Upload model

config.json

@@ -1,25 +1,21 @@
 {
   "architectures": [
-    "Blip2QFormerModel"
+    "ImageQFormerModel"
   ],
-  "num_query_tokens": 32,
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "cross_attention_frequency": 2,
-  "encoder_hidden_size": 1408,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "blip_2_qformer",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "model_type": "blip_2_qformer"
+  },
+  "text_config": {
+    "model_type": "opt"
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
-  "vocab_size": 30522
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "model_type": "blip_2_vision_model"
+  }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d286e0cda62601dfa1ff37ec4a73951af8c49644da3174e1b3b4146b8a7a86
-size 420732489
+oid sha256:e01c57813d103c4430468dca693984c0f547e3a7fed28ea17208997e6c5d31b0
+size 4364700517