init repo

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "CoLwithBert"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "do_voken_cls": true,
+  "do_voken_ctr": false,
+  "do_voken_reg": false,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "shared_head": false,
+  "type_vocab_size": 2,
+  "verbose": true,
+  "vocab_size": 30522,
+  "voken_dim": null,
+  "voken_size": 50000
+}

eval_results.json

@@ -0,0 +1,4 @@
+{
+    "perplexity": 8.294562339782715,
+    "voken_loss": 4.667348582169105
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f655dd4cefefb6ec91cdfc09c38b4188325d8252b19510c00258c24ca1b9e86
+size 244102943

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "model_max_length": 512}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be6f25a803afe0a9d9ed00fb3245c16b491546c8a825fbb0d0f0a73444a65364
+size 2095