Upload T5ForConditionalGeneration

config.json

@@ -1,12 +1,14 @@
 {
-  "_name_or_path": "/safekeeping/t5-1.1.lm100k/t5.1.1.lm100k.large/pytorch_model/",
+  "_name_or_path": "./3vnuv1vf",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
+  "classifier_dropout": 0.0,
   "d_ff": 2816,
   "d_kv": 64,
   "d_model": 1024,
   "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
   "diversity_penalty": null,
   "dropout_rate": 0.1,
   "eos_token_id": 1,
@@ -14,6 +16,7 @@
   "gradient_checkpointing": false,
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "max_length": 512,
   "model_type": "t5",
@@ -23,9 +26,11 @@
   "num_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
-  "transformers_version": "4.8.2",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 32102
 }

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "diversity_penalty": null,
+  "eos_token_id": 1,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941a6b094882f4b73e5650f71432fd9739dd40414e67b48e99ebfc1a5e893745
+size 3132455816