Update tiny models for Blip2QFormerModel

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Blip2QFormerModel"
+  ],
+  "attention_dropout": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "cross_attention_frequency": 2,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "encoder_hidden_size": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "blip_2_qformer",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "pad_token_id": 1,
+  "projection_dim": 32,
+  "transformers_version": "5.16.0.dev0",
+  "use_qformer_text_input": false,
+  "vocab_size": 50266
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfdf372b59976d998a8bbf83228e0a0f31ca51892dc9131b4969606d4c05aafd
+size 76464

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "BlipImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "Blip2Processor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "</s>"
+}