Upload BertForMaskedLM

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "5CD-AI/twhin-bert-large-viso-20kvocab-uit-10epochs",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "relative_key",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 20002,
+  "vocabtrimmer": {
+    "mining_config": {
+      "dataset": "vocabtrimmer/mc4_validation",
+      "dataset_column": "text",
+      "dataset_name": "en",
+      "dataset_split": "validation",
+      "language": "en",
+      "min_frequency": 2,
+      "target_vocab_size": 20000
+    },
+    "stats": {
+      "compression_rate_embedding": 8.000735994112047,
+      "compression_rate_full": 58.03015244164301,
+      "parameter_size_embedding/raw": 256002048,
+      "parameter_size_embedding/trimmed": 20482048,
+      "parameter_size_full/raw": 561712786,
+      "parameter_size_full/trimmed": 325962786,
+      "vocab_size/raw": 250002,
+      "vocab_size/trimmed": 20002
+    }
+  }
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ed1eeeb80dd55ee8496d498eac9a4206954dc2dda64670d8273ab59e646d61
+size 1303901552