Upload T5ForConditionalGeneration

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "analogy_models/opt-125m-analogy-epoch10/model",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "dense_act_fn": "relu",
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "dropout_rate": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "ffn_dim": 3072,
+  "finetuing_config": {
+    "batch_size": 32,
+    "data": "relbert/semeval2012_relational_similarity",
+    "epoch": 10,
+    "gradient_accumulation_steps": 1,
+    "learning_rate": 0.0001,
+    "model": "facebook/opt-125m",
+    "random_seed": 42,
+    "template": "<subj-a> is to <obj-a> what <subj-b> is to <obj-b>"
+  },
+  "init_std": 0.02,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_elementwise_affine": true,
+  "layer_norm_epsilon": 1e-06,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "t5",
+  "num_decoder_layers": 6,
+  "num_heads": 12,
+  "num_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9225b427146a091257a647cf398db7c712f252a942515af23723ef0b3fa639
+size 607617881