File size: 8,122 Bytes
f3d279e | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 | {
"architectures": [
"Qwen3VLTextModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 262144,
"model_type": "qwen3_vl_text",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": null,
"quantization_config": {
"add_skip_keys": false,
"dequantize_fp32": false,
"dynamic_loss_threshold": null,
"group_size": 0,
"hadamard_group_size": 128,
"is_integer": true,
"is_training": false,
"modules_dtype_dict": {},
"modules_quant_config": {},
"modules_to_not_convert": [
"layers.0.self_attn.q_norm.weight",
"layers.0.self_attn.k_norm.weight",
"layers.0.input_layernorm.weight",
"layers.0.post_attention_layernorm.weight",
"layers.1.self_attn.q_norm.weight",
"layers.1.self_attn.k_norm.weight",
"layers.1.input_layernorm.weight",
"layers.1.post_attention_layernorm.weight",
"layers.2.self_attn.q_norm.weight",
"layers.2.self_attn.k_norm.weight",
"layers.2.input_layernorm.weight",
"layers.2.post_attention_layernorm.weight",
"layers.3.self_attn.q_norm.weight",
"layers.3.self_attn.k_norm.weight",
"layers.3.input_layernorm.weight",
"layers.3.post_attention_layernorm.weight",
"layers.4.self_attn.q_norm.weight",
"layers.4.self_attn.k_norm.weight",
"layers.4.input_layernorm.weight",
"layers.4.post_attention_layernorm.weight",
"layers.5.self_attn.q_norm.weight",
"layers.5.self_attn.k_norm.weight",
"layers.5.input_layernorm.weight",
"layers.5.post_attention_layernorm.weight",
"layers.6.self_attn.q_norm.weight",
"layers.6.self_attn.k_norm.weight",
"layers.6.input_layernorm.weight",
"layers.6.post_attention_layernorm.weight",
"layers.7.self_attn.q_norm.weight",
"layers.7.self_attn.k_norm.weight",
"layers.7.input_layernorm.weight",
"layers.7.post_attention_layernorm.weight",
"layers.8.self_attn.q_norm.weight",
"layers.8.self_attn.k_norm.weight",
"layers.8.input_layernorm.weight",
"layers.8.post_attention_layernorm.weight",
"layers.9.self_attn.q_norm.weight",
"layers.9.self_attn.k_norm.weight",
"layers.9.input_layernorm.weight",
"layers.9.post_attention_layernorm.weight",
"layers.10.self_attn.q_norm.weight",
"layers.10.self_attn.k_norm.weight",
"layers.10.input_layernorm.weight",
"layers.10.post_attention_layernorm.weight",
"layers.11.self_attn.q_norm.weight",
"layers.11.self_attn.k_norm.weight",
"layers.11.input_layernorm.weight",
"layers.11.post_attention_layernorm.weight",
"layers.12.self_attn.q_norm.weight",
"layers.12.self_attn.k_norm.weight",
"layers.12.input_layernorm.weight",
"layers.12.post_attention_layernorm.weight",
"layers.13.self_attn.q_norm.weight",
"layers.13.self_attn.k_norm.weight",
"layers.13.input_layernorm.weight",
"layers.13.post_attention_layernorm.weight",
"layers.14.self_attn.q_norm.weight",
"layers.14.self_attn.k_norm.weight",
"layers.14.input_layernorm.weight",
"layers.14.post_attention_layernorm.weight",
"layers.15.self_attn.q_norm.weight",
"layers.15.self_attn.k_norm.weight",
"layers.15.input_layernorm.weight",
"layers.15.post_attention_layernorm.weight",
"layers.16.self_attn.q_norm.weight",
"layers.16.self_attn.k_norm.weight",
"layers.16.input_layernorm.weight",
"layers.16.post_attention_layernorm.weight",
"layers.17.self_attn.q_norm.weight",
"layers.17.self_attn.k_norm.weight",
"layers.17.input_layernorm.weight",
"layers.17.post_attention_layernorm.weight",
"layers.18.self_attn.q_norm.weight",
"layers.18.self_attn.k_norm.weight",
"layers.18.input_layernorm.weight",
