Update config.json

config.json

@@ -1,158 +1,159 @@
-{
-  "_name_or_path": "ayjays132/CustomGPT2Conversational",
-  "activation_function": "gelu_new",
-  "advanced_model_options": {
-    "contextual_embeddings": {
-      "approaches": [
-        "contextual_attention_mechanisms",
-        "semantic_embedding_regularization"
-      ],
-      "enable": true
-    },
-    "dynamic_adaptation": {
-      "enable": true,
-      "techniques": [
-        "adaptive_layer_dropping",
-        "dynamic_context_window"
-      ]
-    },
-    "innovative_neuron_growth": {
-      "enable": true,
-      "strategies": [
-        "selective_neuron_pruning",
-        "progressive_neuron_expansion"
-      ]
-    },
-    "memory_optimization": {
-      "enable": true,
-      "methods": [
-        "gradient_checkpointing",
-        "memory-efficient_attention"
-      ]
-    },
-    "meta_learning": {
-      "approaches": [
-        "meta_learning_rate_adjustment",
-        "online_adaptation"
-      ],
-      "enable": true
-    },
-    "secret_advanced_options": {
-      "adaptive_token_embedding": {
-        "enable": true,
-        "strategies": [
-          "dynamic_embedding_resizing",
-          "contextual_embedding_scaling"
-        ]
-      },
-      "future_context_prediction": {
-        "enable": true,
-        "techniques": [
-          "lookahead_context_integration",
-          "predictive_attention_mechanisms"
-        ]
-      },
-      "multi_modal_integration": {
-        "enable": true,
-        "methods": [
-          "text_image_alignment",
-          "cross_modal_attention"
-        ]
-      }
-    }
-  },
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50267,
-  "context_window": 20,
-  "contextual_embedding_dim": 1024,
-  "device": "cuda",
-  "dropout_rate": 0.1,
-  "early_stopping": true,
-  "embd_pdrop": 0.1,
-  "embedding_dim": 1024,
-  "eos_token_id": 50267,
-  "hidden_dim": 1024,
-  "initializer_range": 0.02,
-  "innovative_growth_capacity": 50000,
-  "integration_settings": {
-    "config_name": "config.json",
-    "load_from_transformers": true,
-    "pytorch_dump_folder_path": "./model_save",
-    "pytorch_model_bin_name": "pytorch_model.bin"
-  },
-  "layer_norm_epsilon": 1e-05,
-  "max_length": 1024,
-  "max_memory_size": 100000,
-  "max_neurons": 100,
-  "meta_learning_rate": 0.001,
-  "min_length": 50,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
-  "n_inner": null,
-  "n_layer": 24,
-  "n_positions": 1024,
-  "no_repeat_ngram_size": 2,
-  "num_beams": 5,
-  "num_embeddings": 50257,
-  "num_heads": 64,
-  "num_layers": 24,
-  "output_attentions": true,
-  "output_hidden_states": true,
-  "pad_token_id": 50267,
-  "planning_enabled": true,
-  "planning_layers": 2,
-  "reasoning_enabled": true,
-  "reasoning_layers": 2,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "sep_token_id": 50267,
-  "special_tokens": {
-    "additional_special_tokens": [
-      "<greeting>",
-      "<farewell>",
-      "<thank>",
-      "<apology>"
-    ],
-    "bos_token": "<bos>",
-    "cls_token": "<cls>",
-    "eos_token": "<eos>",
-    "mask_token": "<mask>",
-    "pad_token": "<pad>",
-    "sep_token": "<sep>",
-    "unk_token": "<unk>"
-  },
-  "state_shape": null,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "target_q_model": null,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "early_stopping": true,
-      "length_penalty": 1.0,
-      "max_length": 2048,
-      "min_length": 64,
-      "no_repeat_ngram_size": 2,
-      "num_beams": 8,
-      "num_return_sequences": 3,
-      "repetition_penalty": 1.2,
-      "temperature": 0.9,
-      "top_k": 50,
-      "top_p": 0.95
-    }
