first version

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/home/patrick/t5/byt5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3584,
+  "d_kv": 64,
+  "d_model": 1472,
+  "decoder_start_token_id": 259,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 4,
+  "num_heads": 6,
+  "num_layers": 12,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "ByT5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 384
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 259,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc8dab0b8a9c65fe864a715e63c254a77ad13b3977bbb9cb13da93315f888d2
+size 1936773

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96e28d451fc176e5deeb6769e8aedfbede564c0c5a88e40ddbb997a21b0f50a
+size 1198609653

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2948fcbfd189c1da52108d2f6e3ef24bd77ec2c52bf29fb0b64b4cb8b949bc
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b26bf31c271e6b54a92b644705993a03ad9dbe024970b74397eda554f31d528
+size 563

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945698497cd92277a49dc73e147d6bc5e15aee5df139a8426aca04ef61f17697
+size 3771