Hugging Face's logo

alphaedge-ai
/
metaclip-2-worldwide-m16-384-haw-32768

Sentence Similarity
sentence-transformers
Safetensors
Hawaiian
metaclip_2
trimmed
Model card Files
xet
 Community
lbourdoispro commited on
Commit
c6ade18
·
verified ·
1 Parent(s): c5b8a12

Trimmed MetaCLIP-2 text vocab for Hawaiian

Browse files
Files changed (7) hide show
  1. README.md +26 -0
  2. config.json +43 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +29 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +56 -0
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: zero-shot-image-classification
3
+ language: haw
4
+ tags:
5
+ - trimmed
6
+ - vision-language
7
+ - clip
8
+ library_name: transformers
9
+ base_model: facebook/metaclip-2-worldwide-m16-384
10
+ base_model_relation: quantized
11
+ datasets:
12
+ - Lumberjackk/fineweb-2-trimming
13
+ ---
14
+
15
+ # metaclip-2-worldwide-m16-384-haw-32768
16
+
17
+ This model is a 82.6% smaller version of [facebook/metaclip-2-worldwide-m16-384](https://huggingface.co/facebook/metaclip-2-worldwide-m16-384)
18
+ optimized for Hawaiian via text vocabulary trimming.
19
+
20
+ ## Model Statistics
21
+ - **Original vocab size:** 901,629
22
+ - **Trimmed vocab size:** 32,768
23
+ - **Vocabulary reduction:** 96.4%
24
+ - **Original params:** 538,547,201
25
+ - **Trimmed params:** 93,690,369
26
+ - **Size reduction:** 82.6%
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MetaClip2Model"
4
+ ],
5
+ "dtype": "float32",
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "metaclip_2",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "attention_dropout": 0.0,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "gelu",
14
+ "hidden_size": 512,
15
+ "initializer_factor": 1.0,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2048,
18
+ "layer_norm_eps": 1e-05,
19
+ "max_position_embeddings": 77,
20
+ "model_type": "metaclip_2_text_model",
21
+ "num_attention_heads": 8,
22
+ "num_hidden_layers": 12,
23
+ "projection_dim": 512,
24
+ "vocab_size": 32768
25
+ },
26
+ "transformers_version": "4.57.1",
27
+ "vision_config": {
28
+ "attention_dropout": 0.0,
29
+ "hidden_act": "gelu",
30
+ "hidden_size": 512,
31
+ "image_size": 384,
32
+ "initializer_factor": 1.0,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 2048,
35
+ "layer_norm_eps": 1e-05,
36
+ "model_type": "metaclip_2_vision_model",
37
+ "num_attention_heads": 8,
38
+ "num_channels": 3,
39
+ "num_hidden_layers": 12,
40
+ "patch_size": 16,
41
+ "projection_dim": 512
42
+ }
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bafad365667ecd26f9317ecb90ed4a17b0a1baa15cb9a48353e007e6b0436ce9
3
+ size 374808820
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 384,
4
+ "width": 384
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "CLIPProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 384,
27
+ "width": 384
28
+ }
29
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32767": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "<pad>",
52
+ "processor_class": "CLIPProcessor",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }