Instructions to use zeromodels/t5_11b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasFormers
How to use zeromodels/t5_11b with KerasFormers:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Keras
How to use zeromodels/t5_11b with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://zeromodels/t5_11b") - Notebooks
- Google Colab
- Kaggle
Commit ·
bf4d254
0
Parent(s):
Super-squash branch 'main' using huggingface_hub
Browse files- .gitattributes +35 -0
- README.md +73 -0
- kf_config.json +29 -0
- model.weights.json +516 -0
- model_00000.weights.h5 +3 -0
- model_00001.weights.h5 +3 -0
- model_00002.weights.h5 +3 -0
- model_00003.weights.h5 +3 -0
- model_00004.weights.h5 +3 -0
- model_00005.weights.h5 +3 -0
- model_00006.weights.h5 +3 -0
- model_00007.weights.h5 +3 -0
- model_00008.weights.h5 +3 -0
- tokenizer.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: translation
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: google-t5/t5-11b
|
| 5 |
+
library_name: kerasformers
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
- fr
|
| 9 |
+
- de
|
| 10 |
+
- ro
|
| 11 |
+
tags:
|
| 12 |
+
- keras
|
| 13 |
+
- kerasformers
|
| 14 |
+
- t5
|
| 15 |
+
- text2text-generation
|
| 16 |
+
- pytorch
|
| 17 |
+
- jax
|
| 18 |
+
- tf
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
# T5-11b in Keras 3: JAX, PyTorch, or TensorFlow
|
| 22 |
+
|
| 23 |
+
[](https://github.com/IMvision12/KerasFormers) [](https://imvision12.github.io/KerasFormers/t5/) [](https://huggingface.co/collections/kerasformers/t5-6a85056935f438653698c56f)
|
| 24 |
+
|
| 25 |
+
# kerasformers/t5_11b
|
| 26 |
+
|
| 27 |
+
Pure-**Keras 3** conversion of [`google-t5/t5-11b`](https://huggingface.co/google-t5/t5-11b) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**, bit-exact with the Hugging Face original. T5 is a text-to-text encoder-decoder; this repo hosts the full backbone (`kf_config.json` declares `T5Model`), and every T5 class (`T5ConditionalGenerate`, `T5EncoderModel`, and the classification / QA heads) loads its subset from the one `model.weights.h5`.
|
| 28 |
+
|
| 29 |
+
For model details, license, and usage terms, see the upstream [model card](https://huggingface.co/google-t5/t5-11b).
|
| 30 |
+
|
| 31 |
+
Paper: [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://arxiv.org/abs/1910.10683)
|
| 32 |
+
|
| 33 |
+
## Quick start
|
| 34 |
+
|
| 35 |
+
```python
|
| 36 |
+
import os
|
| 37 |
+
os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow"
|
| 38 |
+
|
| 39 |
+
from kerasformers.models.t5 import T5ConditionalGenerate, T5Tokenizer
|
| 40 |
+
|
| 41 |
+
model = T5ConditionalGenerate.from_weights("kerasformers/t5_11b")
|
| 42 |
+
tokenizer = T5Tokenizer.from_weights("kerasformers/t5_11b")
|
| 43 |
+
|
| 44 |
+
inputs = tokenizer("translate English to German: The house is wonderful.")
|
| 45 |
+
output_ids = model.generate(
|
| 46 |
+
inputs["input_ids"], inputs["attention_mask"], max_new_tokens=40
|
| 47 |
+
)
|
| 48 |
+
print(tokenizer.decode(output_ids[0]))
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
Load any T5 variant the same way with `from_weights("kerasformers/<variant>")`. Browse them all in the [T5 collection](https://huggingface.co/collections/kerasformers/t5-6a85056935f438653698c56f).
|
| 52 |
+
|
| 53 |
+
## Available classes
|
| 54 |
+
|
| 55 |
+
Load any of these from this repo with `from_weights("kerasformers/t5_11b")` (or on the fly via the `hf:` prefix). The pretrained backbone is shared; task heads not stored in this checkpoint start randomly initialized, ready for fine-tuning (or load a `hf:` fine-tune).
|
| 56 |
+
|
| 57 |
+
| Class | Task |
|
| 58 |
+
|---|---|
|
| 59 |
+
| `T5Model` | Encoder backbone |
|
| 60 |
+
| `T5ConditionalGenerate` | Text-to-text generation |
|
| 61 |
+
| `T5EncoderModel` | Encoder-only features |
|
| 62 |
+
| `T5SequenceClassify` | Sequence classification |
|
| 63 |
+
| `T5TokenClassify` | Token classification (NER / POS) |
|
| 64 |
+
| `T5QnA` | Extractive question answering |
|
| 65 |
+
|
| 66 |
+
```python
|
| 67 |
+
from kerasformers.models.t5 import T5SequenceClassify
|
| 68 |
+
model = T5SequenceClassify.from_weights("kerasformers/t5_11b")
|
| 69 |
+
```
|
| 70 |
+
|
| 71 |
+
## Special Thanks
|
| 72 |
+
|
| 73 |
+
Thank you to the Google T5 team for creating and releasing the T5 models.
|
kf_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "kerasformers",
|
| 3 |
+
"kerasformers_version": "1.2.4",
|
| 4 |
+
"model_module": "kerasformers.models.t5",
|
| 5 |
+
"model_class": "T5Model",
|
| 6 |
+
"variant": "t5_11b",
|
| 7 |
+
"weights": "model.weights.json",
|
| 8 |
+
"schema_version": 2,
|
| 9 |
+
"weight_dtype": "float32",
|
| 10 |
+
"model_type": "t5",
|
| 11 |
+
"text_config": {
|
| 12 |
+
"vocab_size": 32128,
|
| 13 |
+
"embed_dim": 1024,
|
| 14 |
+
"key_value_dim": 128,
|
| 15 |
+
"mlp_dim": 65536,
|
| 16 |
+
"num_layers": 24,
|
| 17 |
+
"num_decoder_layers": 24,
|
| 18 |
+
"num_heads": 128,
|
| 19 |
+
"relative_attention_num_buckets": 32,
|
| 20 |
+
"relative_attention_max_distance": 128,
|
| 21 |
+
"hidden_act": "relu",
|
| 22 |
+
"layer_norm_eps": 1e-06,
|
| 23 |
+
"dropout": 0.1,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"eos_token_id": 1,
|
| 27 |
+
"decoder_start_token_id": 0
|
| 28 |
+
}
|
| 29 |
+
}
|
model.weights.json
ADDED
|
@@ -0,0 +1,516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 45229285376.0
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"/layers/embedding/vars": "model_00000.weights.h5",
|
| 7 |
+
"/layers/t5_position_bias/rel_bias/vars": "model_00000.weights.h5",
|
| 8 |
+
"/layers/t5_encoder_block/ff/layer_norm/vars": "model_00000.weights.h5",
|
| 9 |
+
"/layers/t5_encoder_block/ff/wi/vars": "model_00000.weights.h5",
|
| 10 |
+
"/layers/t5_encoder_block/ff/wo/vars": "model_00000.weights.h5",
|
| 11 |
+
"/layers/t5_encoder_block/self_attention/attention/k/vars": "model_00000.weights.h5",
|
| 12 |
+
"/layers/t5_encoder_block/self_attention/attention/o/vars": "model_00000.weights.h5",
|
| 13 |
+
"/layers/t5_encoder_block/self_attention/attention/q/vars": "model_00000.weights.h5",
|
| 14 |
+
"/layers/t5_encoder_block/self_attention/attention/v/vars": "model_00000.weights.h5",
|
| 15 |
+
"/layers/t5_encoder_block/self_attention/layer_norm/vars": "model_00000.weights.h5",
|
| 16 |
+
"/layers/t5_encoder_block_1/ff/layer_norm/vars": "model_00000.weights.h5",
|
| 17 |
+
"/layers/t5_encoder_block_1/ff/wi/vars": "model_00000.weights.h5",
|
| 18 |
+
"/layers/t5_encoder_block_1/ff/wo/vars": "model_00000.weights.h5",
|
| 19 |
+
"/layers/t5_encoder_block_1/self_attention/attention/k/vars": "model_00000.weights.h5",
|
| 20 |
+
"/layers/t5_encoder_block_1/self_attention/attention/o/vars": "model_00000.weights.h5",
|
| 21 |
+
"/layers/t5_encoder_block_1/self_attention/attention/q/vars": "model_00000.weights.h5",
|
| 22 |
+
