8bit/config.json

{
    "architectures": [
        "Qwen3_5ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_output_gate": true,
    "bos_token_id": null,
    "dtype": "bfloat16",
    "eos_token_id": 248044,
    "full_attention_interval": 4,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 3584,
    "layer_types": [
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention"
    ],
    "linear_conv_kernel_dim": 4,
    "linear_key_head_dim": 128,
    "linear_num_key_heads": 16,
    "linear_num_value_heads": 16,
    "linear_value_head_dim": 128,
    "mamba_ssm_dtype": "float32",
    "max_position_embeddings": 262144,
    "mlp_only_layers": [],
    "model_type": "qwen3_5",
    "mtp_num_hidden_layers": 1,
    "mtp_use_dedicated_embeddings": false,
    "num_attention_heads": 8,
    "num_hidden_layers": 24,
    "num_key_value_heads": 2,
    "pad_token_id": null,
    "partial_rotary_factor": 0.25,
    "quantization": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
        "mrope_interleaved": true,
        "mrope_section": [
            11,
            11,
            10
        ],
        "partial_rotary_factor": 0.25,
        "rope_theta": 10000000,
        "type": "default"
    },
    "tie_word_embeddings": true,
    "transformers_version": "5.17.0",
    "use_cache": true,
    "vocab_size": 248320
}