config.json

{
  "_attn_implementation_autoset": true,
  "activation_function": "gelu_new",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "bos_token_id": 50256,
  "eos_token_id": 50256,
  "hidden_size": 1024,
  "n_embd": 1024,
  "n_head": 16,
  "n_layer": 24,
  "n_inner": 4096,
  "n_ctx": 1024,
  "n_positions": 2048,
  "n_special": 0,
  "num_moe_experts": 16,
  "moe_load_balancing_weight": 0.01,
  "moe_router_z_loss_weight": 0.001,
  "moe_top_k": 4,
  "max_neurons": 8192,
  "max_position_embeddings": 1024,
  "pad_token_id": 50256,
  "predict_special_tokens": true,
  "reward_loss_weight": 0.1,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "task_specific_params": {
    "text-generation": {
      "do_sample": true,
      "max_length": 50
    }
  },
  "torch_dtype": "float32",
  "vocab_size": 50308,
  "model_type": "gpt2"
}