Update tiny models for VideoPrismForVideoClassification

config.json

@@ -0,0 +1,30 @@
+{
+  "apply_l2norm": true,
+  "architectures": [
+    "VideoPrismForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "dtype": "float32",
+  "hidden_act": "gelu_python",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 32,
+  "image_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "layer_norm_eps": 1e-06,
+  "model_type": "videoprism_vision_model",
+  "num_attention_heads": 4,
+  "num_auxiliary_layers": 2,
+  "num_channels": 3,
+  "num_frames": 3,
+  "num_spatial_layers": 3,
+  "num_temporal_layers": 2,
+  "qkv_bias": true,
+  "transformers_version": "5.16.0.dev0",
+  "tubelet_size": [
+    1,
+    4,
+    4
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6546440c8e07653e52835632dc2355fd61ac0d3a82c67bb4284c7fe228eb95c8
+size 224008

video_preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 8,
+    "width": 8
+  },
+  "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": 8,
+    "width": 8
+  },
+  "video_processor_type": "LlavaOnevisionVideoProcessor"
+}