olive-recipes/deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/aitk/deepseek_vitis_ai_config.json at main · microsoft/olive-recipes · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
{
    "input_model": {
        "type": "HfModel",
        "model_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
    },
    "systems": {
        "local_system": {
            "type": "LocalSystem",
            "accelerators": [
                {
                    "device": "cpu",
                    "execution_providers": [
                        "CPUExecutionProvider"
                    ]
                }
            ]
        }
    },
    "data_configs": [
    ],
    "passes": {
        "qq": {
            "type": "QuarkQuantization",
            "quant_scheme": "w_uint4_per_group_asym",
            "quant_algo": "awq",
            "dataset": "pileval_for_awq_benchmark",
            "data_type": "bfloat16",
            "num_calib_data": 128,
            "model_export": [ "hf_format" ],
            "exclude_layers": [  ],
            "quant_config": {
                "name": "awq",
                "scaling_layers": [
                    {
                        "prev_op": "input_layernorm",
                        "layers": [ "self_attn.q_proj", "self_attn.k_proj", "self_attn.v_proj" ],
                        "inp": "self_attn.q_proj",
                        "module2inspect": "self_attn"
                    },
                    { "prev_op": "self_attn.v_proj", "layers": [ "self_attn.o_proj" ], "inp": "self_attn.o_proj" },
                    {
                        "prev_op": "post_attention_layernorm",
                        "layers": [ "mlp.gate_proj", "mlp.up_proj" ],
                        "inp": "mlp.gate_proj",
                        "module2inspect": "mlp"
                    },
                    { "prev_op": "mlp.up_proj", "layers": [ "mlp.down_proj" ], "inp": "mlp.down_proj" }
                ],
                "model_decoder_layers": "model.layers"
            }
        },
        "mg": { "type": "VitisGenerateModelLLM", "packed_const": false, "cpu_only": false }
    },
    "target": "local_system",
    "log_severity_level": 1,
    "output_dir": "model/deepseek",
    "cache_dir": "cache",
    "no_artifacts": true,
    "evaluate_input_model": false
}