"/layers/t5_encoder_block_1/self_attention/attention/v/vars": "model_00000.weights.h5",
|
| 23 |
+
"/layers/t5_encoder_block_1/self_attention/layer_norm/vars": "model_00000.weights.h5",
|
| 24 |
+
"/layers/t5_encoder_block_2/ff/layer_norm/vars": "model_00000.weights.h5",
|
| 25 |
+
"/layers/t5_encoder_block_2/ff/wi/vars": "model_00000.weights.h5",
|
| 26 |
+
"/layers/t5_encoder_block_2/ff/wo/vars": "model_00000.weights.h5",
|
| 27 |
+
"/layers/t5_encoder_block_2/self_attention/attention/k/vars": "model_00000.weights.h5",
|
| 28 |
+
"/layers/t5_encoder_block_2/self_attention/attention/o/vars": "model_00000.weights.h5",
|
| 29 |
+
"/layers/t5_encoder_block_2/self_attention/attention/q/vars": "model_00000.weights.h5",
|
| 30 |
+
"/layers/t5_encoder_block_2/self_attention/attention/v/vars": "model_00000.weights.h5",
|
| 31 |
+
"/layers/t5_encoder_block_2/self_attention/layer_norm/vars": "model_00000.weights.h5",
|
| 32 |
+
"/layers/t5_encoder_block_3/ff/layer_norm/vars": "model_00000.weights.h5",
|
| 33 |
+
"/layers/t5_encoder_block_3/ff/wi/vars": "model_00000.weights.h5",
|
| 34 |
+
"/layers/t5_encoder_block_3/ff/wo/vars": "model_00000.weights.h5",
|
| 35 |
+
"/layers/t5_encoder_block_3/self_attention/attention/k/vars": "model_00000.weights.h5",
|
| 36 |
+
"/layers/t5_encoder_block_3/self_attention/attention/o/vars": "model_00000.weights.h5",
|
| 37 |
+
"/layers/t5_encoder_block_3/self_attention/attention/q/vars": "model_00000.weights.h5",
|
| 38 |
+
"/layers/t5_encoder_block_3/self_attention/attention/v/vars": "model_00000.weights.h5",
|
| 39 |
+
"/layers/t5_encoder_block_3/self_attention/layer_norm/vars": "model_00000.weights.h5",
|
| 40 |
+
"/layers/t5_encoder_block_4/ff/layer_norm/vars": "model_00000.weights.h5",
|
| 41 |
+
"/layers/t5_encoder_block_4/ff/wi/vars": "model_00000.weights.h5",
|
| 42 |
+
"/layers/t5_encoder_block_4/ff/wo/vars": "model_00000.weights.h5",
|
| 43 |
+
"/layers/t5_encoder_block_4/self_attention/attention/k/vars": "model_00000.weights.h5",
|
| 44 |
+
"/layers/t5_encoder_block_4/self_attention/attention/o/vars": "model_00000.weights.h5",
|
| 45 |
+
"/layers/t5_encoder_block_4/self_attention/attention/q/vars": "model_00000.weights.h5",
|
| 46 |
+
"/layers/t5_encoder_block_4/self_attention/attention/v/vars": "model_00000.weights.h5",
|
| 47 |
+
"/layers/t5_encoder_block_4/self_attention/layer_norm/vars": "model_00000.weights.h5",
|
| 48 |
+
"/layers/t5_encoder_block_5/ff/layer_norm/vars": "model_00000.weights.h5",
|
| 49 |
+
"/layers/t5_encoder_block_5/ff/wi/vars": "model_00000.weights.h5",
|
| 50 |
+
"/layers/t5_encoder_block_5/ff/wo/vars": "model_00000.weights.h5",
|
| 51 |
+
"/layers/t5_encoder_block_5/self_attention/attention/k/vars": "model_00000.weights.h5",
|
| 52 |
+
"/layers/t5_encoder_block_5/self_attention/attention/o/vars": "model_00000.weights.h5",
|
| 53 |
+
"/layers/t5_encoder_block_5/self_attention/attention/q/vars": "model_00000.weights.h5",
|
| 54 |
+
"/layers/t5_encoder_block_5/self_attention/attention/v/vars": "model_00000.weights.h5",
|
| 55 |
+
"/layers/t5_encoder_block_5/self_attention/layer_norm/vars": "model_00000.weights.h5",
|
| 56 |
+
"/layers/t5_encoder_block_6/ff/layer_norm/vars": "model_00000.weights.h5",
|
| 57 |
+
"/layers/t5_encoder_block_6/ff/wi/vars": "model_00000.weights.h5",
|
| 58 |
+
"/layers/t5_encoder_block_6/ff/wo/vars": "model_00001.weights.h5",
|
| 59 |
+
"/layers/t5_encoder_block_6/self_attention/attention/k/vars": "model_00001.weights.h5",
|
| 60 |
+
"/layers/t5_encoder_block_6/self_attention/attention/o/vars": "model_00001.weights.h5",
|
| 61 |
+
"/layers/t5_encoder_block_6/self_attention/attention/q/vars": "model_00001.weights.h5",
|
| 62 |
+
"/layers/t5_encoder_block_6/self_attention/attention/v/vars": "model_00001.weights.h5",
|
| 63 |
+
"/layers/t5_encoder_block_6/self_attention/layer_norm/vars": "model_00001.weights.h5",
|
| 64 |
+
"/layers/t5_encoder_block_7/ff/layer_norm/vars": "model_00001.weights.h5",
|
| 65 |
+
"/layers/t5_encoder_block_7/ff/wi/vars": "model_00001.weights.h5",
|
| 66 |
+
"/layers/t5_encoder_block_7/ff/wo/vars": "model_00001.weights.h5",
|
| 67 |
+
"/layers/t5_encoder_block_7/self_attention/attention/k/vars": "model_00001.weights.h5",
|
| 68 |
+
"/layers/t5_encoder_block_7/self_attention/attention/o/vars": "model_00001.weights.h5",
|
| 69 |
+
"/layers/t5_encoder_block_7/self_attention/attention/q/vars": "model_00001.weights.h5",
|
| 70 |
+
"/layers/t5_encoder_block_7/self_attention/attention/v/vars": "model_00001.weights.h5",
|
| 71 |
+
"/layers/t5_encoder_block_7/self_attention/layer_norm/vars": "model_00001.weights.h5",
|
| 72 |
+
"/layers/t5_encoder_block_8/ff/layer_norm/vars": "model_00001.weights.h5",
|
| 73 |
+
"/layers/t5_encoder_block_8/ff/wi/vars": "model_00001.weights.h5",
|
| 74 |
+
"/layers/t5_encoder_block_8/ff/wo/vars": "model_00001.weights.h5",
|
| 75 |
+
"/layers/t5_encoder_block_8/self_attention/attention/k/vars": "model_00001.weights.h5",
|
| 76 |
+
"/layers/t5_encoder_block_8/self_attention/attention/o/vars": "model_00001.weights.h5",
|
| 77 |
+
"/layers/t5_encoder_block_8/self_attention/attention/q/vars": "model_00001.weights.h5",
|
| 78 |
+
"/layers/t5_encoder_block_8/self_attention/attention/v/vars": "model_00001.weights.h5",
|
| 79 |
+
"/layers/t5_encoder_block_8/self_attention/layer_norm/vars": "model_00001.weights.h5",
|
| 80 |
+
"/layers/t5_encoder_block_9/ff/layer_norm/vars": "model_00001.weights.h5",
|
| 81 |
+
"/layers/t5_encoder_block_9/ff/wi/vars": "model_00001.weights.h5",
|
| 82 |
+
"/layers/t5_encoder_block_9/ff/wo/vars": "model_00001.weights.h5",
|
| 83 |
+
"/layers/t5_encoder_block_9/self_attention/attention/k/vars": "model_00001.weights.h5",
|
| 84 |
+
"/layers/t5_encoder_block_9/self_attention/attention/o/vars": "model_00001.weights.h5",
|
| 85 |
+
"/layers/t5_encoder_block_9/self_attention/attention/q/vars": "model_00001.weights.h5",
|
| 86 |
+
"/layers/t5_encoder_block_9/self_attention/attention/v/vars": "model_00001.weights.h5",
|
| 87 |
+
"/layers/t5_encoder_block_9/self_attention/layer_norm/vars": "model_00001.weights.h5",
|
| 88 |
+
"/layers/t5_encoder_block_10/ff/layer_norm/vars": "model_00001.weights.h5",
|
| 89 |
+
"/layers/t5_encoder_block_10/ff/wi/vars": "model_00001.weights.h5",
|
| 90 |
+
"/layers/t5_encoder_block_10/ff/wo/vars": "model_00001.weights.h5",
|
| 91 |
+
"/layers/t5_encoder_block_10/self_attention/attention/k/vars": "model_00001.weights.h5",
|
| 92 |
+
"/layers/t5_encoder_block_10/self_attention/attention/o/vars": "model_00001.weights.h5",
|
| 93 |
+
"/layers/t5_encoder_block_10/self_attention/attention/q/vars": "model_00001.weights.h5",
|
| 94 |
+
"/layers/t5_encoder_block_10/self_attention/attention/v/vars": "model_00001.weights.h5",
|
| 95 |
+
"/layers/t5_encoder_block_10/self_attention/layer_norm/vars": "model_00001.weights.h5",
|
| 96 |
+
"/layers/t5_encoder_block_11/ff/layer_norm/vars": "model_00001.weights.h5",
|
| 97 |
+
