luping-liu
commited on
Upload folder using huggingface_hub
Browse files- config.json +33 -0
- model.safetensors +3 -0
- training_stage.json +13 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPModel"
|
5 |
+
],
|
6 |
+
"initializer_factor": 1.0,
|
7 |
+
"logit_scale_init_value": 2.6592,
|
8 |
+
"model_type": "clip",
|
9 |
+
"projection_dim": 1024,
|
10 |
+
"text_config": {
|
11 |
+
"dropout": 0.0,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"model_type": "clip_text_model",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"projection_dim": 1024
|
19 |
+
},
|
20 |
+
"torch_dtype": "bfloat16",
|
21 |
+
"transformers_version": "4.40.0",
|
22 |
+
"vision_config": {
|
23 |
+
"dropout": 0.0,
|
24 |
+
"hidden_act": "gelu",
|
25 |
+
"hidden_size": 1280,
|
26 |
+
"intermediate_size": 5120,
|
27 |
+
"model_type": "clip_vision_model",
|
28 |
+
"num_attention_heads": 16,
|
29 |
+
"num_hidden_layers": 32,
|
30 |
+
"patch_size": 14,
|
31 |
+
"projection_dim": 1024
|
32 |
+
}
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d0684c1cee3732c3f1cda87d931a465e75bf30e67bce60f7b3ec534ed6c139e
|
3 |
+
size 1972330882
|
training_stage.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0,
|
3 |
+
"step": 5000,
|
4 |
+
"global_step": 5000,
|
5 |
+
"step_loss": 0.0,
|
6 |
+
"lr": 2.7723404743418445e-06,
|
7 |
+
"metrics": {
|
8 |
+
"accuracy": 0.975,
|
9 |
+
"num_samples": 480,
|
10 |
+
"test_unique_accuracy": 0.65,
|
11 |
+
"test_unique_num_samples": 480
|
12 |
+
}
|
13 |
+
}
|