Upload 8 files

config.json

@@ -1,84 +1,77 @@
 {
-  "_name_or_path": "ayjays132/CustomGPT2Conversational",
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "model_type": "gpt2",
+  "architectures": ["GPT2LMHeadModel"],
+  "tokenizer_config": {
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "n_positions": 2048
+  },
   "config": {
     "activation_function": "gelu_new",
-    "attn_pdrop": 0.1,
-    "embd_pdrop": 0.1,
-    "gradient_checkpointing": true,
-    "initializer_range": 0.02,
-    "layer_norm_epsilon": 1e-05,
     "n_ctx": 2048,
     "n_embd": 2048,
     "n_head": 16,
-    "n_layer": 36,
+    "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,
-    "scale_attn_weights": true,
-    "use_cache": true,
-    "vocab_size": 50257
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true
   },
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "initializer_range": 0.02,
-  "language": "en",
-  "layer_norm_epsilon": 1e-05,
-  "library_name": "transformers",
-  "license": "apache-2.0",
-  "metrics": [
-    "perplexity",
-    "accuracy"
-  ],
-  "model_type": "gpt2",
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "pipeline_tag": "conversational",
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "tags": [
-    "conversational",
-    "state-of-the-art"
-  ],
   "task_specific_params": {
     "conversational": {
-      "do_sample": true,
-      "early_stopping": true,
-      "frequency_penalty": 0.5,
-      "length_penalty": 2.0,
       "max_length": 1024,
       "min_length": 20,
-      "no_repeat_ngram_size": 3,
+      "length_penalty": 1.5,
       "num_beams": 5,
-      "presence_penalty": 0.5,
+      "early_stopping": true,
+      "no_repeat_ngram_size": 3,
       "temperature": 0.7,
-      "top_k": 40,
-      "top_p": 0.95
+      "top_k": 50,
+      "top_p": 0.9
     }
   },
-  "tokenizer_config": {
-    "bos_token_id": 50256,
-    "eos_token_id": 50256,
-    "n_positions": 2048,
-    "padding_side": "left",
-    "truncation_side": "right"
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
-  "use_cache": true,
-  "vocab_size": 50257
+  "transformers_version": "4.34.0",
+  "language": ["en"],
+  "tags": ["conversational"],
+  "metrics": ["perplexity", "accuracy"],
+  "pipeline_tag": "conversational",
+  "library_name": "transformers",
+  "datasets": ["vicgalle/alpaca-gpt4"],
+  "license": "apache-2.0",
+  "custom_params": {
+    "adaptation_rate": 0.05,
+    "desired_improvement_rate": 0.02,
+    "ecosystem_dynamics": {
+      "environmental_volatility": 0.1,
+      "resource_pool": 1
+    },
+    "growth_improvement_threshold": 0.01,
+    "hidden_dim": 2048,
+    "initial_neuron_count": 5000,
+    "innovative_growth_net": {
+      "adaptation_rate": 0.05,
+      "initial_capacity": 250000,
+      "input_size": 2048
+    },
+    "input_dimension": 768,
+    "low_stability_threshold": 0.01,
+    "max_complexity": 10000,
+    "max_neurons": 250000,
+    "max_sequence_length": 1024,
+    "min_epochs_before_growth": 5,
+    "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
+  }
 }

special_tokens_map.json

@@ -1,125 +1,51 @@
 {
   "additional_special_tokens": [
-    "<extra_id_0>",
-    "<extra_id_1>",
-    "<extra_id_2>",
-    "<extra_id_3>",
-    "<extra_id_4>",
-    "<extra_id_5>",
-    "<extra_id_6>",
-    "<extra_id_7>",
-    "<extra_id_8>",
-    "<extra_id_9>",
-    "<extra_id_10>",
-    "<extra_id_11>",
-    "<extra_id_12>",
-    "<extra_id_13>",
-    "<extra_id_14>",
-    "<extra_id_15>",
-    "<extra_id_16>",
-    "<extra_id_17>",
-    "<extra_id_18>",
-    "<extra_id_19>",
-    "<extra_id_20>",
-    "<extra_id_21>",
-    "<extra_id_22>",
-    "<extra_id_23>",
-    "<extra_id_24>",
-    "<extra_id_25>",
-    "<extra_id_26>",
-    "<extra_id_27>",
-    "<extra_id_28>",
-    "<extra_id_29>",
-    "<extra_id_30>",
-    "<extra_id_31>",
-    "<extra_id_32>",
-    "<extra_id_33>",
-    "<extra_id_34>",
-    "<extra_id_35>",
-    "<extra_id_36>",
-    "<extra_id_37>",
-    "<extra_id_38>",
-    "<extra_id_39>",
-    "<extra_id_40>",
-    "<extra_id_41>",
-    "<extra_id_42>",
-    "<extra_id_43>",
-    "<extra_id_44>",
-    "<extra_id_45>",
-    "<extra_id_46>",
-    "<extra_id_47>",
-    "<extra_id_48>",
-    "<extra_id_49>",
-    "<extra_id_50>",
-    "<extra_id_51>",
-    "<extra_id_52>",
-    "<extra_id_53>",
-    "<extra_id_54>",
-    "<extra_id_55>",
-    "<extra_id_56>",
-    "<extra_id_57>",
-    "<extra_id_58>",
-    "<extra_id_59>",
-    "<extra_id_60>",
-    "<extra_id_61>",
-    "<extra_id_62>",
-    "<extra_id_63>",
-    "<extra_id_64>",
-    "<extra_id_65>",
-    "<extra_id_66>",
-    "<extra_id_67>",
-    "<extra_id_68>",
-    "<extra_id_69>",
-    "<extra_id_70>",
-    "<extra_id_71>",
-    "<extra_id_72>",
-    "<extra_id_73>",
-    "<extra_id_74>",
-    "<extra_id_75>",
-    "<extra_id_76>",
-    "<extra_id_77>",
-    "<extra_id_78>",
-    "<extra_id_79>",
-    "<extra_id_80>",
-    "<extra_id_81>",
-    "<extra_id_82>",
-    "<extra_id_83>",
-    "<extra_id_84>",
-    "<extra_id_85>",
-    "<extra_id_86>",
-    "<extra_id_87>",
-    "<extra_id_88>",
-    "<extra_id_89>",
-    "<extra_id_90>",
-    "<extra_id_91>",
-    "<extra_id_92>",
-    "<extra_id_93>",
-    "<extra_id_94>",
-    "<extra_id_95>",
-    "<extra_id_96>",
-    "<extra_id_97>",
-    "<extra_id_98>",
-    "<extra_id_99>"
+    {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
   ],
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3738aeb98a27be9bd050d9078f85b6b6fd7ab94dc5f112b747adcdc714b0a421
-size 73332137
+oid sha256:e173edee502038fb1ca5955c8c0989741bae978783c0b0f04e922eabd97c08ae
+size 9133154