Zero-Shot Image Classification
Safetensors
clip
zer0int commited on
Commit
0fa1bb0
1 Parent(s): c4e90fd

Long-CLIP SAE 248 tokens

Browse files

Similar training to the normal (77 tokens) CLIP-SAE, but takes 248 tokens input max.

Long-ViT-L-14-GmP-SAE-TE-only.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eaa28b7c528fca61998085afb1cd16399d3996c61f5ddcf5b726831f5e7fd60
3
+ size 323935052
Long-ViT-L-14-GmP-SAE-full-model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc265a39d3edc2723a9ccaeaad7af5198f0db1261a92a090c60831fbe0da044
3
+ size 931973360
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LongCLIP-SAE-ViT-L-14/",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 4.6052,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 248,
15
+ "model_type": "clip_text_model",
16
+ "num_attention_heads": 12,
17
+ "projection_dim": 768
18
+ },
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.46.3",
21
+ "vision_config": {
22
+ "dropout": 0.0,
23
+ "hidden_size": 1024,
24
+ "intermediate_size": 4096,
25
+ "model_type": "clip_vision_model",
26
+ "num_attention_heads": 16,
27
+ "num_hidden_layers": 24,
28
+ "patch_size": 14,
29
+ "projection_dim": 768
30
+ }
31
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3e6c8c21881f13e532c33a809538b51132bae9ff8a40147fbdd7d57dc8c13e
3
+ size 1711063028
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 224,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 224
19
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": {
3
+ "content": "<|endoftext|>",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true,
8
+ "__type": "AddedToken"
9
+ },
10
+ "bos_token": {
11
+ "content": "<|startoftext|>",
12
+ "single_word": false,
13
+ "lstrip": false,
14
+ "rstrip": false,
15
+ "normalized": true,
16
+ "__type": "AddedToken"
17
+ },
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": true,
24
+ "__type": "AddedToken"
25
+ },
26
+ "pad_token": "<|endoftext|>",
27
+ "add_prefix_space": false,
28
+ "errors": "replace",
29
+ "do_lower_case": true,
30
+ "name_or_path": "zer0int/LongCLIP-L-Diffusers/",
31
+ "model_max_length": 248,
32
+ "special_tokens_map_file": "./special_tokens_map.json",
33
+ "tokenizer_class": "CLIPTokenizer"
34
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff