Upload the CLIP Text Deprojector model.

Used 30000 texts from LAION 400B to train the model.

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/sd/deprojector/model_part_01/",
+  "architectures": [
+    "CLIPTextDeprojector"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "vocab_size": 49408
+}

epoch.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cbce9f839c5087645a3b2c5dc9701d7e05d4813d379c61e82b9269319352619
+size 491

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54aacea44f258deb3576f80930c6fafb9238f9e3d72b655aac830cd2b3088a41
+size 30964147