Hugging Face's logo

SJTU-DENG-Lab
/
LatentUM-Base

Safetensors
Model card Files
xet
 Community
1
LatentUM-Base
File size: 3,866 Bytes
a70902c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "base_model_name_or_path": null,
  "quantizer_ckpt_path": null,
  "llm_hidden_size": 2560,
  "mixture_mode": "mot",
  "embedding_dim": 256,
  "image_size": 448,
  "num_image_tokens": 256,
  "max_num_patches": 12,
  "image_token": "<image>",
  "internvl_config": {
    "architectures": [
      "InternVLChatModel"
    ],
    "auto_map": {
      "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
      "AutoModel": "modeling_internvl_chat.InternVLChatModel",
      "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
    },
    "downsample_ratio": 0.5,
    "dynamic_image_size": true,
    "eos_token_id": 151645,
    "force_image_size": 448,
    "llm_config": {
      "architectures": [
        "Qwen3ForCausalLM"
      ],
      "attention_bias": false,
      "attention_dropout": 0.0,
      "bos_token_id": 151643,
      "debug": false,
      "eos_token_id": 151645,
      "ep_size": 1,
      "head_dim": 128,
      "hidden_act": "silu",
      "hidden_size": 2560,
      "initializer_range": 0.02,
      "intermediate_size": 9728,
      "max_position_embeddings": 40960,
      "max_window_layers": 36,
      "micro_forward": false,
      "model_type": "qwen3",
      "num_attention_heads": 32,
      "num_hidden_layers": 36,
      "num_key_value_heads": 8,
      "rms_norm_eps": 1e-06,
      "rope_scaling": null,
      "rope_theta": 1000000,
      "skip_checkpoint": false,
      "sliding_window": null,
      "torch_dtype": "bfloat16",
      "use_cache": false,
      "use_deepep": false,
      "use_sliding_window": false,
      "vocab_size": 151936
    },
    "max_dynamic_patch": 12,
    "min_dynamic_patch": 1,
    "model_type": "internvl_chat",
    "pad2square": false,
    "pad_token_id": 151643,
    "ps_version": "v2",
    "select_layer": -1,
    "template": "internvl2_5",
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": null,
    "use_backbone_lora": 0,
    "use_llm_lora": 0,
    "use_thumbnail": true,
    "vision_config": {
      "architectures": [
        "InternVisionModel"
      ],
      "attention_dropout": 0.0,
      "auto_map": {
        "AutoConfig": "configuration_intern_vit.InternVisionConfig",
        "AutoModel": "modeling_intern_vit.InternVisionModel"
      },
      "drop_path_rate": 0.1,
      "dropout": 0.0,
      "hidden_act": "gelu",
      "hidden_size": 1024,
      "image_size": 448,
      "initializer_factor": 1.0,
      "initializer_range": 0.02,
      "intermediate_size": 4096,
      "layer_norm_eps": 1e-06,
      "model_type": "intern_vit_6b",
      "norm_type": "layer_norm",
      "num_attention_heads": 16,
      "num_channels": 3,
      "num_hidden_layers": 24,
      "patch_size": 14,
      "qk_normalization": false,
      "qkv_bias": true,
      "torch_dtype": "bfloat16",
      "use_fa3": false,
      "use_flash_attn": true
    }
  },
  "model": {
    "internvl_path": null,
    "llm_hidden_size": 2560,
    "mixture_mode": "mot",
    "embedding_dim": 256,
    "quantizer": {
      "ckpt_path": null,
      "vq_type": "multi_vq",
      "type": "MLP",
      "input_feature_dim": 4096,
      "embedding_dim": 256,
      "llm_hidden_size": 2560,
      "num_embeddings": 2048,
      "num_codebooks": 8
    },
    "head": {
      "num_codebooks": 8,
      "num_layers": 3,
      "hidden_size": 2560,
      "num_embeddings": 2048,
      "num_heads": 32,
      "mlp_ratio": 4.0
    }
  },
  "quantizer": {
    "ckpt_path": null,
    "vq_type": "multi_vq",
    "type": "MLP",
    "input_feature_dim": 4096,
    "embedding_dim": 256,
    "llm_hidden_size": 2560,
    "num_embeddings": 2048,
    "num_codebooks": 8
  },
  "head": {
    "num_codebooks": 8,
    "num_layers": 3,
    "hidden_size": 2560,
    "num_embeddings": 2048,
    "num_heads": 32,
    "mlp_ratio": 4.0
  },
  "legacy_checkpoint_path": null,
  "legacy_state_key": "module"
}