config.json

{
  "_name_or_path": "ayjays132/Phillnet2",
  "activation_function": "gelu_new",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "config": {
    "activation_function": "gelu_new",
    "attn_pdrop": 0.1,
    "embd_pdrop": 0.1,
    "initializer_range": 0.02,
    "layer_norm_epsilon": 1e-05,
    "n_ctx": 2048,
    "n_embd": 2048,
    "n_head": 16,
    "n_layer": 24,
    "n_positions": 2048,
    "n_special": 0,
    "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
  },
  "custom_params": {
    "DEFAULT_ADAPTATION_RATE": 0.05,
    "DEFAULT_MAX_NEURONS": 242798,
    "actual_vocab_size": 25000,
    "adaptation_rate": 0.05,
    "complexity_metric": null,
    "desired_improvement_rate": 0.02,
    "ecosystem_dynamics": {
      "environmental_volatility": 0.1,
      "resource_pool": 1
    },
    "embedding_dim": 2048,
    "eval_interval": 10,
    "gamma": 0.99,
    "growth_improvement_threshold": 0.01,
    "hidden_dim": 2048,
    "initial_neuron_count": 105000,
    "innovative_growth_net": {
      "adaptation_rate": 0.05,
      "initial_capacity": 250000,
      "input_size": 2048
    },
    "input_dimension": 2048,
    "learning_rate": 0.001,
    "low_stability_threshold": 0.01,
    "max_complexity": 5000000,
    "max_neurons": 800000,
    "max_sequence_length": 2048,
    "min_epochs_before_growth": 5,
    "model_filename": "pytorch_model.bin",
    "num_classes": 25000,
    "num_embeddings": 25000,
    "num_heads": 64,
    "num_words": 25000,
    "pruning_improvement_threshold": 0.005,
    "sequence_length": 1024,
    "some_adaptation_rate": 0.05,
    "some_intermediate_size": 2048,
    "stability_threshold": 0.02,
    "start_token_index": 2,
    "update_freq": 100,
    "vocab_size": 25000,
    "weight_decay": 0.005
  },
  "datasets": [
    "vicgalle/alpaca-gpt4"
  ],
  "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"
  ],
  "task_specific_params": {
    "conversational": {
      "early_stopping": true,
      "length_penalty": 1.5,
      "max_length": 1024,
      "min_length": 20,
      "no_repeat_ngram_size": 3,
      "num_beams": 5,
      "temperature": 0.7,
      "top_k": 50,
      "top_p": 0.9
    }
  },
  "tokenizer_config": {
    "bos_token_id": 50256,
    "eos_token_id": 50256,
    "n_positions": 2048
  },
  "torch_dtype": "float32",
  "transformers_version": "4.37.2",
  "use_cache": true,
  "vocab_size": 50257
}