config.json

{
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "model_type": "gpt2",
  "vocab_size": 50257,
  "n_positions": 1024,
  "n_embd": 512,
  "n_layer": 8,
  "n_head": 8,
  "n_inner": 2048,
  "activation_function": "gelu_new",
  "resid_pdrop": 0.1,
  "embd_pdrop": 0.1,
  "attn_pdrop": 0.1,
  "layer_norm_epsilon": 0.00001,
  "initializer_range": 0.02,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "summary_activation": null,
  "summary_proj_to_labels": true,
  "summary_first_dropout": 0.1,
  "scale_attn_weights": true,
  "use_cache": true,
  "bos_token_id": 50256,
  "eos_token_id": 50256,
  "transformers_version": "4.36.0",
  "grpo_config": {
    "group_size": 8,
    "kl_penalty": 0.1,
    "advantage_clip": 2,
    "mask_intensity": 0.8,
    "feedback_window": 50
  },
  "vae_config": {
    "latent_dim": 32,
    "beta": 0.01,
    "filter_threshold": 0.7
  },
  "cache_config": {
    "cache_size": 512,
    "reuse_threshold": 0.9
  }
}