"layers.18.post_attention_layernorm.weight",
"layers.19.self_attn.q_norm.weight",
"layers.19.self_attn.k_norm.weight",
"layers.19.input_layernorm.weight",
"layers.19.post_attention_layernorm.weight",
"layers.20.self_attn.q_norm.weight",
"layers.20.self_attn.k_norm.weight",
"layers.20.input_layernorm.weight",
"layers.20.post_attention_layernorm.weight",
"layers.21.self_attn.q_norm.weight",
"layers.21.self_attn.k_norm.weight",
"layers.21.input_layernorm.weight",
"layers.21.post_attention_layernorm.weight",
"layers.22.self_attn.q_norm.weight",
"layers.22.self_attn.k_norm.weight",
"layers.22.input_layernorm.weight",
"layers.22.post_attention_layernorm.weight",
"layers.23.self_attn.q_norm.weight",
"layers.23.self_attn.k_norm.weight",
"layers.23.input_layernorm.weight",
"layers.23.post_attention_layernorm.weight",
"layers.24.self_attn.q_norm.weight",
"layers.24.self_attn.k_norm.weight",
"layers.24.input_layernorm.weight",
"layers.24.post_attention_layernorm.weight",
"layers.25.self_attn.q_norm.weight",
"layers.25.self_attn.k_norm.weight",
"layers.25.input_layernorm.weight",
"layers.25.post_attention_layernorm.weight",
"layers.26.self_attn.q_norm.weight",
"layers.26.self_attn.k_norm.weight",
"layers.26.input_layernorm.weight",
"layers.26.post_attention_layernorm.weight",
"layers.27.self_attn.q_norm.weight",
"layers.27.self_attn.k_norm.weight",
"layers.27.input_layernorm.weight",
"layers.27.post_attention_layernorm.weight",
"layers.28.self_attn.q_norm.weight",
"layers.28.self_attn.k_norm.weight",
"layers.28.input_layernorm.weight",
"layers.28.post_attention_layernorm.weight",
"layers.29.self_attn.q_norm.weight",
"layers.29.self_attn.k_norm.weight",
"layers.29.input_layernorm.weight",
"layers.29.post_attention_layernorm.weight",
"layers.30.self_attn.q_norm.weight",
"layers.30.self_attn.k_norm.weight",
"layers.30.input_layernorm.weight",
"layers.30.post_attention_layernorm.weight",
"layers.31.self_attn.q_norm.weight",
"layers.31.self_attn.k_norm.weight",
"layers.31.input_layernorm.weight",
"layers.31.post_attention_layernorm.weight",
"layers.32.self_attn.q_norm.weight",
"layers.32.self_attn.k_norm.weight",
"layers.32.input_layernorm.weight",
"layers.32.post_attention_layernorm.weight",
"layers.33.self_attn.q_norm.weight",
"layers.33.self_attn.k_norm.weight",
"layers.33.input_layernorm.weight",
"layers.33.post_attention_layernorm.weight",
"layers.34.self_attn.q_norm.weight",
"layers.34.self_attn.k_norm.weight",
"layers.34.input_layernorm.weight",
"layers.34.post_attention_layernorm.weight",
"layers.35.self_attn.q_norm.weight",
"layers.35.self_attn.k_norm.weight",
"layers.35.input_layernorm.weight",
"layers.35.post_attention_layernorm.weight",
"norm.weight"
],
"modules_to_not_use_matmul": [],
"non_blocking": false,
"quant_conv": false,
"quant_embedding": true,
"quant_method": "sdnq",
"quantization_device": null,
"quantized_matmul_dtype": null,
"return_device": null,
"sdnq_version": "0.1.9",
"svd_rank": 32,
"svd_steps": 8,
"use_dynamic_quantization": false,
"use_grad_ckpt": true,
"use_hadamard": false,
"use_quantized_matmul": false,
"use_quantized_matmul_conv": false,
"use_static_quantization": true,
"use_stochastic_rounding": false,
"use_svd": false,
"weights_dtype": "uint4"
},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
24,
20,
20
],
"rope_theta": 5000000,
"rope_type": "default"
},
"transformers_version": "5.10.1",
"use_cache": true,
"vocab_size": 151936
}
|