Hugging Face's logo

thu-ml
/
zh-clip-vit-roberta-large-patch14

Transformers
PyTorch
zhclip
Inference Endpoints
Model card Files Community
zh-clip-vit-roberta-large-patch14
File size: 3,586 Bytes 
e285cd4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "architectures": [
      "ZHCLIPModel"
    ],
    "initializer_factor": 1.0,
    "logit_scale_init_value": 2.6592,
    "model_type": "zhclip",
    "projection_dim": 768,
    "text_config": {
        "attention_probs_dropout_prob": 0.1,
        "bos_token_id": 0,
        "directionality": "bidi",
        "eos_token_id": 2,
        "hidden_act": "gelu",
        "hidden_dropout_prob": 0.1,
        "hidden_size": 1024,
        "initializer_range": 0.02,
        "intermediate_size": 4096,
        "layer_norm_eps": 1e-12,
        "max_position_embeddings": 512,
        "model_type": "bert",
        "num_attention_heads": 16,
        "num_hidden_layers": 24,
        "output_past": true,
        "pad_token_id": 0,
        "pooler_fc_size": 768,
        "pooler_num_attention_heads": 12,
        "pooler_num_fc_layers": 3,
        "pooler_size_per_head": 128,
        "pooler_type": "first_token_transform",
        "type_vocab_size": 2,
        "vocab_size": 21128
    },
    "text_config_dict": {
      "hidden_act": "gelu",
      "hidden_size": 768,
      "intermediate_size": 3072,
      "num_attention_heads": 12
    },
    "torch_dtype": "float32",
    "transformers_version": null,
    "vision_config": {
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "attention_dropout": 0.0,
      "bad_words_ids": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "dropout": 0.0,
      "early_stopping": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "hidden_act": "gelu",
      "hidden_size": 1024,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "image_size": 224,
      "initializer_factor": 1.0,
      "initializer_range": 0.02,
      "intermediate_size": 4096,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-05,
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "model_type": "clip_vision_model",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 16,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_channels": 3,
      "num_hidden_layers": 24,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "patch_size": 14,
      "prefix": null,
      "problem_type": null,
      "pruned_heads": {},
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "sep_token_id": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tf_legacy_loss": false,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torch_dtype": null,
      "torchscript": false,
      "transformers_version": "4.21.3",
      "typical_p": 1.0,
      "use_bfloat16": false
    },
    "vision_config_dict": {
      "hidden_act": "gelu",
      "hidden_size": 1024,
      "intermediate_size": 4096,
      "num_attention_heads": 16,
      "num_hidden_layers": 24,
      "patch_size": 14
    }
  }