Update text_encoder_2/config.json

text_encoder_2/config.json

@@ -1,31 +1,24 @@
 {
   "architectures": [
-    "T5EncoderModel"
+    "CLIPTextModelWithProjection"
   ],
-  "classifier_dropout": 0.0,
-  "d_ff": 10240,
-  "d_kv": 64,
-  "d_model": 4096,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
+  "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,
-  "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "num_decoder_layers": 24,
-  "num_heads": 64,
-  "num_layers": 24,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
+  "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": "float16",
   "transformers_version": "4.41.2",
-  "use_cache": true,
-  "vocab_size": 32128
-}
+  "vocab_size": 49408
+}