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
-  "use_cache": true,
-  "vocab_size": 50257
-}
+{
+  "_name_or_path": "ayjays132/CustomGPT2Conversational",
+  "model_type": "gpt2",
+  "activation_function": "gelu_new",
+  "advanced_model_options": {
+    "contextual_embeddings": {
+      "approaches": [
+        "contextual_attention_mechanisms",
+        "semantic_embedding_regularization"
+      ],
+      "enable": true
+    },
+    "dynamic_adaptation": {
+      "enable": true,
+      "techniques": [
+        "adaptive_layer_dropping",
+        "dynamic_context_window"
+      ]
+    },
+    "innovative_neuron_growth": {
+      "enable": true,
+      "strategies": [
+        "selective_neuron_pruning",
+        "progressive_neuron_expansion"
+      ]
+    },
+    "memory_optimization": {
+      "enable": true,
+      "methods": [
+        "gradient_checkpointing",
+        "memory-efficient_attention"
+      ]
+    },
+    "meta_learning": {
+      "approaches": [
+        "meta_learning_rate_adjustment",
+        "online_adaptation"
+      ],
+      "enable": true
+    },
+    "secret_advanced_options": {
+      "adaptive_token_embedding": {
+        "enable": true,
+        "strategies": [
+          "dynamic_embedding_resizing",
+          "contextual_embedding_scaling"
+        ]
+      },
+      "future_context_prediction": {
+        "enable": true,
+        "techniques": [
+          "lookahead_context_integration",
+          "predictive_attention_mechanisms"
+        ]
+      },
+      "multi_modal_integration": {
+        "enable": true,
+        "methods": [
+          "text_image_alignment",
+          "cross_modal_attention"
+        ]
+      }
+    }
+  },
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50267,
+  "context_window": 20,
+  "contextual_embedding_dim": 1024,
+  "device": "cuda",
+  "dropout_rate": 0.1,
+  "early_stopping": true,
+  "embd_pdrop": 0.1,
+  "embedding_dim": 1024,
+  "eos_token_id": 50267,
+  "hidden_dim": 1024,
+  "initializer_range": 0.02,
+  "innovative_growth_capacity": 50000,
+  "integration_settings": {
+    "config_name": "config.json",
+    "load_from_transformers": true,
+    "pytorch_dump_folder_path": "./model_save",
+    "pytorch_model_bin_name": "pytorch_model.bin"
+  },
+  "layer_norm_epsilon": 1e-05,
+  "max_length": 1024,
+  "max_memory_size": 100000,
+  "max_neurons": 100,
+  "meta_learning_rate": 0.001,
+  "min_length": 50,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 5,
+  "num_embeddings": 50257,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_attentions": true,
+  "output_hidden_states": true,
+  "pad_token_id": 50267,
+  "planning_enabled": true,
+  "planning_layers": 2,
+  "reasoning_enabled": true,
+  "reasoning_layers": 2,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "sep_token_id": 50267,
+  "special_tokens": {
+    "additional_special_tokens": [
+      "<greeting>",
+      "<farewell>",
+      "<thank>",
+      "<apology>"
+    ],
+    "bos_token": "<bos>",
+    "cls_token": "<cls>",
+    "eos_token": "<eos>",
+    "mask_token": "<mask>",
+    "pad_token": "<pad>",
+    "sep_token": "<sep>",
+    "unk_token": "<unk>"
+  },
+  "state_shape": null,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "target_q_model": null,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "early_stopping": true,
+      "length_penalty": 1.0,
+      "max_length": 2048,
+      "min_length": 64,
+      "no_repeat_ngram_size": 2,
+      "num_beams": 8,
+      "num_return_sequences": 3,
+      "repetition_penalty": 1.2,
+      "temperature": 0.9,
+      "top_k": 50,
+      "top_p": 0.95
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}