Hugging Face's logo

EjZhou
/
test-v4

Safetensors
qwen3_5_text
compressed-tensors
Model card Files
xet
 Community
test-v4
File size: 5,060 Bytes
6445fb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
{
  "architectures": [
    "Qwen3_5ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_output_gate": true,
  "dtype": "bfloat16",
  "eos_token_id": 248044,
  "full_attention_interval": 4,
  "head_dim": 256,
  "hidden_act": "silu",
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 9216,
  "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_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": 32,
  "linear_value_head_dim": 128,
  "mamba_ssm_dtype": "float32",
  "max_position_embeddings": 262144,
  "mlp_only_layers": [],
  "model_type": "qwen3_5_text",
  "mtp_num_hidden_layers": 1,
  "mtp_use_dedicated_embeddings": false,
  "num_attention_heads": 16,
  "num_hidden_layers": 32,
  "num_key_value_heads": 4,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 32,
          "num_bits": 4,
          "observer": "mse",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "group",
          "symmetric": true,
          "type": "int",
          "zp_dtype": null
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.layers.0.linear_attn.in_proj_b",
      "model.layers.0.linear_attn.in_proj_a",
      "model.layers.1.linear_attn.in_proj_b",
      "model.layers.1.linear_attn.in_proj_a",
      "model.layers.2.linear_attn.in_proj_b",
      "model.layers.2.linear_attn.in_proj_a",
      "model.layers.4.linear_attn.in_proj_b",
      "model.layers.4.linear_attn.in_proj_a",
      "model.layers.5.linear_attn.in_proj_b",
      "model.layers.5.linear_attn.in_proj_a",
      "model.layers.6.linear_attn.in_proj_b",
      "model.layers.6.linear_attn.in_proj_a",
      "model.layers.8.linear_attn.in_proj_b",
      "model.layers.8.linear_attn.in_proj_a",
      "model.layers.9.linear_attn.in_proj_b",
      "model.layers.9.linear_attn.in_proj_a",
      "model.layers.10.linear_attn.in_proj_b",
      "model.layers.10.linear_attn.in_proj_a",
      "model.layers.12.linear_attn.in_proj_b",
      "model.layers.12.linear_attn.in_proj_a",
      "model.layers.13.linear_attn.in_proj_b",
      "model.layers.13.linear_attn.in_proj_a",
      "model.layers.14.linear_attn.in_proj_b",
      "model.layers.14.linear_attn.in_proj_a",
      "model.layers.16.linear_attn.in_proj_b",
      "model.layers.16.linear_attn.in_proj_a",
      "model.layers.17.linear_attn.in_proj_b",
      "model.layers.17.linear_attn.in_proj_a",
      "model.layers.18.linear_attn.in_proj_b",
      "model.layers.18.linear_attn.in_proj_a",
      "model.layers.20.linear_attn.in_proj_b",
      "model.layers.20.linear_attn.in_proj_a",
      "model.layers.21.linear_attn.in_proj_b",
      "model.layers.21.linear_attn.in_proj_a",
      "model.layers.22.linear_attn.in_proj_b",
      "model.layers.22.linear_attn.in_proj_a",
      "model.layers.24.linear_attn.in_proj_b",
      "model.layers.24.linear_attn.in_proj_a",
      "model.layers.25.linear_attn.in_proj_b",
      "model.layers.25.linear_attn.in_proj_a",
      "model.layers.26.linear_attn.in_proj_b",
      "model.layers.26.linear_attn.in_proj_a",
      "model.layers.28.linear_attn.in_proj_b",
      "model.layers.28.linear_attn.in_proj_a",
      "model.layers.29.linear_attn.in_proj_b",
      "model.layers.29.linear_attn.in_proj_a",
      "model.layers.30.linear_attn.in_proj_b",
      "model.layers.30.linear_attn.in_proj_a",
      "lm_head",
      "mtp.fc"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.14.1.dev20+g5d2f568"
  },
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "mrope_interleaved": true,
    "mrope_section": [
      11,
      11,
      10
    ],
    "partial_rotary_factor": 0.25,
    "rope_theta": 10000000,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "use_cache": true,
  "vocab_size": 248320
}