"/layers/t5_encoder_block_11/ff/wi/vars": "model_00001.weights.h5",
|
| 98 |
+
"/layers/t5_encoder_block_11/ff/wo/vars": "model_00001.weights.h5",
|
| 99 |
+
"/layers/t5_encoder_block_11/self_attention/attention/k/vars": "model_00001.weights.h5",
|
| 100 |
+
"/layers/t5_encoder_block_11/self_attention/attention/o/vars": "model_00001.weights.h5",
|
| 101 |
+
"/layers/t5_encoder_block_11/self_attention/attention/q/vars": "model_00001.weights.h5",
|
| 102 |
+
"/layers/t5_encoder_block_11/self_attention/attention/v/vars": "model_00001.weights.h5",
|
| 103 |
+
"/layers/t5_encoder_block_11/self_attention/layer_norm/vars": "model_00001.weights.h5",
|
| 104 |
+
"/layers/t5_encoder_block_12/ff/layer_norm/vars": "model_00001.weights.h5",
|
| 105 |
+
"/layers/t5_encoder_block_12/ff/wi/vars": "model_00001.weights.h5",
|
| 106 |
+
"/layers/t5_encoder_block_12/ff/wo/vars": "model_00001.weights.h5",
|
| 107 |
+
"/layers/t5_encoder_block_12/self_attention/attention/k/vars": "model_00001.weights.h5",
|
| 108 |
+
"/layers/t5_encoder_block_12/self_attention/attention/o/vars": "model_00001.weights.h5",
|
| 109 |
+
"/layers/t5_encoder_block_12/self_attention/attention/q/vars": "model_00001.weights.h5",
|
| 110 |
+
"/layers/t5_encoder_block_12/self_attention/attention/v/vars": "model_00002.weights.h5",
|
| 111 |
+
"/layers/t5_encoder_block_12/self_attention/layer_norm/vars": "model_00002.weights.h5",
|
| 112 |
+
"/layers/t5_encoder_block_13/ff/layer_norm/vars": "model_00002.weights.h5",
|
| 113 |
+
"/layers/t5_encoder_block_13/ff/wi/vars": "model_00002.weights.h5",
|
| 114 |
+
"/layers/t5_encoder_block_13/ff/wo/vars": "model_00002.weights.h5",
|
| 115 |
+
"/layers/t5_encoder_block_13/self_attention/attention/k/vars": "model_00002.weights.h5",
|
| 116 |
+
"/layers/t5_encoder_block_13/self_attention/attention/o/vars": "model_00002.weights.h5",
|
| 117 |
+
"/layers/t5_encoder_block_13/self_attention/attention/q/vars": "model_00002.weights.h5",
|
| 118 |
+
"/layers/t5_encoder_block_13/self_attention/attention/v/vars": "model_00002.weights.h5",
|
| 119 |
+
"/layers/t5_encoder_block_13/self_attention/layer_norm/vars": "model_00002.weights.h5",
|
| 120 |
+
"/layers/t5_encoder_block_14/ff/layer_norm/vars": "model_00002.weights.h5",
|
| 121 |
+
"/layers/t5_encoder_block_14/ff/wi/vars": "model_00002.weights.h5",
|
| 122 |
+
"/layers/t5_encoder_block_14/ff/wo/vars": "model_00002.weights.h5",
|
| 123 |
+
"/layers/t5_encoder_block_14/self_attention/attention/k/vars": "model_00002.weights.h5",
|
| 124 |
+
"/layers/t5_encoder_block_14/self_attention/attention/o/vars": "model_00002.weights.h5",
|
| 125 |
+
"/layers/t5_encoder_block_14/self_attention/attention/q/vars": "model_00002.weights.h5",
|
| 126 |
+
"/layers/t5_encoder_block_14/self_attention/attention/v/vars": "model_00002.weights.h5",
|
| 127 |
+
"/layers/t5_encoder_block_14/self_attention/layer_norm/vars": "model_00002.weights.h5",
|
| 128 |
+
"/layers/t5_encoder_block_15/ff/layer_norm/vars": "model_00002.weights.h5",
|
| 129 |
+
"/layers/t5_encoder_block_15/ff/wi/vars": "model_00002.weights.h5",
|
| 130 |
+
"/layers/t5_encoder_block_15/ff/wo/vars": "model_00002.weights.h5",
|
| 131 |
+
"/layers/t5_encoder_block_15/self_attention/attention/k/vars": "model_00002.weights.h5",
|
| 132 |
+
"/layers/t5_encoder_block_15/self_attention/attention/o/vars": "model_00002.weights.h5",
|
| 133 |
+
"/layers/t5_encoder_block_15/self_attention/attention/q/vars": "model_00002.weights.h5",
|
| 134 |
+
"/layers/t5_encoder_block_15/self_attention/attention/v/vars": "model_00002.weights.h5",
|
| 135 |
+
"/layers/t5_encoder_block_15/self_attention/layer_norm/vars": "model_00002.weights.h5",
|
| 136 |
+
"/layers/t5_encoder_block_16/ff/layer_norm/vars": "model_00002.weights.h5",
|
| 137 |
+
"/layers/t5_encoder_block_16/ff/wi/vars": "model_00002.weights.h5",
|
| 138 |
+
"/layers/t5_encoder_block_16/ff/wo/vars": "model_00002.weights.h5",
|
| 139 |
+
"/layers/t5_encoder_block_16/self_attention/attention/k/vars": "model_00002.weights.h5",
|
| 140 |
+
"/layers/t5_encoder_block_16/self_attention/attention/o/vars": "model_00002.weights.h5",
|
| 141 |
+
"/layers/t5_encoder_block_16/self_attention/attention/q/vars": "model_00002.weights.h5",
|
| 142 |
+
"/layers/t5_encoder_block_16/self_attention/attention/v/vars": "model_00002.weights.h5",
|
| 143 |
+
"/layers/t5_encoder_block_16/self_attention/layer_norm/vars": "model_00002.weights.h5",
|
| 144 |
+
"/layers/t5_encoder_block_17/ff/layer_norm/vars": "model_00002.weights.h5",
|
| 145 |
+
"/layers/t5_encoder_block_17/ff/wi/vars": "model_00002.weights.h5",
|
| 146 |
+
"/layers/t5_encoder_block_17/ff/wo/vars": "model_00002.weights.h5",
|
| 147 |
+
"/layers/t5_encoder_block_17/self_attention/attention/k/vars": "model_00002.weights.h5",
|
| 148 |
+
"/layers/t5_encoder_block_17/self_attention/attention/o/vars": "model_00002.weights.h5",
|
| 149 |
+
"/layers/t5_encoder_block_17/self_attention/attention/q/vars": "model_00002.weights.h5",
|
| 150 |
+
"/layers/t5_encoder_block_17/self_attention/attention/v/vars": "model_00002.weights.h5",
|
| 151 |
+
"/layers/t5_encoder_block_17/self_attention/layer_norm/vars": "model_00002.weights.h5",
|
| 152 |
+
"/layers/t5_encoder_block_18/ff/layer_norm/vars": "model_00002.weights.h5",
|
| 153 |
+
"/layers/t5_encoder_block_18/ff/wi/vars": "model_00002.weights.h5",
|
| 154 |
+
"/layers/t5_encoder_block_18/ff/wo/vars": "model_00002.weights.h5",
|
| 155 |
+
"/layers/t5_encoder_block_18/self_attention/attention/k/vars": "model_00002.weights.h5",
|
| 156 |
+
"/layers/t5_encoder_block_18/self_attention/attention/o/vars": "model_00002.weights.h5",
|
| 157 |
+
"/layers/t5_encoder_block_18/self_attention/attention/q/vars": "model_00002.weights.h5",
|
| 158 |
+
"/layers/t5_encoder_block_18/self_attention/attention/v/vars": "model_00002.weights.h5",
|
| 159 |
+
"/layers/t5_encoder_block_18/self_attention/layer_norm/vars": "model_00002.weights.h5",
|
| 160 |
+
"/layers/t5_encoder_block_19/ff/layer_norm/vars": "model_00002.weights.h5",
|
| 161 |
+
"/layers/t5_encoder_block_19/ff/wi/vars": "model_00002.weights.h5",
|
| 162 |
+
"/layers/t5_encoder_block_19/ff/wo/vars": "model_00003.weights.h5",
|
| 163 |
+
"/layers/t5_encoder_block_19/self_attention/attention/k/vars": "model_00003.weights.h5",
|
| 164 |
+
"/layers/t5_encoder_block_19/self_attention/attention/o/vars": "model_00003.weights.h5",
|
| 165 |
+
"/layers/t5_encoder_block_19/self_attention/attention/q/vars": "model_00003.weights.h5",
|
| 166 |
+
"/layers/t5_encoder_block_19/self_attention/attention/v/vars": "model_00003.weights.h5",
|
| 167 |
+
"/layers/t5_encoder_block_19/self_attention/layer_norm/vars": "model_00003.weights.h5",
|
| 168 |
+
"/layers/t5_encoder_block_20/ff/layer_norm/vars": "model_00003.weights.h5",
|
| 169 |
+
"/layers/t5_encoder_block_20/ff/wi/vars": "model_00003.weights.h5",
|
| 170 |
+
"/layers/t5_encoder_block_20/ff/wo/vars": "model_00003.weights.h5",
|
