change

cog-pretrain.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea6f4164152bc58d23e24e48f7bf4187aad72a32e97ec4b3acc832fe183cbc2
+size 1021864

config.json

@@ -1,7 +1,7 @@
 {
   "encoder_model_path":  "/encoder/",
   "decoder_model_path":  "/decoder/",
-  "sentencepiece_model_path":"/decoder/cog-pretrain.model",
+  "sentencepiece_model_path":"cog-pretrain.model",
   "latent_size":256,
   "seed": 42, 
   "ratio_increase": 0.5, 
@@ -31,5 +31,46 @@
   "logger": true, 
   "checkpoint_callback": null,
   "enable_checkpointing": true, 
-  "process_position": 0
+  "process_position": 0,
+  "encoder":{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "type_vocab_size": 2,
+  "vocab_size": 21128
+},
+  "decoder":{
+    "num_layers":32,
+    "vocab_size":50048,
+    "hidden_size":1600,
+    "num_attention_heads":25,
+    "embedding_dropout_prob":0.1,
+    "attention_dropout_prob":0.1,
+    "output_dropout_prob":0.1,
+    "max_sequence_length":512,
+    "max_memory_length":512,
+    "latent_size":256,
+    "checkpoint_activations":false,
+    "checkpoint_num_layers":1,
+    "parallel_output":true,
+    "relative_encoding":true
 }
+}