4M chkpt

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/patrick/hugging_face/t5/t5-v1_1-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f401f7237cfac1359d30794250da36aa8f879f6df2db218e059c73c12f3c87
+size 990323615

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294ffaf2800adb3104609eb3a1ee3a25c17057121d6f35886459a6049dfd4c8b
+size 990404917

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3134ea035ee87cd627d7008161bba33ac8bee406203aa850d7c014f30a5213d
+size 721070