Commit ·
12efdb7
1
Parent(s): 828d59c
config
Browse files- config.json +184 -0
config.json
ADDED
|
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"InternVLChatModel"
|
| 4 |
+
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
|
| 7 |
+
"AutoModel": "modeling_internvl_chat.InternVLChatModel",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
|
| 9 |
+
},
|
| 10 |
+
"downsample_ratio": 0.5,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"dynamic_image_size": true,
|
| 13 |
+
"force_image_size": 448,
|
| 14 |
+
"hidden_size": 5120,
|
| 15 |
+
"image_fold": null,
|
| 16 |
+
"keys_to_ignore_at_inference": [
|
| 17 |
+
"past_key_values"
|
| 18 |
+
],
|
| 19 |
+
"llm_config": {
|
| 20 |
+
"_attn_implementation_autoset": true,
|
| 21 |
+
"_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
|
| 22 |
+
"architectures": [
|
| 23 |
+
"Qwen2ForCausalLM"
|
| 24 |
+
],
|
| 25 |
+
"attention_dropout": 0.0,
|
| 26 |
+
"bos_token_id": 151643,
|
| 27 |
+
"dtype": "bfloat16",
|
| 28 |
+
"eos_token_id": 151643,
|
| 29 |
+
"hidden_act": "silu",
|
| 30 |
+
"hidden_size": 5120,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"intermediate_size": 27648,
|
| 33 |
+
"layer_types": [
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"full_attention",
|
| 76 |
+
"full_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"full_attention",
|
| 80 |
+
"full_attention",
|
| 81 |
+
"full_attention",
|
| 82 |
+
"full_attention",
|
| 83 |
+
"full_attention",
|
| 84 |
+
"full_attention",
|
| 85 |
+
"full_attention",
|
| 86 |
+
"full_attention",
|
| 87 |
+
"full_attention",
|
| 88 |
+
"full_attention",
|
| 89 |
+
"full_attention",
|
| 90 |
+
"full_attention",
|
| 91 |
+
"full_attention",
|
| 92 |
+
"full_attention",
|
| 93 |
+
"full_attention",
|
| 94 |
+
"full_attention",
|
| 95 |
+
"full_attention",
|
| 96 |
+
"full_attention",
|
| 97 |
+
"full_attention"
|
| 98 |
+
],
|
| 99 |
+
"max_position_embeddings": 32768,
|
| 100 |
+
"max_window_layers": 70,
|
| 101 |
+
"model_type": "qwen2",
|
| 102 |
+
"moe_config": null,
|
| 103 |
+
"num_attention_heads": 40,
|
| 104 |
+
"num_hidden_layers": 64,
|
| 105 |
+
"num_key_value_heads": 8,
|
| 106 |
+
"pad_token_id": 151643,
|
| 107 |
+
"rms_norm_eps": 1e-06,
|
| 108 |
+
"rope_scaling": {
|
| 109 |
+
"factor": 2.0,
|
| 110 |
+
"rope_type": "dynamic",
|
| 111 |
+
"type": "dynamic"
|
| 112 |
+
},
|
| 113 |
+
"rope_theta": 1000000.0,
|
| 114 |
+
"sliding_window": null,
|
| 115 |
+
"use_bfloat16": true,
|
| 116 |
+
"use_cache": false,
|
| 117 |
+
"use_sliding_window": false,
|
| 118 |
+
"vocab_size": 151674
|
| 119 |
+
},
|
| 120 |
+
"max_dynamic_patch": 12,
|
| 121 |
+
"min_dynamic_patch": 1,
|
| 122 |
+
"model_type": "internvl_chat",
|
| 123 |
+
"output_attentions": false,
|
| 124 |
+
"pad2square": false,
|
| 125 |
+
"pad_token_id": 151643,
|
| 126 |
+
"ps_version": "v2",
|
| 127 |
+
"select_layer": -1,
|
| 128 |
+
"system_message": null,
|
| 129 |
+
"template": "internvl2_5",
|
| 130 |
+
"tie_word_embeddings": false,
|
| 131 |
+
"torch_dtype": "bfloat16",
|
| 132 |
+
"transformers_version": null,
|
| 133 |
+
"use_backbone_lora": 0,
|
| 134 |
+
"use_llm_lora": 0,
|
| 135 |
+
"use_thumbnail": true,
|
| 136 |
+
"vision_config": {
|
| 137 |
+
"_attn_implementation_autoset": true,
|
| 138 |
+
"_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
|
| 139 |
+
"architectures": [
|
| 140 |
+
"InternVisionModel"
|
| 141 |
+
],
|
| 142 |
+
"attention_dropout": 0.0,
|
| 143 |
+
"auto_map": {
|
| 144 |
+
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
|
| 145 |
+
"AutoModel": "modeling_intern_vit.InternVisionModel"
|
| 146 |
+
},
|
| 147 |
+
"capacity_factor": 1.2,
|
| 148 |
+
"drop_path_rate": 0.4,
|
| 149 |
+
"dropout": 0.0,
|
| 150 |
+
"dtype": "bfloat16",
|
| 151 |
+
"eval_capacity_factor": 1.4,
|
| 152 |
+
"hidden_act": "gelu",
|
| 153 |
+
"hidden_size": 3200,
|
| 154 |
+
"image_size": 448,
|
| 155 |
+
"initializer_factor": 0.1,
|
| 156 |
+
"initializer_range": 1e-10,
|
| 157 |
+
"intermediate_size": 12800,
|
| 158 |
+
"laux_allreduce": "all_nodes",
|
| 159 |
+
"layer_norm_eps": 1e-06,
|
| 160 |
+
"model_type": "intern_vit_6b",
|
| 161 |
+
"moe_coeff_ratio": 0.5,
|
| 162 |
+
"moe_intermediate_size": 768,
|
| 163 |
+
"moe_output_scale": 4.0,
|
| 164 |
+
"noisy_gate_policy": "RSample_before",
|
| 165 |
+
"norm_type": "rms_norm",
|
| 166 |
+
"num_attention_heads": 25,
|
| 167 |
+
"num_channels": 3,
|
| 168 |
+
"num_experts": 8,
|
| 169 |
+
"num_hidden_layers": 45,
|
| 170 |
+
"num_routed_experts": 4,
|
| 171 |
+
"num_shared_experts": 4,
|
| 172 |
+
"pad_token_id": 151643,
|
| 173 |
+
"patch_size": 14,
|
| 174 |
+
"qk_normalization": true,
|
| 175 |
+
"qkv_bias": false,
|
| 176 |
+
"shared_expert_intermediate_size": 3072,
|
| 177 |
+
"use_bfloat16": true,
|
| 178 |
+
"use_flash_attn": false,
|
| 179 |
+
"use_moe": false,
|
| 180 |
+
"use_residual": true,
|
| 181 |
+
"use_rts": false,
|
| 182 |
+
"use_weighted_residual": false
|
| 183 |
+
}
|
| 184 |
+
}
|