Update all files for DOFA-CLIP-ViT-B-16
Browse files
diffusers/text_encoder/config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPTextModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 49406,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 49407,
|
| 9 |
+
"hidden_act": "quick_gelu",
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_factor": 1.0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 64,
|
| 16 |
+
"model_type": "clip_text_model",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"projection_dim": 512,
|
| 21 |
+
"transformers_version": "5.0.0.dev0",
|
| 22 |
+
"vocab_size": 32000
|
| 23 |
+
}
|