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
57
Xenova HF Staff commited on
Commit
beedcea
·
verified ·
1 Parent(s): 7a7a393

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +66 -74
config.json CHANGED
@@ -1,78 +1,70 @@
1
  {
2
- "add_projections": false,
3
- "architectures": [
4
- "JinaCLIPModel"
5
- ],
6
- "auto_map": {
7
- "AutoConfig": "jinaai/jina-clip-implementation--configuration_clip.JinaCLIPConfig",
8
- "AutoModel": "jinaai/jina-clip-implementation--modeling_clip.JinaCLIPModel"
9
- },
10
- "initializer_factor": 1.0,
11
- "logit_scale_init_value": 2.6592,
12
- "matryoshka_dimensions": [
13
- 32,
14
- 64,
15
- 128,
16
- 256,
17
- 512,
18
- 768,
19
- 1024
20
- ],
21
- "model_type": "jina_clip",
22
- "projection_dim": 1024,
23
- "text_config": {
24
- "default_instruction_task": null,
25
- "default_lora_task": "retrieval.query",
26
- "embed_dim": 1024,
27
- "hf_model_config_kwargs": {
28
- "load_trained_adapters": false,
29
- "lora_adaptations": [
30
- "retrieval.query"
31
- ],
32
- "lora_alpha": 4,
33
- "lora_dropout_p": 0.0,
34
- "lora_main_params_trainable": false,
35
- "lora_rank": 4,
36
- "task_instructions": {
37
- "retrieval.query": "Represent the query for retrieving evidence documents: "
38
- },
39
- "use_flash_attn": true
40
  },
41
- "hf_model_name_or_path": "jinaai/jina-embeddings-v3",
42
- "model_type": "jina_clip_text",
43
- "pooler_type": "mean_pooler",
44
- "proj_bias": false,
45
- "proj_type": null
46
- },
47
- "torch_dtype": "bfloat16",
48
- "truncate_dim": null,
49
- "use_text_flash_attn": null,
50
- "use_vision_xformers": null,
51
- "vision_config": {
52
- "embed_dim": 1024,
53
- "fused_layer_norm": false,
54
- "head_width": 64,
55
- "image_size": 512,
56
- "intp_freq": true,
57
- "layers": 24,
58
- "ls_init_value": null,
59
- "mlp_ratio": 2.6667,
60
- "model_type": "jina_clip_vision",
61
- "naive_swiglu": true,
62
- "patch_dropout": 0.1,
63
- "patch_size": 14,
64
- "post_norm": false,
65
- "proj_type": null,
66
- "pt_hw_seq_len": 16,
67
- "qkv_bias": true,
68
- "rope_embeddings": true,
69
- "subln": true,
70
- "width": 1024,
71
- "x_attention": true
72
- },
73
- "transformers.js_config": {
74
- "use_external_data_format": {
75
- "model.onnx": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
- }
78
  }
 
1
  {
2
+ "add_projections": false,
3
+ "architectures": [
4
+ "JinaCLIPModel"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "jinaai/jina-clip-implementation--configuration_clip.JinaCLIPConfig",
8
+ "AutoModel": "jinaai/jina-clip-implementation--modeling_clip.JinaCLIPModel"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
10
+ "initializer_factor": 1.0,
11
+ "logit_scale_init_value": 2.6592,
12
+ "matryoshka_dimensions": [32, 64, 128, 256, 512, 768, 1024],
13
+ "model_type": "jina_clip",
14
+ "projection_dim": 1024,
15
+ "text_config": {
16
+ "default_instruction_task": null,
17
+ "default_lora_task": "retrieval.query",
18
+ "embed_dim": 1024,
19
+ "hf_model_config_kwargs": {
20
+ "load_trained_adapters": false,
21
+ "lora_adaptations": [
22
+ "retrieval.query"
23
+ ],
24
+ "lora_alpha": 4,
25
+ "lora_dropout_p": 0.0,
26
+ "lora_main_params_trainable": false,
27
+ "lora_rank": 4,
28
+ "task_instructions": {
29
+ "retrieval.query": "Represent the query for retrieving evidence documents: "
30
+ },
31
+ "use_flash_attn": true
32
+ },
33
+ "hf_model_name_or_path": "jinaai/jina-embeddings-v3",
34
+ "model_type": "jina_clip_text",
35
+ "pooler_type": "mean_pooler",
36
+ "proj_bias": false,
37
+ "proj_type": null
38
+ },
39
+ "torch_dtype": "bfloat16",
40
+ "transformers.js_config": {
41
+ "use_external_data_format": {
42
+ "model.onnx": true
43
+ }
44
+ },
45
+ "truncate_dim": null,
46
+ "use_text_flash_attn": null,
47
+ "use_vision_xformers": null,
48
+ "vision_config": {
49
+ "embed_dim": 1024,
50
+ "fused_layer_norm": false,
51
+ "head_width": 64,
52
+ "image_size": 512,
53
+ "intp_freq": true,
54
+ "layers": 24,
55
+ "ls_init_value": null,
56
+ "mlp_ratio": 2.6667,
57
+ "model_type": "jina_clip_vision",
58
+ "naive_swiglu": true,
59
+ "patch_dropout": 0.1,
60
+ "patch_size": 14,
61
+ "post_norm": false,
62
+ "proj_type": null,
63
+ "pt_hw_seq_len": 16,
64
+ "qkv_bias": true,
65
+ "rope_embeddings": true,
66
+ "subln": true,
67
+ "width": 1024,
68
+ "x_attention": true
69
  }
 
70
  }