summary> Click to expand </summary>
-```python
-# pip install accelerate
-from transformers import T5Tokenizer, T5ForConditionalGeneration
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto")
-input_text = "translate English to German: How old are you?"
-input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids.to("cuda")
-outputs = model.generate(input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-</details>
-### Running the model on a GPU using different precisions
-#### FP16
-<details>
-<summary> Click to expand </summary>
-```python
-# pip install accelerate
-import torch
-from transformers import T5Tokenizer, T5ForConditionalGeneration
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto", torch_dtype=torch.float16)
-input_text = "translate English to German: How old are you?"
-input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids.to("cuda")
-outputs = model.generate(input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-</details>
-#### INT8
-<details>
-<summary> Click to expand </summary>
-```python
-# pip install bitsandbytes accelerate
-from transformers import T5Tokenizer, T5ForConditionalGeneration
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto", load_in_8bit=True)
-input_text = "translate English to German: How old are you?"
-input_ids = tokenizer.encode(input_text, return_tensors="pt").input_ids.to("cuda")
-outputs = model.generate(input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-</details>
-# Uses
-## Direct Use and Downstream Use
-The authors write in [the original paper's model card](https://arxiv.org/pdf/2210.11416.pdf) that:
-> 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
-See the [research paper](https://arxiv.org/pdf/2210.11416.pdf) for further details.
-## Out-of-Scope Use
-More information needed.
-# Bias, Risks, and Limitations
-The information below in this section are copied from the model's [official model card](https://arxiv.org/pdf/2210.11416.pdf):
-> 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.
-## Ethical considerations and risks
-> 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.
-## Known Limitations
-> Flan-T5 has not been tested in real world applications.
-## Sensitive Use:
-> Flan-T5 should not be applied for any unacceptable use cases, e.g., generation of abusive speech.
-# Training Details
-## Training Data
-The model was trained on a mixture of tasks, that includes the tasks described in the table below (from the original paper, figure 2):
-![table.png](https://s3.amazonaws.com/moonup/production/uploads/1666363265279-62441d1d9fdefb55a0b7d12c.png)
-## Training Procedure
-According to the model card from the [original paper](https://arxiv.org/pdf/2210.11416.pdf):
-> 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.
-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).
-# Evaluation
-## Testing Data, Factors & Metrics
-The authors evaluated the model on various tasks covering several languages (1836 in total). See the table below for some quantitative evaluation:
-![image.png](https://s3.amazonaws.com/moonup/production/uploads/1666361983550-62441d1d9fdefb55a0b7d12c.png)
-For full details, please check the [research paper](https://arxiv.org/pdf/2210.11416.pdf).
-## Results
-For full results for FLAN-T5-Large, see the [research paper](https://arxiv.org/pdf/2210.11416.pdf), Table 3.
-# Environmental Impact
-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).
-- **Hardware Type:** Google Cloud TPU Pods - TPU v3 or TPU v4  | Number of chips ≥ 4.
-- **Hours used:** More information needed
-- **Cloud Provider:** GCP
-- **Compute Region:** More information needed
-- **Carbon Emitted:** More information needed
-# Citation
-**BibTeX:**
-```bibtex
-@misc{https://doi.org/10.48550/arxiv.2210.11416,
-  doi = {10.48550/ARXIV.2210.11416},
-  url = {https://arxiv.org/abs/2210.11416},
-  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},
-  keywords = {Machine Learning (cs.LG), Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
-  title = {Scaling Instruction-Finetuned Language Models},
-  publisher = {arXiv},
-  year = {2022},
-  copyright = {Creative Commons Attribution 4.0 International}
-}
-```

