Upload T5ForConditionalGeneration

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/home/user/app/tmp/train_spelling/space1/m=google_t5-efficient-mini;t=t5-small;ds=all.33;lr=8e-4;grd=8;bf16=y;prev=[ds=all.37;lr=8e-3;grd=16]/model",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1536,
+  "d_kv": 64,
+  "d_model": 384,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 4,
+  "num_heads": 8,
+  "num_layers": 4,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d094734974bf5347a6ec5ddc105acd746d5267114f57564dcc8051b5cb95f4f
+size 124892304