Upload MT5ForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "lmqg_output/trimmed_qa/mt5-small-trimmed-ru-90000-ruquad-qg/best_model",
+  "_name_or_path": "lmqg_output/trimmed_qg/mt5-small-trimmed-ru-90000-ruquad-qg/best_model",
   "add_prefix": false,
   "architectures": [
     "MT5ForConditionalGeneration"
@@ -28,7 +28,7 @@
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
   "use_cache": true,
-  "vocab_size": 15002,
+  "vocab_size": 90002,
   "vocabtrimmer": {
     "mining_config": {
       "dataset": "vocabtrimmer/mc4_validation",
@@ -37,17 +37,17 @@
       "dataset_split": "validation",
       "language": "ru",
       "min_frequency": 2,
-      "target_vocab_size": 15000
+      "target_vocab_size": 90000
     },
     "stats": {
-      "compression_rate_embedding": 5.9977130245649946,
-      "compression_rate_full": 19.796036980450133,
+      "compression_rate_embedding": 35.984279042988746,
+      "compression_rate_full": 45.38096166056395,
       "parameter_size_embedding/raw": 256114688,
-      "parameter_size_embedding/trimmed": 15361024,
+      "parameter_size_embedding/trimmed": 92161024,
       "parameter_size_full/raw": 300176768,
-      "parameter_size_full/trimmed": 59423104,
+      "parameter_size_full/trimmed": 136223104,
       "vocab_size/raw": 250112,
-      "vocab_size/trimmed": 15001
+      "vocab_size/trimmed": 90001
     }
   }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b72a27251ecdb427fda1fc2c56c646df3a3997c78d2dfcdadd71961327e818
-size 237760197
+oid sha256:d1e298ed57660592933fc55dc994eb4207578a69aeca401ef2f9c79f408cbae6
+size 544961925