Update tiny models for InstructBlipVideoModel

config.json

@@ -0,0 +1,76 @@
+{
+  "architectures": [
+    "InstructBlipVideoModel"
+  ],
+  "dtype": "float32",
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "instructblipvideo",
+  "num_query_tokens": 10,
+  "qformer_config": {
+    "attention_dropout": 0.1,
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": 0,
+    "cross_attention_frequency": 2,
+    "dropout": 0.1,
+    "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": "instructblipvideo_qformer",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "pad_token_id": 0,
+    "projection_dim": 32,
+    "vocab_size": 99
+  },
+  "text_config": {
+    "_remove_final_layer_norm": false,
+    "activation_function": "relu",
+    "attention_dropout": 0.1,
+    "bos_token_id": 0,
+    "do_layer_norm_before": true,
+    "dropout": 0.1,
+    "embed_dim": 16,
+    "enable_bias": true,
+    "eos_token_id": 1,
+    "ffn_dim": 4,
+    "hidden_size": 16,
+    "init_std": 0.02,
+    "layer_norm_elementwise_affine": true,
+    "layerdrop": 0.0,
+    "max_position_embeddings": 200,
+    "model_type": "opt",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "pad_token_id": 0,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 32102,
+    "word_embed_proj_dim": 16
+  },
+  "transformers_version": "5.16.0.dev0",
+  "use_decoder_only_language_model": true,
+  "video_token_index": 4,
+  "vision_config": {
+    "attention_dropout": 0.1,
+    "dropout": 0.1,
+    "hidden_act": "gelu",
+    "hidden_size": 32,
+    "image_size": 30,
+    "initializer_range": 1e-10,
+    "intermediate_size": 37,
+    "layer_norm_eps": 1e-06,
+    "model_type": "instructblipvideo_vision_model",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 2,
+    "projection_dim": 32,
+    "qkv_bias": true
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0392b0be4eb96bb82f40dd33355f398cdd637744114288b1999e6aa65202850
+size 2351296

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 30,
+    "width": 30
+  },
+  "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": 30,
+    "width": 30
+  }
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "InstructBlipProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "left",
+  "unk_token": "<unk>"
+}

video_preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 30,
+    "width": 30
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "height": 30,
+    "width": 30
+  },
+  "video_processor_type": "InstructBlipVideoVideoProcessor"
+}