{
  "architectures": [
    "EvaGptForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "bos_token_id": 3,
  "dtype": "bfloat16",
  "eos_token_id": 3,
  "experts_per_token": 4,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initial_context_length": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "layer_types": [
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "model_type": "eva_gpt",
  "num_attention_heads": 32,
  "num_experts_per_tok": 1,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "num_local_experts": 1,
  "output_router_logits": false,
  "pad_token_id": 4,
  "quantization_config": {
    "modules_to_not_convert": [
      "model.layers.*.self_attn",
      "model.layers.*.mlp.router",
      "model.embed_tokens",
      "lm_head"
    ],
    "quant_method": "mxfp4"
  },
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 32.0,
    "original_max_position_embeddings": 4096,
    "rope_theta": 150000,
    "rope_type": "yarn"
  },
  "router_aux_loss_coef": 0.9,
  "sliding_window": 128,
  "swiglu_limit": 7.0,
  "tie_word_embeddings": false,
  "transformers_version": "5.0.0.dev0",
  "use_cache": true,
  "vocab_size": 200022
}