File size: 9,619 Bytes
f2b7557 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 | {
"architectures": [
"Mistral3Model"
],
"dtype": "bfloat16",
"image_token_index": 10,
"model_type": "mistral3",
"multimodal_projector_bias": false,
"projector_hidden_act": "gelu",
"quantization_config": {
"add_skip_keys": false,
"dequantize_fp32": false,
"dynamic_loss_threshold": null,
"group_size": 0,
"is_integer": true,
"is_training": false,
"modules_dtype_dict": {},
"modules_quant_config": {},
"modules_to_not_convert": [
".img_out",
".proj_out",
".emb_in",
".final_layer",
"patch_embed",
"language_model.norm",
".time_embed",
"multi_modal_projector",
".condition_embedder",
".t_embedder",
"wte",
"lm_head",
".txt_out",
"time_text_embed",
".context_embedder",
".txt_in",
".emb_out",
".norm_out",
".img_in",
".vid_in",
".x_embedder",
"patch_embedding",
"patch_emb",
".vid_out",
".y_embedder",
"language_model.embed_tokens.weight",
"language_model.layers.0.input_layernorm.weight",
"language_model.layers.0.post_attention_layernorm.weight",
"language_model.layers.1.input_layernorm.weight",
"language_model.layers.1.post_attention_layernorm.weight",
"language_model.layers.2.input_layernorm.weight",
"language_model.layers.2.post_attention_layernorm.weight",
"language_model.layers.3.input_layernorm.weight",
"language_model.layers.3.post_attention_layernorm.weight",
"language_model.layers.4.input_layernorm.weight",
"language_model.layers.4.post_attention_layernorm.weight",
"language_model.layers.5.input_layernorm.weight",
"language_model.layers.5.post_attention_layernorm.weight",
"language_model.layers.6.input_layernorm.weight",
"language_model.layers.6.post_attention_layernorm.weight",
"language_model.layers.7.input_layernorm.weight",
"language_model.layers.7.post_attention_layernorm.weight",
"language_model.layers.8.input_layernorm.weight",
"language_model.layers.8.post_attention_layernorm.weight",
"language_model.layers.9.input_layernorm.weight",
"language_model.layers.9.post_attention_layernorm.weight",
"language_model.layers.10.input_layernorm.weight",
"language_model.layers.10.post_attention_layernorm.weight",
"language_model.layers.11.input_layernorm.weight",
"language_model.layers.11.post_attention_layernorm.weight",
"language_model.layers.12.input_layernorm.weight",
"language_model.layers.12.post_attention_layernorm.weight",
"language_model.layers.13.input_layernorm.weight",
"language_model.layers.13.post_attention_layernorm.weight",
"language_model.layers.14.input_layernorm.weight",
"language_model.layers.14.post_attention_layernorm.weight",
"language_model.layers.15.input_layernorm.weight",
"language_model.layers.15.post_attention_layernorm.weight",
"language_model.layers.16.input_layernorm.weight",
"language_model.layers.16.post_attention_layernorm.weight",
"language_model.layers.17.input_layernorm.weight",
"language_model.layers.17.post_attention_layernorm.weight",
"language_model.layers.18.input_layernorm.weight",
"language_model.layers.18.post_attention_layernorm.weight",
"language_model.layers.19.input_layernorm.weight",
"language_model.layers.19.post_attention_layernorm.weight",
"language_model.layers.20.input_layernorm.weight",
"language_model.layers.20.post_attention_layernorm.weight",
"language_model.layers.21.input_layernorm.weight",
"language_model.layers.21.post_attention_layernorm.weight",
"language_model.layers.22.input_layernorm.weight",
"language_model.layers.22.post_attention_layernorm.weight",
"language_model.layers.23.input_layernorm.weight",
"language_model.layers.23.post_attention_layernorm.weight",
"language_model.layers.24.input_layernorm.weight",
"language_model.layers.24.post_attention_layernorm.weight",
"language_model.layers.25.input_layernorm.weight",
"language_model.layers.25.post_attention_layernorm.weight",
"language_model.norm.weight",
"multi_modal_projector.linear_1.weight",
"multi_modal_projector.linear_2.weight",
"multi_modal_projector.norm.weight",
"multi_modal_projector.patch_merger.merging_layer.weight",
"vision_tower.ln_pre.weight",
"vision_tower.patch_conv.weight",
