config.json

{
    "architectures": [
        "SmolLM3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": 128012,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "layer_types": [
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention"
    ],
    "max_position_embeddings": 65536,
    "max_window_layers": 28,
    "mlp_bias": false,
    "model_type": "smollm3",
    "no_rope_layer_interval": 4,
    "no_rope_layers": [
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        0
    ],
    "num_attention_heads": 16,
    "num_hidden_layers": 36,
    "num_key_value_heads": 4,
    "pad_token_id": 128004,
    "pretraining_tp": 2,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 5000000.0,
    "sliding_window": null,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.54.0.dev0",
    "use_cache": false,
    "use_sliding_window": false,
    "vocab_size": 128256,
    "quantization_config": {
        "quant_method": "exl3",
        "version": "0.0.4",
        "bits": 2.5,
        "head_bits": 6,
        "calibration": {
            "rows": 100,
            "cols": 2048
        },
        "out_scales": "auto"
    }
}