Pushed SI-IMAGE model from prithivMLmods/Human-vs-NonHuman-Detection
Browse files- config.json +60 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SiglipForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"encoder_stride": 16,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.0,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "human",
|
| 12 |
+
"1": "AI-generated"
|
| 13 |
+
},
|
| 14 |
+
"image_size": 224,
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"AI-generated": 1,
|
| 20 |
+
"human": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "siglip",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"text_config": {
|
| 31 |
+
"attention_dropout": 0.0,
|
| 32 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 33 |
+
"hidden_size": 768,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"layer_norm_eps": 1e-06,
|
| 36 |
+
"max_position_embeddings": 64,
|
| 37 |
+
"model_type": "siglip_text_model",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_hidden_layers": 12,
|
| 40 |
+
"projection_size": 768,
|
| 41 |
+
"torch_dtype": "float32",
|
| 42 |
+
"vocab_size": 32000
|
| 43 |
+
},
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.53.0",
|
| 46 |
+
"vision_config": {
|
| 47 |
+
"attention_dropout": 0.0,
|
| 48 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 49 |
+
"hidden_size": 768,
|
| 50 |
+
"image_size": 224,
|
| 51 |
+
"intermediate_size": 3072,
|
| 52 |
+
"layer_norm_eps": 1e-06,
|
| 53 |
+
"model_type": "siglip_vision_model",
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_channels": 3,
|
| 56 |
+
"num_hidden_layers": 12,
|
| 57 |
+
"patch_size": 16,
|
| 58 |
+
"torch_dtype": "float32"
|
| 59 |
+
}
|
| 60 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4b7854560add2de5236664e032f505f0ac9bc665fe5f9c33762aafbd18f6493
|
| 3 |
+
size 371567992
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|