| 171 |
+
"/layers/t5_encoder_block_20/self_attention/attention/k/vars": "model_00003.weights.h5",
|
| 172 |
+
"/layers/t5_encoder_block_20/self_attention/attention/o/vars": "model_00003.weights.h5",
|
| 173 |
+
"/layers/t5_encoder_block_20/self_attention/attention/q/vars": "model_00003.weights.h5",
|
| 174 |
+
"/layers/t5_encoder_block_20/self_attention/attention/v/vars": "model_00003.weights.h5",
|
| 175 |
+
"/layers/t5_encoder_block_20/self_attention/layer_norm/vars": "model_00003.weights.h5",
|
| 176 |
+
"/layers/t5_encoder_block_21/ff/layer_norm/vars": "model_00003.weights.h5",
|
| 177 |
+
"/layers/t5_encoder_block_21/ff/wi/vars": "model_00003.weights.h5",
|
| 178 |
+
"/layers/t5_encoder_block_21/ff/wo/vars": "model_00003.weights.h5",
|
| 179 |
+
"/layers/t5_encoder_block_21/self_attention/attention/k/vars": "model_00003.weights.h5",
|
| 180 |
+
"/layers/t5_encoder_block_21/self_attention/attention/o/vars": "model_00003.weights.h5",
|
| 181 |
+
"/layers/t5_encoder_block_21/self_attention/attention/q/vars": "model_00003.weights.h5",
|
| 182 |
+
"/layers/t5_encoder_block_21/self_attention/attention/v/vars": "model_00003.weights.h5",
|
| 183 |
+
"/layers/t5_encoder_block_21/self_attention/layer_norm/vars": "model_00003.weights.h5",
|
| 184 |
+
"/layers/t5_encoder_block_22/ff/layer_norm/vars": "model_00003.weights.h5",
|
| 185 |
+
"/layers/t5_encoder_block_22/ff/wi/vars": "model_00003.weights.h5",
|
| 186 |
+
"/layers/t5_encoder_block_22/ff/wo/vars": "model_00003.weights.h5",
|
| 187 |
+
"/layers/t5_encoder_block_22/self_attention/attention/k/vars": "model_00003.weights.h5",
|
| 188 |
+
"/layers/t5_encoder_block_22/self_attention/attention/o/vars": "model_00003.weights.h5",
|
| 189 |
+
"/layers/t5_encoder_block_22/self_attention/attention/q/vars": "model_00003.weights.h5",
|
| 190 |
+
"/layers/t5_encoder_block_22/self_attention/attention/v/vars": "model_00003.weights.h5",
|
| 191 |
+
"/layers/t5_encoder_block_22/self_attention/layer_norm/vars": "model_00003.weights.h5",
|
| 192 |
+
"/layers/t5_encoder_block_23/ff/layer_norm/vars": "model_00003.weights.h5",
|
| 193 |
+
"/layers/t5_encoder_block_23/ff/wi/vars": "model_00003.weights.h5",
|
| 194 |
+
"/layers/t5_encoder_block_23/ff/wo/vars": "model_00003.weights.h5",
|
| 195 |
+
"/layers/t5_encoder_block_23/self_attention/attention/k/vars": "model_00003.weights.h5",
|
| 196 |
+
"/layers/t5_encoder_block_23/self_attention/attention/o/vars": "model_00003.weights.h5",
|
| 197 |
+
"/layers/t5_encoder_block_23/self_attention/attention/q/vars": "model_00003.weights.h5",
|
| 198 |
+
"/layers/t5_encoder_block_23/self_attention/attention/v/vars": "model_00003.weights.h5",
|
| 199 |
+
"/layers/t5_encoder_block_23/self_attention/layer_norm/vars": "model_00003.weights.h5",
|
| 200 |
+
"/layers/t5_layer_norm/vars": "model_00003.weights.h5",
|
| 201 |
+
"/layers/t5_position_bias_1/rel_bias/vars": "model_00003.weights.h5",
|
| 202 |
+
"/layers/t5_decoder_block/cross_attention/attention/k/vars": "model_00003.weights.h5",
|
| 203 |
+
"/layers/t5_decoder_block/cross_attention/attention/o/vars": "model_00003.weights.h5",
|
| 204 |
+
"/layers/t5_decoder_block/cross_attention/attention/q/vars": "model_00003.weights.h5",
|
| 205 |
+
"/layers/t5_decoder_block/cross_attention/attention/v/vars": "model_00003.weights.h5",
|
| 206 |
+
"/layers/t5_decoder_block/cross_attention/layer_norm/vars": "model_00003.weights.h5",
|
| 207 |
+
"/layers/t5_decoder_block/ff/layer_norm/vars": "model_00003.weights.h5",
|
| 208 |
+
"/layers/t5_decoder_block/ff/wi/vars": "model_00003.weights.h5",
|
| 209 |
+
"/layers/t5_decoder_block/ff/wo/vars": "model_00003.weights.h5",
|
| 210 |
+
"/layers/t5_decoder_block/self_attention/attention/k/vars": "model_00003.weights.h5",
|
| 211 |
+
"/layers/t5_decoder_block/self_attention/attention/o/vars": "model_00003.weights.h5",
|
| 212 |
+
"/layers/t5_decoder_block/self_attention/attention/q/vars": "model_00003.weights.h5",
|
| 213 |
+
"/layers/t5_decoder_block/self_attention/attention/v/vars": "model_00003.weights.h5",
|
| 214 |
+
"/layers/t5_decoder_block/self_attention/layer_norm/vars": "model_00003.weights.h5",
|
| 215 |
+
"/layers/t5_decoder_block_1/cross_attention/attention/k/vars": "model_00003.weights.h5",
|
| 216 |
+
"/layers/t5_decoder_block_1/cross_attention/attention/o/vars": "model_00003.weights.h5",
|
| 217 |
+
"/layers/t5_decoder_block_1/cross_attention/attention/q/vars": "model_00003.weights.h5",
|
| 218 |
+
"/layers/t5_decoder_block_1/cross_attention/attention/v/vars": "model_00003.weights.h5",
|
| 219 |
+
"/layers/t5_decoder_block_1/cross_attention/layer_norm/vars": "model_00003.weights.h5",
|
| 220 |
+
"/layers/t5_decoder_block_1/ff/layer_norm/vars": "model_00003.weights.h5",
|
| 221 |
+
"/layers/t5_decoder_block_1/ff/wi/vars": "model_00004.weights.h5",
|
| 222 |
+
"/layers/t5_decoder_block_1/ff/wo/vars": "model_00004.weights.h5",
|
| 223 |
+
"/layers/t5_decoder_block_1/self_attention/attention/k/vars": "model_00004.weights.h5",
|
| 224 |
+
"/layers/t5_decoder_block_1/self_attention/attention/o/vars": "model_00004.weights.h5",
|
| 225 |
+
"/layers/t5_decoder_block_1/self_attention/attention/q/vars": "model_00004.weights.h5",
|
| 226 |
+
"/layers/t5_decoder_block_1/self_attention/attention/v/vars": "model_00004.weights.h5",
|
| 227 |
+
"/layers/t5_decoder_block_1/self_attention/layer_norm/vars": "model_00004.weights.h5",
|
| 228 |
+
"/layers/t5_decoder_block_2/cross_attention/attention/k/vars": "model_00004.weights.h5",
|
| 229 |
+
"/layers/t5_decoder_block_2/cross_attention/attention/o/vars": "model_00004.weights.h5",
|
| 230 |
+
"/layers/t5_decoder_block_2/cross_attention/attention/q/vars": "model_00004.weights.h5",
|
| 231 |
+
"/layers/t5_decoder_block_2/cross_attention/attention/v/vars": "model_00004.weights.h5",
|
| 232 |
+
"/layers/t5_decoder_block_2/cross_attention/layer_norm/vars": "model_00004.weights.h5",
|
| 233 |
+
"/layers/t5_decoder_block_2/ff/layer_norm/vars": "model_00004.weights.h5",
|
| 234 |
+
"/layers/t5_decoder_block_2/ff/wi/vars": "model_00004.weights.h5",
|
| 235 |
+
"/layers/t5_decoder_block_2/ff/wo/vars": "model_00004.weights.h5",
|
| 236 |
+
"/layers/t5_decoder_block_2/self_attention/attention/k/vars": "model_00004.weights.h5",
|
| 237 |
+
"/layers/t5_decoder_block_2/self_attention/attention/o/vars": "model_00004.weights.h5",
|
| 238 |
+
"/layers/t5_decoder_block_2/self_attention/attention/q/vars": "model_00004.weights.h5",
|
| 239 |
+
"/layers/t5_decoder_block_2/self_attention/attention/v/vars": "model_00004.weights.h5",
|
| 240 |
+
"/layers/t5_decoder_block_2/self_attention/layer_norm/vars": "model_00004.weights.h5",
|
| 241 |
+
"/layers/t5_decoder_block_3/cross_attention/attention/k/vars": "model_00004.weights.h5",
|
| 242 |
+
"/layers/t5_decoder_block_3/cross_attention/attention/o/vars": "model_00004.weights.h5",
|
| 243 |
+
"/layers/t5_decoder_block_3/cross_attention/attention/q/vars": "model_00004.weights.h5",
