Add model

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text

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": 7.818178176879883,
+    "voken_loss": 4.580071432837125
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a78cb17ee7b5f52ee05e5fce7c55f0e46b1c73fc4ee08b273b65b486271e65
+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:bb7a5156a268203138e5a9a055ef3257c965776747d1ff930e6d326ecd9e41fb
+size 1903