Hugging Face's logo

playable
/
playable1-int4-bfloat16

Safetensors
qwen2
quark
Model card Files
xet
Community
playable1-int4-bfloat16
File size: 3,459 Bytes 
1356f91
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
 
{
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "dtype": "float16",
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "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"
  ],
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "quantization_config": {
    "algo_config": [
      {
        "model_decoder_layers": "model.layers",
        "name": "awq",
        "scaling_layers": [
          {
            "inp": "self_attn.q_proj",
            "layers": [
              "self_attn.q_proj",
              "self_attn.k_proj",
              "self_attn.v_proj"
            ],
            "module2inspect": "self_attn",
            "prev_op": "input_layernorm"
          },
          {
            "inp": "self_attn.o_proj",
            "layers": [
              "self_attn.o_proj"
            ],
            "prev_op": "self_attn.v_proj"
          },
          {
            "inp": "mlp.gate_proj",
            "layers": [
              "mlp.gate_proj",
              "mlp.up_proj"
            ],
            "module2inspect": "mlp",
            "prev_op": "post_attention_layernorm"
          },
          {
            "inp": "mlp.down_proj",
            "layers": [
              "mlp.down_proj"
            ],
            "prev_op": "mlp.up_proj"
          }
        ]
      }
    ],
    "exclude": [],
    "export": {
      "kv_cache_group": [
        "*k_proj",
        "*v_proj"
      ],
      "min_kv_scale": 0.0,
      "pack_method": "reorder",
      "weight_format": "real_quantized",
      "weight_merge_groups": null
    },
    "global_quant_config": {
      "bias": null,
      "input_tensors": null,
      "output_tensors": null,
      "target_device": null,
      "weight": {
        "ch_axis": -1,
        "dtype": "uint4",
        "group_size": 128,
        "is_dynamic": false,
        "is_scale_quant": false,
        "mx_element_dtype": null,
        "observer_cls": "PerGroupMinMaxObserver",
        "qscheme": "per_group",
        "round_method": "half_even",
        "scale_calculation_mode": null,
        "scale_format": null,
        "scale_type": "float",
        "symmetric": false
      }
    },
    "kv_cache_quant_config": {},
    "layer_quant_config": {},
    "layer_type_quant_config": {},
    "quant_method": "quark",
    "quant_mode": "eager_mode",
    "softmax_quant_spec": null,
    "version": "0.10"
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}