|
| 244 |
+
"/layers/t5_decoder_block_3/cross_attention/attention/v/vars": "model_00004.weights.h5",
|
| 245 |
+
"/layers/t5_decoder_block_3/cross_attention/layer_norm/vars": "model_00004.weights.h5",
|
| 246 |
+
"/layers/t5_decoder_block_3/ff/layer_norm/vars": "model_00004.weights.h5",
|
| 247 |
+
"/layers/t5_decoder_block_3/ff/wi/vars": "model_00004.weights.h5",
|
| 248 |
+
"/layers/t5_decoder_block_3/ff/wo/vars": "model_00004.weights.h5",
|
| 249 |
+
"/layers/t5_decoder_block_3/self_attention/attention/k/vars": "model_00004.weights.h5",
|
| 250 |
+
"/layers/t5_decoder_block_3/self_attention/attention/o/vars": "model_00004.weights.h5",
|
| 251 |
+
"/layers/t5_decoder_block_3/self_attention/attention/q/vars": "model_00004.weights.h5",
|
| 252 |
+
"/layers/t5_decoder_block_3/self_attention/attention/v/vars": "model_00004.weights.h5",
|
| 253 |
+
"/layers/t5_decoder_block_3/self_attention/layer_norm/vars": "model_00004.weights.h5",
|
| 254 |
+
"/layers/t5_decoder_block_4/cross_attention/attention/k/vars": "model_00004.weights.h5",
|
| 255 |
+
"/layers/t5_decoder_block_4/cross_attention/attention/o/vars": "model_00004.weights.h5",
|
| 256 |
+
"/layers/t5_decoder_block_4/cross_attention/attention/q/vars": "model_00004.weights.h5",
|
| 257 |
+
"/layers/t5_decoder_block_4/cross_attention/attention/v/vars": "model_00004.weights.h5",
|
| 258 |
+
"/layers/t5_decoder_block_4/cross_attention/layer_norm/vars": "model_00004.weights.h5",
|
| 259 |
+
"/layers/t5_decoder_block_4/ff/layer_norm/vars": "model_00004.weights.h5",
|
| 260 |
+
"/layers/t5_decoder_block_4/ff/wi/vars": "model_00004.weights.h5",
|
| 261 |
+
"/layers/t5_decoder_block_4/ff/wo/vars": "model_00004.weights.h5",
|
| 262 |
+
"/layers/t5_decoder_block_4/self_attention/attention/k/vars": "model_00004.weights.h5",
|
| 263 |
+
"/layers/t5_decoder_block_4/self_attention/attention/o/vars": "model_00004.weights.h5",
|
| 264 |
+
"/layers/t5_decoder_block_4/self_attention/attention/q/vars": "model_00004.weights.h5",
|
| 265 |
+
"/layers/t5_decoder_block_4/self_attention/attention/v/vars": "model_00004.weights.h5",
|
| 266 |
+
"/layers/t5_decoder_block_4/self_attention/layer_norm/vars": "model_00004.weights.h5",
|
| 267 |
+
"/layers/t5_decoder_block_5/cross_attention/attention/k/vars": "model_00004.weights.h5",
|
| 268 |
+
"/layers/t5_decoder_block_5/cross_attention/attention/o/vars": "model_00004.weights.h5",
|
| 269 |
+
"/layers/t5_decoder_block_5/cross_attention/attention/q/vars": "model_00004.weights.h5",
|
| 270 |
+
"/layers/t5_decoder_block_5/cross_attention/attention/v/vars": "model_00004.weights.h5",
|
| 271 |
+
"/layers/t5_decoder_block_5/cross_attention/layer_norm/vars": "model_00004.weights.h5",
|
| 272 |
+
"/layers/t5_decoder_block_5/ff/layer_norm/vars": "model_00004.weights.h5",
|
| 273 |
+
"/layers/t5_decoder_block_5/ff/wi/vars": "model_00004.weights.h5",
|
| 274 |
+
"/layers/t5_decoder_block_5/ff/wo/vars": "model_00004.weights.h5",
|
| 275 |
+
"/layers/t5_decoder_block_5/self_attention/attention/k/vars": "model_00004.weights.h5",
|
| 276 |
+
"/layers/t5_decoder_block_5/self_attention/attention/o/vars": "model_00004.weights.h5",
|
| 277 |
+
"/layers/t5_decoder_block_5/self_attention/attention/q/vars": "model_00004.weights.h5",
|
| 278 |
+
"/layers/t5_decoder_block_5/self_attention/attention/v/vars": "model_00004.weights.h5",
|
| 279 |
+
"/layers/t5_decoder_block_5/self_attention/layer_norm/vars": "model_00004.weights.h5",
|
| 280 |
+
"/layers/t5_decoder_block_6/cross_attention/attention/k/vars": "model_00004.weights.h5",
|
| 281 |
+
"/layers/t5_decoder_block_6/cross_attention/attention/o/vars": "model_00004.weights.h5",
|
| 282 |
+
"/layers/t5_decoder_block_6/cross_attention/attention/q/vars": "model_00004.weights.h5",
|
| 283 |
+
"/layers/t5_decoder_block_6/cross_attention/attention/v/vars": "model_00005.weights.h5",
|
| 284 |
+
"/layers/t5_decoder_block_6/cross_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 285 |
+
"/layers/t5_decoder_block_6/ff/layer_norm/vars": "model_00005.weights.h5",
|
| 286 |
+
"/layers/t5_decoder_block_6/ff/wi/vars": "model_00005.weights.h5",
|
| 287 |
+
"/layers/t5_decoder_block_6/ff/wo/vars": "model_00005.weights.h5",
|
| 288 |
+
"/layers/t5_decoder_block_6/self_attention/attention/k/vars": "model_00005.weights.h5",
|
| 289 |
+
"/layers/t5_decoder_block_6/self_attention/attention/o/vars": "model_00005.weights.h5",
|
| 290 |
+
"/layers/t5_decoder_block_6/self_attention/attention/q/vars": "model_00005.weights.h5",
|
| 291 |
+
"/layers/t5_decoder_block_6/self_attention/attention/v/vars": "model_00005.weights.h5",
|
| 292 |
+
"/layers/t5_decoder_block_6/self_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 293 |
+
"/layers/t5_decoder_block_7/cross_attention/attention/k/vars": "model_00005.weights.h5",
|
| 294 |
+
"/layers/t5_decoder_block_7/cross_attention/attention/o/vars": "model_00005.weights.h5",
|
| 295 |
+
"/layers/t5_decoder_block_7/cross_attention/attention/q/vars": "model_00005.weights.h5",
|
| 296 |
+
"/layers/t5_decoder_block_7/cross_attention/attention/v/vars": "model_00005.weights.h5",
|
| 297 |
+
"/layers/t5_decoder_block_7/cross_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 298 |
+
"/layers/t5_decoder_block_7/ff/layer_norm/vars": "model_00005.weights.h5",
|
| 299 |
+
"/layers/t5_decoder_block_7/ff/wi/vars": "model_00005.weights.h5",
|
| 300 |
+
"/layers/t5_decoder_block_7/ff/wo/vars": "model_00005.weights.h5",
|
| 301 |
+
"/layers/t5_decoder_block_7/self_attention/attention/k/vars": "model_00005.weights.h5",
|
| 302 |
+
"/layers/t5_decoder_block_7/self_attention/attention/o/vars": "model_00005.weights.h5",
|
| 303 |
+
"/layers/t5_decoder_block_7/self_attention/attention/q/vars": "model_00005.weights.h5",
|
| 304 |
+
"/layers/t5_decoder_block_7/self_attention/attention/v/vars": "model_00005.weights.h5",
|
| 305 |
+
"/layers/t5_decoder_block_7/self_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 306 |
+
"/layers/t5_decoder_block_8/cross_attention/attention/k/vars": "model_00005.weights.h5",
|
| 307 |
+
"/layers/t5_decoder_block_8/cross_attention/attention/o/vars": "model_00005.weights.h5",
|
| 308 |
+
"/layers/t5_decoder_block_8/cross_attention/attention/q/vars": "model_00005.weights.h5",
|
| 309 |
+
"/layers/t5_decoder_block_8/cross_attention/attention/v/vars": "model_00005.weights.h5",
|
| 310 |
+
"/layers/t5_decoder_block_8/cross_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 311 |
+
"/layers/t5_decoder_block_8/ff/layer_norm/vars": "model_00005.weights.h5",
|
| 312 |
+
"/layers/t5_decoder_block_8/ff/wi/vars": "model_00005.weights.h5",
|
| 313 |
+
"/layers/t5_decoder_block_8/ff/wo/vars": "model_00005.weights.h5",
|
| 314 |
+
"/layers/t5_decoder_block_8/self_attention/attention/k/vars": "model_00005.weights.h5",
|
| 315 |
+
"/layers/t5_decoder_block_8/self_attention/attention/o/vars": "model_00005.weights.h5",
