File size: 1,686 Bytes
e20a49b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "_name_or_path": "MODELS/llava-v1.6-vicuna-7b-hf",
  "architectures": [
    "PlavaForConditionalGeneration"
  ],
  "causal_conv_ks": [
    3,
    3,
    3
  ],
  "causal_conv_pad_mod": "constant",
  "dilation": 1,
  "frame_shape": [
    24,
    24
  ],
  "gradient_checkpointing": false,
  "highres": null,
  "ignore_index": -100,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_token_index": 32000,
  "model_type": "llava",
  "num_frames": 16,
  "pooling_method": "avg",
  "pooling_shape": [
    16,
    12,
    12
  ],
  "projector_hidden_act": "gelu",
  "register": false,
  "slide_pooling_shape": [
    16,
    2,
    2
  ],
  "stride": 1,
  "text_config": {
    "_name_or_path": "lmsys/vicuna-7b-v1.5",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "gradient_checkpointing": false,
    "max_position_embeddings": 4096,
    "model_type": "llama",
    "pad_token_id": 0,
    "rms_norm_eps": 1e-05,
    "torch_dtype": "bfloat16",
    "vocab_size": 32064
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.37.1",
  "use_cc": false,
  "use_image_newline_parameter": true,
  "use_pooling": true,
  "use_yi": false,
  "vision_config": {
    "hidden_size": 1024,
    "image_size": 336,
    "intermediate_size": 4096,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768,
    "vocab_size": 32000
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default",
  "vocab_size": 32064
}