Hugging Face's logo

openbmb
/
MiniCPM-V-4.6-GPTQ

Image-Text-to-Text
Safetensors
minicpmv4_6
minicpm-v
multimodal
conversational
4-bit precision
gptq
Model card Files
xet
 Community
MiniCPM-V-4.6-GPTQ
File size: 3,381 Bytes
2e3bf0e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "transformers_version": "5.7.0",
  "architectures": [
    "MiniCPMV4_6ForConditionalGeneration"
  ],
  "dtype": null,
  "text_config": {
    "dtype": null,
    "vocab_size": 248094,
    "hidden_size": 1024,
    "intermediate_size": 3584,
    "num_hidden_layers": 24,
    "num_attention_heads": 8,
    "num_key_value_heads": 2,
    "hidden_act": "silu",
    "max_position_embeddings": 262144,
    "initializer_range": 0.02,
    "rms_norm_eps": 1e-06,
    "use_cache": true,
    "tie_word_embeddings": true,
    "rope_parameters": {
      "partial_rotary_factor": 0.25,
      "rope_theta": 10000000,
      "rope_type": "default"
    },
    "attention_bias": false,
    "attention_dropout": 0.0,
    "head_dim": 256,
    "linear_conv_kernel_dim": 4,
    "linear_key_head_dim": 128,
    "linear_value_head_dim": 128,
    "linear_num_key_heads": 16,
    "linear_num_value_heads": 16,
    "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"
    ],
    "pad_token_id": null,
    "bos_token_id": null,
    "eos_token_id": null,
    "attn_output_gate": true,
    "full_attention_interval": 4,
    "mamba_ssm_dtype": "float32",
    "mlp_only_layers": [],
    "mtp_num_hidden_layers": 1,
    "mtp_use_dedicated_embeddings": false,
    "partial_rotary_factor": 0.25,
    "model_type": "qwen3_5_text"
  },
  "vision_config": {
    "dtype": null,
    "hidden_size": 1152,
    "intermediate_size": 4304,
    "num_hidden_layers": 27,
    "num_attention_heads": 16,
    "num_channels": 3,
    "image_size": 980,
    "patch_size": 14,
    "hidden_act": "gelu_pytorch_tanh",
    "layer_norm_eps": 1e-06,
    "attention_dropout": 0.0,
    "insert_layer_id": 6,
    "window_kernel_size": [
      2,
      2
    ],
    "model_type": "minicpmv4_6_vision"
  },
  "insert_layer_id": 6,
  "image_size": 1120,
  "drop_vision_last_layer": false,
  "image_token_id": 248056,
  "video_token_id": 248057,
  "tie_word_embeddings": true,
  "downsample_mode": "16x",
  "merge_kernel_size": [
    2,
    2
  ],
  "merger_times": 1,
  "patch_size": 14,
  "bos_token_id": null,
  "eos_token_id": 248044,
  "model_type": "minicpmv4_6",
  "pad_token_id": null,
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "damp_percent": 0.01,
    "desc_act": false,
    "static_groups": false,
    "sym": true,
    "true_sequential": true,
    "quant_method": "gptq",
    "checkpoint_format": "gptq",
    "modules_in_block_to_quantize": [
      [
        "self_attn.q_proj",
        "self_attn.k_proj",
        "self_attn.v_proj"
      ],
      [
        "self_attn.o_proj"
      ],
      [
        "linear_attn.in_proj_qkv",
        "linear_attn.in_proj_z"
      ],
      [
        "linear_attn.out_proj"
      ],
      [
        "mlp.gate_proj",
        "mlp.up_proj"
      ],
      [
        "mlp.down_proj"
      ]
    ]
  }
}