|
| 316 |
+
"/layers/t5_decoder_block_8/self_attention/attention/q/vars": "model_00005.weights.h5",
|
| 317 |
+
"/layers/t5_decoder_block_8/self_attention/attention/v/vars": "model_00005.weights.h5",
|
| 318 |
+
"/layers/t5_decoder_block_8/self_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 319 |
+
"/layers/t5_decoder_block_9/cross_attention/attention/k/vars": "model_00005.weights.h5",
|
| 320 |
+
"/layers/t5_decoder_block_9/cross_attention/attention/o/vars": "model_00005.weights.h5",
|
| 321 |
+
"/layers/t5_decoder_block_9/cross_attention/attention/q/vars": "model_00005.weights.h5",
|
| 322 |
+
"/layers/t5_decoder_block_9/cross_attention/attention/v/vars": "model_00005.weights.h5",
|
| 323 |
+
"/layers/t5_decoder_block_9/cross_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 324 |
+
"/layers/t5_decoder_block_9/ff/layer_norm/vars": "model_00005.weights.h5",
|
| 325 |
+
"/layers/t5_decoder_block_9/ff/wi/vars": "model_00005.weights.h5",
|
| 326 |
+
"/layers/t5_decoder_block_9/ff/wo/vars": "model_00005.weights.h5",
|
| 327 |
+
"/layers/t5_decoder_block_9/self_attention/attention/k/vars": "model_00005.weights.h5",
|
| 328 |
+
"/layers/t5_decoder_block_9/self_attention/attention/o/vars": "model_00005.weights.h5",
|
| 329 |
+
"/layers/t5_decoder_block_9/self_attention/attention/q/vars": "model_00005.weights.h5",
|
| 330 |
+
"/layers/t5_decoder_block_9/self_attention/attention/v/vars": "model_00005.weights.h5",
|
| 331 |
+
"/layers/t5_decoder_block_9/self_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 332 |
+
"/layers/t5_decoder_block_10/cross_attention/attention/k/vars": "model_00005.weights.h5",
|
| 333 |
+
"/layers/t5_decoder_block_10/cross_attention/attention/o/vars": "model_00005.weights.h5",
|
| 334 |
+
"/layers/t5_decoder_block_10/cross_attention/attention/q/vars": "model_00005.weights.h5",
|
| 335 |
+
"/layers/t5_decoder_block_10/cross_attention/attention/v/vars": "model_00005.weights.h5",
|
| 336 |
+
"/layers/t5_decoder_block_10/cross_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 337 |
+
"/layers/t5_decoder_block_10/ff/layer_norm/vars": "model_00005.weights.h5",
|
| 338 |
+
"/layers/t5_decoder_block_10/ff/wi/vars": "model_00005.weights.h5",
|
| 339 |
+
"/layers/t5_decoder_block_10/ff/wo/vars": "model_00005.weights.h5",
|
| 340 |
+
"/layers/t5_decoder_block_10/self_attention/attention/k/vars": "model_00005.weights.h5",
|
| 341 |
+
"/layers/t5_decoder_block_10/self_attention/attention/o/vars": "model_00005.weights.h5",
|
| 342 |
+
"/layers/t5_decoder_block_10/self_attention/attention/q/vars": "model_00005.weights.h5",
|
| 343 |
+
"/layers/t5_decoder_block_10/self_attention/attention/v/vars": "model_00005.weights.h5",
|
| 344 |
+
"/layers/t5_decoder_block_10/self_attention/layer_norm/vars": "model_00005.weights.h5",
|
| 345 |
+
"/layers/t5_decoder_block_11/cross_attention/attention/k/vars": "model_00005.weights.h5",
|
| 346 |
+
"/layers/t5_decoder_block_11/cross_attention/attention/o/vars": "model_00005.weights.h5",
|
| 347 |
+
"/layers/t5_decoder_block_11/cross_attention/attention/q/vars": "model_00006.weights.h5",
|
| 348 |
+
"/layers/t5_decoder_block_11/cross_attention/attention/v/vars": "model_00006.weights.h5",
|
| 349 |
+
"/layers/t5_decoder_block_11/cross_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 350 |
+
"/layers/t5_decoder_block_11/ff/layer_norm/vars": "model_00006.weights.h5",
|
| 351 |
+
"/layers/t5_decoder_block_11/ff/wi/vars": "model_00006.weights.h5",
|
| 352 |
+
"/layers/t5_decoder_block_11/ff/wo/vars": "model_00006.weights.h5",
|
| 353 |
+
"/layers/t5_decoder_block_11/self_attention/attention/k/vars": "model_00006.weights.h5",
|
| 354 |
+
"/layers/t5_decoder_block_11/self_attention/attention/o/vars": "model_00006.weights.h5",
|
| 355 |
+
"/layers/t5_decoder_block_11/self_attention/attention/q/vars": "model_00006.weights.h5",
|
| 356 |
+
"/layers/t5_decoder_block_11/self_attention/attention/v/vars": "model_00006.weights.h5",
|
| 357 |
+
"/layers/t5_decoder_block_11/self_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 358 |
+
"/layers/t5_decoder_block_12/cross_attention/attention/k/vars": "model_00006.weights.h5",
|
| 359 |
+
"/layers/t5_decoder_block_12/cross_attention/attention/o/vars": "model_00006.weights.h5",
|
| 360 |
+
"/layers/t5_decoder_block_12/cross_attention/attention/q/vars": "model_00006.weights.h5",
|
| 361 |
+
"/layers/t5_decoder_block_12/cross_attention/attention/v/vars": "model_00006.weights.h5",
|
| 362 |
+
"/layers/t5_decoder_block_12/cross_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 363 |
+
"/layers/t5_decoder_block_12/ff/layer_norm/vars": "model_00006.weights.h5",
|
| 364 |
+
"/layers/t5_decoder_block_12/ff/wi/vars": "model_00006.weights.h5",
|
| 365 |
+
"/layers/t5_decoder_block_12/ff/wo/vars": "model_00006.weights.h5",
|
| 366 |
+
"/layers/t5_decoder_block_12/self_attention/attention/k/vars": "model_00006.weights.h5",
|
| 367 |
+
"/layers/t5_decoder_block_12/self_attention/attention/o/vars": "model_00006.weights.h5",
|
| 368 |
+
"/layers/t5_decoder_block_12/self_attention/attention/q/vars": "model_00006.weights.h5",
|
| 369 |
+
"/layers/t5_decoder_block_12/self_attention/attention/v/vars": "model_00006.weights.h5",
|
| 370 |
+
"/layers/t5_decoder_block_12/self_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 371 |
+
"/layers/t5_decoder_block_13/cross_attention/attention/k/vars": "model_00006.weights.h5",
|
| 372 |
+
"/layers/t5_decoder_block_13/cross_attention/attention/o/vars": "model_00006.weights.h5",
|
| 373 |
+
"/layers/t5_decoder_block_13/cross_attention/attention/q/vars": "model_00006.weights.h5",
|
| 374 |
+
"/layers/t5_decoder_block_13/cross_attention/attention/v/vars": "model_00006.weights.h5",
|
| 375 |
+
"/layers/t5_decoder_block_13/cross_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 376 |
+
"/layers/t5_decoder_block_13/ff/layer_norm/vars": "model_00006.weights.h5",
|
| 377 |
+
"/layers/t5_decoder_block_13/ff/wi/vars": "model_00006.weights.h5",
|
| 378 |
+
"/layers/t5_decoder_block_13/ff/wo/vars": "model_00006.weights.h5",
|
| 379 |
+
"/layers/t5_decoder_block_13/self_attention/attention/k/vars": "model_00006.weights.h5",
|
| 380 |
+
"/layers/t5_decoder_block_13/self_attention/attention/o/vars": "model_00006.weights.h5",
|
| 381 |
+
"/layers/t5_decoder_block_13/self_attention/attention/q/vars": "model_00006.weights.h5",
|
| 382 |
+
"/layers/t5_decoder_block_13/self_attention/attention/v/vars": "model_00006.weights.h5",
|
| 383 |
+
"/layers/t5_decoder_block_13/self_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 384 |
+
"/layers/t5_decoder_block_14/cross_attention/attention/k/vars": "model_00006.weights.h5",
|
| 385 |
+
"/layers/t5_decoder_block_14/cross_attention/attention/o/vars": "model_00006.weights.h5",
|
| 386 |
+
"/layers/t5_decoder_block_14/cross_attention/attention/q/vars": "model_00006.weights.h5",
|
| 387 |
+
"/layers/t5_decoder_block_14/cross_attention/attention/v/vars": "model_00006.weights.h5",
|
| 388 |
+
"/layers/t5_decoder_block_14/cross_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 389 |
+
"/layers/t5_decoder_block_14/ff/layer_norm/vars": "model_00006.weights.h5",
|
| 390 |
+
"/layers/t5_decoder_block_14/ff/wi/vars": "model_00006.weights.h5",
|
| 391 |
+
"/layers/t5_decoder_block_14/ff/wo/vars": "model_00006.weights.h5",
|
| 392 |
+
"/layers/t5_decoder_block_14/self_attention/attention/k/vars": "model_00006.weights.h5",
|
| 393 |
+
"/layers/t5_decoder_block_14/self_attention/attention/o/vars": "model_00006.weights.h5",
|
| 394 |
+
"/layers/t5_decoder_block_14/self_attention/attention/q/vars": "model_00006.weights.h5",
|
| 395 |
+
"/layers/t5_decoder_block_14/self_attention/attention/v/vars": "model_00006.weights.h5",
|
| 396 |
+
"/layers/t5_decoder_block_14/self_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 397 |
+
"/layers/t5_decoder_block_15/cross_attention/attention/k/vars": "model_00006.weights.h5",
|
| 398 |
+
"/layers/t5_decoder_block_15/cross_attention/attention/o/vars": "model_00006.weights.h5",
|
| 399 |
+
"/layers/t5_decoder_block_15/cross_attention/attention/q/vars": "model_00006.weights.h5",
|
| 400 |
+
"/layers/t5_decoder_block_15/cross_attention/attention/v/vars": "model_00006.weights.h5",
|
| 401 |
+
"/layers/t5_decoder_block_15/cross_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 402 |
+
"/layers/t5_decoder_block_15/ff/layer_norm/vars": "model_00006.weights.h5",
|
| 403 |
+
"/layers/t5_decoder_block_15/ff/wi/vars": "model_00006.weights.h5",
|
| 404 |
+
"/layers/t5_decoder_block_15/ff/wo/vars": "model_00006.weights.h5",
|
| 405 |
+
"/layers/t5_decoder_block_15/self_attention/attention/k/vars": "model_00006.weights.h5",
|
| 406 |
+
"/layers/t5_decoder_block_15/self_attention/attention/o/vars": "model_00006.weights.h5",
|
| 407 |
+
"/layers/t5_decoder_block_15/self_attention/attention/q/vars": "model_00006.weights.h5",
|
| 408 |
+
"/layers/t5_decoder_block_15/self_attention/attention/v/vars": "model_00006.weights.h5",
|
| 409 |
+
"/layers/t5_decoder_block_15/self_attention/layer_norm/vars": "model_00006.weights.h5",
|
| 410 |
+
"/layers/t5_decoder_block_16/cross_attention/attention/k/vars": "model_00006.weights.h5",
|
| 411 |
+
"/layers/t5_decoder_block_16/cross_attention/attention/o/vars": "model_00007.weights.h5",
|
| 412 |
+
"/layers/t5_decoder_block_16/cross_attention/attention/q/vars": "model_00007.weights.h5",
|
| 413 |
+
"/layers/t5_decoder_block_16/cross_attention/attention/v/vars": "model_00007.weights.h5",
|
| 414 |
+
"/layers/t5_decoder_block_16/cross_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 415 |
+
"/layers/t5_decoder_block_16/ff/layer_norm/vars": "model_00007.weights.h5",
|
| 416 |
+
"/layers/t5_decoder_block_16/ff/wi/vars": "model_00007.weights.h5",
|
| 417 |
+
"/layers/t5_decoder_block_16/ff/wo/vars": "model_00007.weights.h5",
|
| 418 |
+
"/layers/t5_decoder_block_16/self_attention/attention/k/vars": "model_00007.weights.h5",
|
| 419 |
+
"/layers/t5_decoder_block_16/self_attention/attention/o/vars": "model_00007.weights.h5",
|
| 420 |
+
"/layers/t5_decoder_block_16/self_attention/attention/q/vars": "model_00007.weights.h5",
|
| 421 |
+
"/layers/t5_decoder_block_16/self_attention/attention/v/vars": "model_00007.weights.h5",
|
| 422 |
+
"/layers/t5_decoder_block_16/self_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 423 |
+
"/layers/t5_decoder_block_17/cross_attention/attention/k/vars": "model_00007.weights.h5",
|
| 424 |
+
"/layers/t5_decoder_block_17/cross_attention/attention/o/vars": "model_00007.weights.h5",
|
| 425 |
+
"/layers/t5_decoder_block_17/cross_attention/attention/q/vars": "model_00007.weights.h5",
|
| 426 |
+
"/layers/t5_decoder_block_17/cross_attention/attention/v/vars": "model_00007.weights.h5",
|
| 427 |
+
"/layers/t5_decoder_block_17/cross_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 428 |
+
"/layers/t5_decoder_block_17/ff/layer_norm/vars": "model_00007.weights.h5",
|
| 429 |
+
"/layers/t5_decoder_block_17/ff/wi/vars": "model_00007.weights.h5",
|
| 430 |
+
"/layers/t5_decoder_block_17/ff/wo/vars": "model_00007.weights.h5",
|
| 431 |
+
"/layers/t5_decoder_block_17/self_attention/attention/k/vars": "model_00007.weights.h5",
|
| 432 |
+
"/layers/t5_decoder_block_17/self_attention/attention/o/vars": "model_00007.weights.h5",
|
| 433 |
+
"/layers/t5_decoder_block_17/self_attention/attention/q/vars": "model_00007.weights.h5",
|
| 434 |
+
"/layers/t5_decoder_block_17/self_attention/attention/v/vars": "model_00007.weights.h5",
|
| 435 |
+
"/layers/t5_decoder_block_17/self_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 436 |
+
"/layers/t5_decoder_block_18/cross_attention/attention/k/vars": "model_00007.weights.h5",
|
| 437 |
+
"/layers/t5_decoder_block_18/cross_attention/attention/o/vars": "model_00007.weights.h5",
|
| 438 |
+
"/layers/t5_decoder_block_18/cross_attention/attention/q/vars": "model_00007.weights.h5",
|
| 439 |
+
"/layers/t5_decoder_block_18/cross_attention/attention/v/vars": "model_00007.weights.h5",
|
| 440 |
+
"/layers/t5_decoder_block_18/cross_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 441 |
+
"/layers/t5_decoder_block_18/ff/layer_norm/vars": "model_00007.weights.h5",
|
| 442 |
+
"/layers/t5_decoder_block_18/ff/wi/vars": "model_00007.weights.h5",
|
| 443 |
+
"/layers/t5_decoder_block_18/ff/wo/vars": "model_00007.weights.h5",
|
| 444 |
+
"/layers/t5_decoder_block_18/self_attention/attention/k/vars": "model_00007.weights.h5",
|
| 445 |
+
"/layers/t5_decoder_block_18/self_attention/attention/o/vars": "model_00007.weights.h5",
|
| 446 |
+
"/layers/t5_decoder_block_18/self_attention/attention/q/vars": "model_00007.weights.h5",
|
| 447 |
+
"/layers/t5_decoder_block_18/self_attention/attention/v/vars": "model_00007.weights.h5",
|
| 448 |
+
"/layers/t5_decoder_block_18/self_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 449 |
+
"/layers/t5_decoder_block_19/cross_attention/attention/k/vars": "model_00007.weights.h5",
|
| 450 |
+
"/layers/t5_decoder_block_19/cross_attention/attention/o/vars": "model_00007.weights.h5",
|
| 451 |
+
"/layers/t5_decoder_block_19/cross_attention/attention/q/vars": "model_00007.weights.h5",
|
| 452 |
+
"/layers/t5_decoder_block_19/cross_attention/attention/v/vars": "model_00007.weights.h5",
|
| 453 |
+
"/layers/t5_decoder_block_19/cross_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 454 |
+
"/layers/t5_decoder_block_19/ff/layer_norm/vars": "model_00007.weights.h5",
|
| 455 |
+
"/layers/t5_decoder_block_19/ff/wi/vars": "model_00007.weights.h5",
|
| 456 |
+
"/layers/t5_decoder_block_19/ff/wo/vars": "model_00007.weights.h5",
|
| 457 |
+
"/layers/t5_decoder_block_19/self_attention/attention/k/vars": "model_00007.weights.h5",
|
| 458 |
+
"/layers/t5_decoder_block_19/self_attention/attention/o/vars": "model_00007.weights.h5",
|
| 459 |
+
