{
    "architectures": [
        "GptOssForCausalLM"
    ],
    "attention_bias": true,
    "attention_dropout": 0.0,
    "bos_token_id": null,
    "dtype": "bfloat16",
    "eos_token_id": [
        200002,
        199999
    ],
    "experts_per_token": 4,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 2880,
    "initial_context_length": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 2880,
    "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",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "full_attention"
    ],
    "max_position_embeddings": 131072,
    "model_type": "gpt_oss",
    "num_attention_heads": 64,
    "num_experts_per_tok": 4,
    "num_hidden_layers": 24,
    "num_key_value_heads": 8,
    "num_local_experts": 32,
    "output_router_logits": false,
    "pad_token_id": 199999,
    "quantization": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.mlp.router": {
            "group_size": 64,
            "bits": 8
        }
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.mlp.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.mlp.router": {
            "group_size": 64,
            "bits": 8
        }
    },
    "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",
        "truncate": false
    },
    "router_aux_loss_coef": 0.9,
    "sliding_window": 128,
    "swiglu_limit": 7.0,
    "tie_word_embeddings": false,
    "transformers_version": "5.3.0",
    "use_cache": true,
    "vocab_size": 201088
}