 ---
 tags:
+- generated_from_keras_callback
+model-index:
+- name: t5-xxl
+  results: []
 ---
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+# t5-xxl
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- optimizer: None
+- training_precision: float32
+### Training results
+### Framework versions
+- Transformers 4.24.0.dev0
+- TensorFlow 2.10.0
+- Datasets 2.6.1
+- Tokenizers 0.13.1

tf_model-00001-of-00005.h5 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9b26cdb4f6a728ad7d7ac8ab74100ceb9988f27119a4c58e96c781baa9cb9f6a
+size 9989362864

tf_model-00002-of-00005.h5 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f22f1007bc7f7df18cd01258ca980ed570f3ef9c0d0d2e7dfaf214693e92b28c
+size 9932810536

tf_model-00003-of-00005.h5 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f8c1b2e49c147718deeaf0562bc46f9ca1bca52e38f66fe25c6271a67c3b92b
+size 9999968760

tf_model-00004-of-00005.h5 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0096154c641dba8fdc3d87fabbdf2346693b45d81711ca9913a13b4734c44540
+size 9999964640

tf_model-00005-of-00005.h5 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:020b93b1bb89dbbdf61fec1184c342e78ec06294c52708efda40a7fee0edbae8
+size 4620350264

tf_model.h5.index.json ADDED Viewed

	@@ -0,0 +1,565 @@

+{
+  "metadata": {
+    "total_size": 44541329408
+  },
+  "weight_map": {
+    "shared/shared/embeddings:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/relative_attention_bias/embeddings:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._0/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._1/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._10/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._11/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._12/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._13/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._14/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._15/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._16/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._17/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._18/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/SelfAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/SelfAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/SelfAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._0/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._1/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._19/layer_._2/layer_norm/weight:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._2/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/SelfAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/SelfAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/SelfAttention/q/kernel:0": "tf_model-00004-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/SelfAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._0/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._1/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._20/layer_._2/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/SelfAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/SelfAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/SelfAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/SelfAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._0/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._1/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._21/layer_._2/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/SelfAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/SelfAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/SelfAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/SelfAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._0/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._1/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._22/layer_._2/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/SelfAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/SelfAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/SelfAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/SelfAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._0/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._1/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._23/layer_._2/layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._3/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._4/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._5/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._6/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._7/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._8/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/SelfAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/SelfAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/SelfAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/SelfAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._0/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/EncDecAttention/k/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/EncDecAttention/o/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/EncDecAttention/q/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/EncDecAttention/v/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._1/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._2/DenseReluDense/wi_0/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._2/DenseReluDense/wi_1/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._2/DenseReluDense/wo/kernel:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/block_._9/layer_._2/layer_norm/weight:0": "tf_model-00003-of-00005.h5",
+    "tft5_for_conditional_generation_1/decoder/final_layer_norm/weight:0": "tf_model-00005-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/relative_attention_bias/embeddings:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._0/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._1/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._1/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._1/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._1/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._1/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._10/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._10/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._10/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._10/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._10/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._11/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._11/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._11/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._11/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._11/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._12/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._12/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._12/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._12/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._12/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._13/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._13/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._13/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._13/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._13/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._14/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._14/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._14/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._14/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._14/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._15/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._15/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._15/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._15/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._15/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._16/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._16/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._16/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._16/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._16/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._17/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._17/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._17/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._17/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._17/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._18/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._18/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._18/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._18/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._18/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._19/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._19/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._19/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._19/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._19/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._2/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._2/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._2/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._2/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._2/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._20/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._20/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._20/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._20/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._20/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._21/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._21/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._21/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._21/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._21/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._22/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._22/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._22/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._22/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._22/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/SelfAttention/k/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/SelfAttention/o/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/SelfAttention/q/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/SelfAttention/v/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._23/layer_._0/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._23/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._23/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._23/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._23/layer_._1/layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._3/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._3/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._3/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._3/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._3/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._4/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._4/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._4/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._4/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._4/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._5/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._5/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._5/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._5/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._5/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._6/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._6/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._6/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._6/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._6/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._7/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._7/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._7/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._7/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._7/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._8/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._8/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._8/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._8/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._8/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/SelfAttention/k/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/SelfAttention/o/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/SelfAttention/q/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/SelfAttention/v/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._9/layer_._0/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._9/layer_._1/DenseReluDense/wi_0/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._9/layer_._1/DenseReluDense/wi_1/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._9/layer_._1/DenseReluDense/wo/kernel:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/block_._9/layer_._1/layer_norm/weight:0": "tf_model-00001-of-00005.h5",
+    "tft5_for_conditional_generation_1/encoder/final_layer_norm/weight:0": "tf_model-00002-of-00005.h5",
+    "tft5_for_conditional_generation_1/lm_head/kernel:0": "tf_model-00005-of-00005.h5"
+  }
+}