Hugging Face's logo

hf-tiny-v2
/
tiny-random-FastVlmForConditionalGeneration

Safetensors
fast_vlm
Model card Files
xet
 Community
tiny-random-FastVlmForConditionalGeneration
File size: 2,142 Bytes
a6c8104
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "architectures": [
    "FastVlmForConditionalGeneration"
  ],
  "dtype": "float32",
  "ignore_index": -100,
  "image_seq_length": 576,
  "image_token_index": 0,
  "model_type": "fast_vlm",
  "multimodal_projector_bias": true,
  "projector_hidden_act": "gelu",
  "text_config": {
    "attention_dropout": 0.0,
    "attention_probs_dropout_prob": 0.1,
    "bos_token_id": null,
    "eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 32,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "is_training": true,
    "layer_types": [
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 512,
    "max_window_layers": 28,
    "model_type": "qwen2",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "num_key_value_heads": 4,
    "pad_token_id": 151643,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "rope_theta": 10000.0,
      "rope_type": "default"
    },
    "sliding_window": null,
    "tie_word_embeddings": false,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151647
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.16.0.dev0",
  "vision_config": {
    "architecture": "fastvit_mci3",
    "do_pooling": true,
    "global_pool": "avg",
    "hidden_size": 32,
    "image_size": 16,
    "initializer_range": 0.02,
    "label_names": [
      "LABEL_0",
      "LABEL_1"
    ],
    "model_args": {
      "downsamples": [
        false,
        true
      ],
      "embed_dims": [
        8,
        16
      ],
      "inference_mode": true,
      "layers": [
        2,
        2
      ],
      "lkc_use_act": true,
      "mlp_ratios": [
        4,
        4
      ],
      "pos_embs": [
        null,
        null
      ],
      "se_downsamples": [
        false,
        false
      ],
      "stem_use_scale_branch": false,
      "token_mixers": [
        "repmixer",
        "repmixer"
      ]
    },
    "model_type": "timm_wrapper",
    "num_channels": 3,
    "num_classes": 2,
    "patch_size": 8
  },
  "vision_feature_layer": -1,
  "vision_feature_select_strategy": "full"
}