Hugging Face's logo

jinaai
/
jina-clip-v2

Feature Extraction
Transformers
PyTorch
ONNX
Safetensors
sentence-transformers
Transformers.js
jina_clip
xlm-roberta
eva02
clip
sentence-similarity
retrieval
multimodal
multi-modal
crossmodal
cross-modal
mteb
clip-benchmark
vidore
custom_code
🇪🇺 Region: EU
Model card Files Community
23
jina-clip-v2
File size: 5,512 Bytes 
af015b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
 
{
    "_commit_hash": null,
    "_name_or_path": "jinaai/jina-clip-v2-test",
    "add_projections": false,
    "architectures": [
        "JinaCLIPModel"
    ],
    "auto_map": {
        "AutoConfig": "jinaai/jina-clip-implementation--configuration_clip.JinaCLIPConfig",
        "AutoModel": "jinaai/jina-clip-implementation--modeling_clip.JinaCLIPModel"
    },
    "initializer_factor": 1.0,
    "logit_scale_init_value": 2.6592,
    "model_type": "jina_clip",
    "projection_dim": 1024,
    "matryoshka_dimensions": [32, 64, 128, 256, 512, 768, 1024],
    "text_config": {
        "_name_or_path": "",
        "add_cross_attention": false,
        "architectures": null,
        "bad_words_ids": null,
        "begin_suppress_tokens": 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,
        "early_stopping": false,
        "embed_dim": 1024,
        "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,
        "hf_model_config_kwargs": {
            "use_flash_attn": false
        },
        "hf_model_name_or_path": "jinaai/jina-xlm-roberta-large-rope-8k",
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "is_decoder": false,
        "is_encoder_decoder": false,
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "length_penalty": 1.0,
        "max_length": 20,
        "min_length": 0,
        "model_type": "jina_clip_text",
        "no_repeat_ngram_size": 0,
        "num_beam_groups": 1,
        "num_beams": 1,
        "num_return_sequences": 1,
        "output_attentions": false,
        "output_hidden_states": false,
        "output_scores": false,
        "pad_token_id": null,
        "pooler_type": "mean_pooler",
        "prefix": null,
        "problem_type": null,
        "proj_bias": false,
        "proj_type": null,
        "pruned_heads": {},
        "remove_invalid_values": false,
        "repetition_penalty": 1.0,
        "return_dict": true,
        "return_dict_in_generate": false,
        "sep_token_id": null,
        "suppress_tokens": 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": "4.42.4",
        "typical_p": 1.0,
        "use_bfloat16": false
    },
    "torch_dtype": "float16",
    "transformers_version": null,
    "use_text_flash_attn": null,
    "use_vision_xformers": null,
    "vision_config": {
        "_name_or_path": "",
        "add_cross_attention": false,
        "architectures": null,
        "bad_words_ids": null,
        "begin_suppress_tokens": 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,
        "drop_path_rate": 0.0,
        "early_stopping": false,
        "embed_dim": 1024,
        "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,
        "fused_layer_norm": false,
        "head_width": 64,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "image_size": 384,
        "intp_freq": true,
        "is_decoder": false,
        "is_encoder_decoder": false,
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "layers": 24,
        "length_penalty": 1.0,
        "ls_init_value": null,
        "max_length": 20,
        "min_length": 0,
        "mlp_ratio": 2.6667,
        "model_type": "jina_clip_vision",
        "naive_swiglu": true,
        "no_repeat_ngram_size": 0,
        "num_beam_groups": 1,
        "num_beams": 1,
        "num_return_sequences": 1,
        "output_attentions": false,
        "output_hidden_states": false,
        "output_scores": false,
        "pad_token_id": null,
        "patch_dropout": 0.1,
        "patch_size": 14,
        "post_norm": false,
        "prefix": null,
        "problem_type": null,
        "proj_type": null,
        "pruned_heads": {},
        "pt_hw_seq_len": 16,
        "qkv_bias": true,
        "remove_invalid_values": false,
        "repetition_penalty": 1.0,
        "return_dict": true,
        "return_dict_in_generate": false,
        "rope_embeddings": true,
        "sep_token_id": null,
        "subln": true,
        "suppress_tokens": 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": "4.42.4",
        "typical_p": 1.0,
        "use_bfloat16": false,
        "width": 1024,
        "x_attention": false
    }
}