Hugging Face's logo

sartifyllc
/
AViLaMa

Zero-Shot Image Classification
Transformers
PyTorch
Safetensors
vision-text-dual-encoder
image generation
visual qa
text-image embedding
image-text embedding
sartify
visual conversional ai
image semantic retrival
african raw resourced languages
Inference Endpoints
Model card Files Community
1
innocent-charles commited on
Commit
d397478
•
1 Parent(s): 604f62f

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. avilama_config.json +14 -25
  2. open_clip_config.json +14 -25
avilama_config.json CHANGED
@@ -1,30 +1,19 @@
1
  {
2
  "model_cfg": {
3
- "seed": 42,
4
- "max_length": 200,
5
- "image_encoder": "vit_large_patch14_clip_336",
6
- "text_encoder": "sartifyllc/AviLaBSE",
7
- "text_tokenizer": "sartifyllc/AviLaBSE",
8
- "flip_ratio": 0.5,
9
- "tensor_ratio": 1.0,
10
- "imgs_pixels": 255.0,
11
- "image_size": 336,
12
- "batch_size": 4,
13
- "num_workers": 4,
14
- "num_projection_layers": 1,
15
- "projection_dim": 256,
16
- "dropout": 0.1,
17
- "image_embedding": 1024,
18
- "text_embedding": 768,
19
- "temperature": 1.0,
20
- "head_lr": 0.001,
21
- "image_encoder_lr": 0.0001,
22
- "text_encoder_lr": 1e-05,
23
- "weight_decay": 0.001,
24
- "patience": 1,
25
- "factor": 0.8,
26
- "epochs": 2,
27
- "context_length": 512
28
  },
29
  "preprocess_cfg": {
30
  "mean": [
 
1
  {
2
  "model_cfg": {
3
+ "model_cfg": {
4
+ "embed_dim": 1024,
5
+ "vision_cfg": {
6
+ "image_size": 336,
7
+ "layers": 1,
8
+ "width": 336,
9
+ "patch_size": 14
10
+ },
11
+ "text_cfg": {
12
+ "context_length": 512,
13
+ "vocab_size": 501153,
14
+ "layers": 1
15
+ }
16
+ }
 
 
 
 
 
 
 
 
 
 
 
17
  },
18
  "preprocess_cfg": {
19
  "mean": [
open_clip_config.json CHANGED
@@ -1,30 +1,19 @@
1
  {
2
  "model_cfg": {
3
- "seed": 42,
4
- "max_length": 200,
5
- "image_encoder": "vit_large_patch14_clip_336",
6
- "text_encoder": "sartifyllc/AviLaBSE",
7
- "text_tokenizer": "sartifyllc/AviLaBSE",
8
- "flip_ratio": 0.5,
9
- "tensor_ratio": 1.0,
10
- "imgs_pixels": 255.0,
11
- "image_size": 336,
12
- "batch_size": 4,
13
- "num_workers": 4,
14
- "num_projection_layers": 1,
15
- "projection_dim": 256,
16
- "dropout": 0.1,
17
- "image_embedding": 1024,
18
- "text_embedding": 768,
19
- "temperature": 1.0,
20
- "head_lr": 0.001,
21
- "image_encoder_lr": 0.0001,
22
- "text_encoder_lr": 1e-05,
23
- "weight_decay": 0.001,
24
- "patience": 1,
25
- "factor": 0.8,
26
- "epochs": 2,
27
- "context_length": 512
28
  },
29
  "preprocess_cfg": {
30
  "mean": [
 
1
  {
2
  "model_cfg": {
3
+ "model_cfg": {
4
+ "embed_dim": 1024,
5
+ "vision_cfg": {
6
+ "image_size": 336,
7
+ "layers": 1,
8
+ "width": 336,
9
+ "patch_size": 14
10
+ },
11
+ "text_cfg": {
12
+ "context_length": 512,
13
+ "vocab_size": 501153,
14
+ "layers": 1
15
+ }
16
+ }
 
 
 
 
 
 
 
 
 
 
 
17
  },
18
  "preprocess_cfg": {
19
  "mean": [