Instructions to use zeromodels/t5_3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/t5_3b with ZeroModels:
# pip install -U zeromodels # ZeroModels is pure Keras 3, so pick a backend: "jax", "torch" or "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" from zeromodels import AutoZModel # AutoZModel reads the repo's model_type and loads the matching class. # For a task head use the matching loader, e.g. AutoZMImageClassify / AutoZMDetect / # AutoZMSemanticSegment / AutoZMTextGenerate (see zeromodels.auto). model = AutoZModel.from_weights("zeromodels/t5_3b") - Keras
How to use zeromodels/t5_3b with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://zeromodels/t5_3b") - Notebooks
- Google Colab
- Kaggle
Download model.weights.json from zeromodels/t5_3b: direct link, hf CLI and curl.
- Browser
- Download file 46.5 kB
-
https://huggingface.co/zeromodels/t5_3b/resolve/main/model.weights.json
- Command line
-
hf download hf://zeromodels/t5_3b/model.weights.json
-
curl -L -o model.weights.json https://huggingface.co/zeromodels/t5_3b/resolve/main/model.weights.json
46.5 kB
| { | |
| "metadata": { | |
| "total_size": 11406393344.0 | |
| }, | |
| "weight_map": { | |
| "/layers/embedding/vars": "model_00000.weights.h5", | |
| "/layers/t5_position_bias/rel_bias/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_1/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_1/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_1/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_1/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_1/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_1/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_1/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_1/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_2/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_2/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_2/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_2/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_2/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_2/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_2/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_2/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_3/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_3/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_3/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_3/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_3/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_3/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_3/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_3/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_4/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_4/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_4/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_4/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_4/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_4/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_4/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_4/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_5/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_5/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_5/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_5/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_5/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_5/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_5/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_5/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_6/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_6/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_6/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_6/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_6/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_6/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_6/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_6/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_7/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_7/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_7/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_7/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_7/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_7/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_7/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_7/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_8/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_8/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_8/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_8/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_8/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_8/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_8/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_8/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_9/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_9/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_9/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_9/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_9/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_9/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_9/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_9/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_10/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_10/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_10/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_10/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_10/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_10/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_10/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_10/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_11/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_11/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_11/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_11/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_11/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_11/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_11/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_11/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_12/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_12/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_12/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_12/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_12/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_12/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_12/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_12/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_13/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_13/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_13/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_13/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_13/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_13/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_13/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_13/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_14/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_14/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_14/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_14/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_14/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_14/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_14/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_14/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_15/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_15/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_15/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_15/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_15/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_15/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_15/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_15/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_16/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_16/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_16/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_16/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_16/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_16/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_16/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_16/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_17/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_17/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_17/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_17/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_17/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_17/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_17/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_17/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_18/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_18/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_18/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_18/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_18/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_18/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_18/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_18/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_19/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_19/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_19/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_19/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_19/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_19/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_19/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_19/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_20/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_20/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_20/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_20/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_20/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_20/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_20/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_20/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_21/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_21/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_21/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_21/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_21/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_21/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_21/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_21/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_22/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_22/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_22/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_22/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_22/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_22/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_22/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_22/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_23/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_23/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_23/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_23/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_23/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_23/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_23/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_encoder_block_23/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_position_bias_1/rel_bias/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/cross_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/cross_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/cross_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/cross_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/cross_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/ff/wo/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/self_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/self_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/self_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/self_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block/self_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block_1/cross_attention/attention/k/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block_1/cross_attention/attention/o/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block_1/cross_attention/attention/q/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block_1/cross_attention/attention/v/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block_1/cross_attention/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block_1/ff/layer_norm/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block_1/ff/wi/vars": "model_00000.weights.h5", | |
| "/layers/t5_decoder_block_1/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_1/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_1/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_1/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_1/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_1/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_2/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_3/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_4/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_5/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_6/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_7/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_8/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_9/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_10/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_11/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_12/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_13/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_14/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_15/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_16/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_17/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_18/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_19/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/ff/wi/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/ff/wo/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/self_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/self_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/self_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/self_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_20/self_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_21/cross_attention/attention/k/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_21/cross_attention/attention/o/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_21/cross_attention/attention/q/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_21/cross_attention/attention/v/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_21/cross_attention/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_21/ff/layer_norm/vars": "model_00001.weights.h5", | |
| "/layers/t5_decoder_block_21/ff/wi/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_21/ff/wo/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_21/self_attention/attention/k/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_21/self_attention/attention/o/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_21/self_attention/attention/q/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_21/self_attention/attention/v/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_21/self_attention/layer_norm/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/cross_attention/attention/k/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/cross_attention/attention/o/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/cross_attention/attention/q/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/cross_attention/attention/v/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/cross_attention/layer_norm/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/ff/layer_norm/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/ff/wi/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/ff/wo/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/self_attention/attention/k/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/self_attention/attention/o/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/self_attention/attention/q/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/self_attention/attention/v/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_22/self_attention/layer_norm/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/cross_attention/attention/k/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/cross_attention/attention/o/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/cross_attention/attention/q/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/cross_attention/attention/v/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/cross_attention/layer_norm/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/ff/layer_norm/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/ff/wi/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/ff/wo/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/self_attention/attention/k/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/self_attention/attention/o/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/self_attention/attention/q/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/self_attention/attention/v/vars": "model_00002.weights.h5", | |
| "/layers/t5_decoder_block_23/self_attention/layer_norm/vars": "model_00002.weights.h5", | |
| "/layers/t5_layer_norm_1/vars": "model_00002.weights.h5" | |
| } | |
| } |