"vision_tower.transformer.layers.0.attention_norm.weight",
"vision_tower.transformer.layers.0.ffn_norm.weight",
"vision_tower.transformer.layers.1.attention_norm.weight",
"vision_tower.transformer.layers.1.ffn_norm.weight",
"vision_tower.transformer.layers.2.attention_norm.weight",
"vision_tower.transformer.layers.2.ffn_norm.weight",
"vision_tower.transformer.layers.3.attention_norm.weight",
"vision_tower.transformer.layers.3.ffn_norm.weight",
"vision_tower.transformer.layers.4.attention_norm.weight",
"vision_tower.transformer.layers.4.ffn_norm.weight",
"vision_tower.transformer.layers.5.attention_norm.weight",
"vision_tower.transformer.layers.5.ffn_norm.weight",
"vision_tower.transformer.layers.6.attention_norm.weight",
"vision_tower.transformer.layers.6.ffn_norm.weight",
"vision_tower.transformer.layers.7.attention_norm.weight",
"vision_tower.transformer.layers.7.ffn_norm.weight",
"vision_tower.transformer.layers.8.attention_norm.weight",
"vision_tower.transformer.layers.8.ffn_norm.weight",
"vision_tower.transformer.layers.9.attention_norm.weight",
"vision_tower.transformer.layers.9.ffn_norm.weight",
"vision_tower.transformer.layers.10.attention_norm.weight",
"vision_tower.transformer.layers.10.ffn_norm.weight",
"vision_tower.transformer.layers.11.attention_norm.weight",
"vision_tower.transformer.layers.11.ffn_norm.weight",
"vision_tower.transformer.layers.12.attention_norm.weight",
"vision_tower.transformer.layers.12.ffn_norm.weight",
"vision_tower.transformer.layers.13.attention_norm.weight",
"vision_tower.transformer.layers.13.ffn_norm.weight",
"vision_tower.transformer.layers.14.attention_norm.weight",
"vision_tower.transformer.layers.14.ffn_norm.weight",
"vision_tower.transformer.layers.15.attention_norm.weight",
"vision_tower.transformer.layers.15.ffn_norm.weight",
"vision_tower.transformer.layers.16.attention_norm.weight",
"vision_tower.transformer.layers.16.ffn_norm.weight",
"vision_tower.transformer.layers.17.attention_norm.weight",
"vision_tower.transformer.layers.17.ffn_norm.weight",
"vision_tower.transformer.layers.18.attention_norm.weight",
"vision_tower.transformer.layers.18.ffn_norm.weight",
"vision_tower.transformer.layers.19.attention_norm.weight",
"vision_tower.transformer.layers.19.ffn_norm.weight",
"vision_tower.transformer.layers.20.attention_norm.weight",
"vision_tower.transformer.layers.20.ffn_norm.weight",
"vision_tower.transformer.layers.21.attention_norm.weight",
"vision_tower.transformer.layers.21.ffn_norm.weight",
"vision_tower.transformer.layers.22.attention_norm.weight",
"vision_tower.transformer.layers.22.ffn_norm.weight",
"vision_tower.transformer.layers.23.attention_norm.weight",
"vision_tower.transformer.layers.23.ffn_norm.weight"
],
"modules_to_not_use_matmul": [],
"non_blocking": false,
"quant_conv": false,
"quant_embedding": false,
"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_quantized_matmul": false,
"use_quantized_matmul_conv": false,
"use_static_quantization": true,
"use_stochastic_rounding": false,
"use_svd": false,
"weights_dtype": "uint4"
},
"spatial_merge_size": 2,
"text_config": {
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 9216,
"max_position_embeddings": 262144,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 26,
"num_key_value_heads": 8,
"pad_token_id": null,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"beta_fast": 32.0,
"beta_slow": 1.0,
"factor": 16.0,
"llama_4_scaling_beta": 0.1,
"mscale": 1.0,
"mscale_all_dim": 1.0,
"original_max_position_embeddings": 16384,
"rope_theta": 1000000.0,
"rope_type": "yarn",
"type": "yarn"
},
"sliding_window": null,
"tie_word_embeddings": true,
"use_cache": true,
"vocab_size": 131072
},
"tie_word_embeddings": true,
"transformers_version": "5.8.0.dev0",
"vision_config": {
"attention_dropout": 0.0,
"dtype": "bfloat16",
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 1024,
"image_size": 1540,
"initializer_range": 0.02,
"intermediate_size": 4096,
"model_type": "pixtral",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 24,
"patch_size": 14,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"vision_feature_layer": -1
}
|