"/layers/t5_decoder_block_19/self_attention/attention/q/vars": "model_00007.weights.h5",
|
| 460 |
+
"/layers/t5_decoder_block_19/self_attention/attention/v/vars": "model_00007.weights.h5",
|
| 461 |
+
"/layers/t5_decoder_block_19/self_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 462 |
+
"/layers/t5_decoder_block_20/cross_attention/attention/k/vars": "model_00007.weights.h5",
|
| 463 |
+
"/layers/t5_decoder_block_20/cross_attention/attention/o/vars": "model_00007.weights.h5",
|
| 464 |
+
"/layers/t5_decoder_block_20/cross_attention/attention/q/vars": "model_00007.weights.h5",
|
| 465 |
+
"/layers/t5_decoder_block_20/cross_attention/attention/v/vars": "model_00007.weights.h5",
|
| 466 |
+
"/layers/t5_decoder_block_20/cross_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 467 |
+
"/layers/t5_decoder_block_20/ff/layer_norm/vars": "model_00007.weights.h5",
|
| 468 |
+
"/layers/t5_decoder_block_20/ff/wi/vars": "model_00007.weights.h5",
|
| 469 |
+
"/layers/t5_decoder_block_20/ff/wo/vars": "model_00007.weights.h5",
|
| 470 |
+
"/layers/t5_decoder_block_20/self_attention/attention/k/vars": "model_00007.weights.h5",
|
| 471 |
+
"/layers/t5_decoder_block_20/self_attention/attention/o/vars": "model_00007.weights.h5",
|
| 472 |
+
"/layers/t5_decoder_block_20/self_attention/attention/q/vars": "model_00007.weights.h5",
|
| 473 |
+
"/layers/t5_decoder_block_20/self_attention/attention/v/vars": "model_00007.weights.h5",
|
| 474 |
+
"/layers/t5_decoder_block_20/self_attention/layer_norm/vars": "model_00007.weights.h5",
|
| 475 |
+
"/layers/t5_decoder_block_21/cross_attention/attention/k/vars": "model_00008.weights.h5",
|
| 476 |
+
"/layers/t5_decoder_block_21/cross_attention/attention/o/vars": "model_00008.weights.h5",
|
| 477 |
+
"/layers/t5_decoder_block_21/cross_attention/attention/q/vars": "model_00008.weights.h5",
|
| 478 |
+
"/layers/t5_decoder_block_21/cross_attention/attention/v/vars": "model_00008.weights.h5",
|
| 479 |
+
"/layers/t5_decoder_block_21/cross_attention/layer_norm/vars": "model_00008.weights.h5",
|
| 480 |
+
"/layers/t5_decoder_block_21/ff/layer_norm/vars": "model_00008.weights.h5",
|
| 481 |
+
"/layers/t5_decoder_block_21/ff/wi/vars": "model_00008.weights.h5",
|
| 482 |
+
"/layers/t5_decoder_block_21/ff/wo/vars": "model_00008.weights.h5",
|
| 483 |
+
"/layers/t5_decoder_block_21/self_attention/attention/k/vars": "model_00008.weights.h5",
|
| 484 |
+
"/layers/t5_decoder_block_21/self_attention/attention/o/vars": "model_00008.weights.h5",
|
| 485 |
+
"/layers/t5_decoder_block_21/self_attention/attention/q/vars": "model_00008.weights.h5",
|
| 486 |
+
"/layers/t5_decoder_block_21/self_attention/attention/v/vars": "model_00008.weights.h5",
|
| 487 |
+
"/layers/t5_decoder_block_21/self_attention/layer_norm/vars": "model_00008.weights.h5",
|
| 488 |
+
"/layers/t5_decoder_block_22/cross_attention/attention/k/vars": "model_00008.weights.h5",
|
| 489 |
+
"/layers/t5_decoder_block_22/cross_attention/attention/o/vars": "model_00008.weights.h5",
|
| 490 |
+
"/layers/t5_decoder_block_22/cross_attention/attention/q/vars": "model_00008.weights.h5",
|
| 491 |
+
"/layers/t5_decoder_block_22/cross_attention/attention/v/vars": "model_00008.weights.h5",
|
| 492 |
+
"/layers/t5_decoder_block_22/cross_attention/layer_norm/vars": "model_00008.weights.h5",
|
| 493 |
+
"/layers/t5_decoder_block_22/ff/layer_norm/vars": "model_00008.weights.h5",
|
| 494 |
+
"/layers/t5_decoder_block_22/ff/wi/vars": "model_00008.weights.h5",
|
| 495 |
+
"/layers/t5_decoder_block_22/ff/wo/vars": "model_00008.weights.h5",
|
| 496 |
+
"/layers/t5_decoder_block_22/self_attention/attention/k/vars": "model_00008.weights.h5",
|
| 497 |
+
"/layers/t5_decoder_block_22/self_attention/attention/o/vars": "model_00008.weights.h5",
|
| 498 |
+
"/layers/t5_decoder_block_22/self_attention/attention/q/vars": "model_00008.weights.h5",
|
| 499 |
+
"/layers/t5_decoder_block_22/self_attention/attention/v/vars": "model_00008.weights.h5",
|
| 500 |
+
"/layers/t5_decoder_block_22/self_attention/layer_norm/vars": "model_00008.weights.h5",
|
| 501 |
+
"/layers/t5_decoder_block_23/cross_attention/attention/k/vars": "model_00008.weights.h5",
|
| 502 |
+
"/layers/t5_decoder_block_23/cross_attention/attention/o/vars": "model_00008.weights.h5",
|
| 503 |
+
"/layers/t5_decoder_block_23/cross_attention/attention/q/vars": "model_00008.weights.h5",
|
| 504 |
+
"/layers/t5_decoder_block_23/cross_attention/attention/v/vars": "model_00008.weights.h5",
|
| 505 |
+
"/layers/t5_decoder_block_23/cross_attention/layer_norm/vars": "model_00008.weights.h5",
|
| 506 |
+
"/layers/t5_decoder_block_23/ff/layer_norm/vars": "model_00008.weights.h5",
|
| 507 |
+
"/layers/t5_decoder_block_23/ff/wi/vars": "model_00008.weights.h5",
|
| 508 |
+
"/layers/t5_decoder_block_23/ff/wo/vars": "model_00008.weights.h5",
|
| 509 |
+
"/layers/t5_decoder_block_23/self_attention/attention/k/vars": "model_00008.weights.h5",
|
| 510 |
+
"/layers/t5_decoder_block_23/self_attention/attention/o/vars": "model_00008.weights.h5",
|
| 511 |
+
"/layers/t5_decoder_block_23/self_attention/attention/q/vars": "model_00008.weights.h5",
|
| 512 |
+
"/layers/t5_decoder_block_23/self_attention/attention/v/vars": "model_00008.weights.h5",
|
| 513 |
+
"/layers/t5_decoder_block_23/self_attention/layer_norm/vars": "model_00008.weights.h5",
|
| 514 |
+
"/layers/t5_layer_norm_1/vars": "model_00008.weights.h5"
|
| 515 |
+
}
|
| 516 |
+
}
|
model_00000.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a1050745e98f30b8714403665f4fc75bbf11493352c9514305b4d37beb7f343
|
| 3 |
+
size 5232141504
|
model_00001.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1708b3ed8659cd8cc6bf41307d0dfa85651c53d2b1539ec5c09bf93d2e58af99
|
| 3 |
+
size 5301844648
|
model_00002.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be257c9f88cfbb9a1240f6628f31e3ec692c774a85b83085e5f88619fcc27ae9
|
| 3 |
+
size 5167638168
|
model_00003.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18865b0184266094c72a8fb96c59353ca1de42bf944780d5f8ef9f768cd0c982
|
| 3 |
+
size 5100571600
|
model_00004.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7ffaf71a200194dccdfed062b76387cbdeba47b0c6129c525ae725259960abb
|
| 3 |
+
size 5301874896
|
model_00005.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af8663b87bfb5374ecc6737841a972f372fff034b4d184991c7f10f0c8d2da64
|
| 3 |
+
size 5301892648
|
model_00006.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aafde5aa5d8f25ae0018329062ed42368770f7d7508a3d94d03734de4bf3334c
|
| 3 |
+
size 5301892672
|
model_00007.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7273b06e4c633427b2542e9f688b983df5ba8964ae12dd3d766e5851970488d
|
| 3 |
+
size 5301892704
|
model_00008.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e27ddaae33e1dcd850264d6e610ed8335d8ecb3b957083cc7a73ca08ff69de32
|
| 3 |
+
size 3221406096
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|