Upload MT5ForConditionalGeneration

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "sj/mt5-small-ko",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "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": "mt5",
+  "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,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 73356,
+  "vocabtrimmer": {
+    "mining_config": {
+      "dataset": "vocabtrimmer/mc4_validation",
+      "dataset_column": "text",
+      "dataset_name": "ko",
+      "dataset_split": "validation",
+      "language": "ko",
+      "min_frequency": 2,
+      "target_vocab_size": null
+    },
+    "stats": {
+      "compression_rate_embedding": 29.329260491299898,
+      "compression_rate_full": 53.38313542168039,
+      "parameter_size_embedding/raw": 384172032,
+      "parameter_size_embedding/trimmed": 112674816,
+      "parameter_size_full/raw": 582401280,
+      "parameter_size_full/trimmed": 310904064,
+      "vocab_size/raw": 250112,
+      "vocab_size/trimmed": 73356
+    }
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1474fe650dd63e290e32a0506efe4b5c1e3a6367cef4762c4d0da6d8bcff7f1e
+size 1243649896