Update config.json

config.json

@@ -1,30 +1,23 @@
 {
   "model_type": "gpt2",
   "architectures": ["GPT2LMHeadModel"],
-  "tokenizer_config": {
-    "bos_token_id": 50256,
-    "eos_token_id": 50256,
-    "n_positions": 2048
-  },
-  "config": {
-    "activation_function": "gelu_new",
-    "n_ctx": 2048,
-    "n_embd": 2048,
-    "n_head": 16,
-    "n_layer": 24,
-    "n_positions": 2048,
-    "n_special": 0,
-    "attn_pdrop": 0.1,
-    "embd_pdrop": 0.1,
-    "initializer_range": 0.02,
-    "layer_norm_epsilon": 1e-05,
-    "resid_pdrop": 0.1,
-    "summary_activation": null,
-    "summary_first_dropout": 0.1,
-    "summary_proj_to_labels": true,
-    "summary_type": "cls_index",
-    "summary_use_proj": true
-  },
+  "activation_function": "gelu_new",
+  "n_ctx": 2048,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "n_special": 0,
+  "attn_pdrop": 0.1,
+  "embd_pdrop": 0.1,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
   "task_specific_params": {
     "conversational": {
       "max_length": 1024,
@@ -69,11 +62,16 @@
     "max_neurons": 250000,
     "max_sequence_length": 1024,
     "min_epochs_before_growth": 5,
-    "model_filename": "tf_model.h5",
+    "model_filename": "pytorch_model.bin",
     "num_embeddings": 25000,
     "pruning_improvement_threshold": 0.005,
     "some_adaptation_rate": 0.05,
     "stability_threshold": 0.02,
     "start_token_index": 2
+  },
+  "tokenizer_config": {
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "n_positions": 2048
   }
 }