add model

README.md

@@ -1,3 +1,47 @@
 ---
-license: unknown
+tags:
+- generated_from_keras_callback
+model-index:
+- name: t5_l12_large_dataset
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# t5_l12_large_dataset
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: None
+- training_precision: float32
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.19.2
+- TensorFlow 2.7.0
+- Datasets 2.2.2
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "models/t5_large_dataset/",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 320,
+  "decoder_start_token_id": 234,
+  "dropout_rate": 0.1,
+  "eos_token_id": 3,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 8,
+  "num_layers": 12,
+  "pad_token_id": 234,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "transformers_version": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 237
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ec2968d7bccb4fe6783c3f53ce8327765a145b7f7e31d7f780a6dd2ce1e0970
+size 158245488