Upload 5 files

mm_projector/config.json

@@ -0,0 +1,10 @@
+{
+  "_name_or_path": "./LongVILA-R1-7B/mm_projector",
+  "architectures": [
+    "MultimodalProjector"
+  ],
+  "mm_projector_type": "mlp_downsample_2x2_fix",
+  "model_type": "v2l_projector",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2"
+}

mm_projector/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7c609b2101362c7d9eff47c7b9614deb522870142caa0bfe5853a7fd375809
+size 58753552

vision_tower/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "./LongVILA-R1-7B/vision_tower",
+  "architectures": [
+    "SiglipVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "image_size": 448,
+  "intermediate_size": 4304,
+  "layer_norm_eps": 1e-06,
+  "model_type": "siglip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 27,
+  "num_image_tokens": 256,
+  "patch_size": 14,
+  "projection_dim": 2048,
+  "projector_hidden_act": "gelu_fast",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "vision_use_head": false,
+  "_attn_implementation": "flash_attention_2"
+}

vision_tower/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da663dfa03dc91b404e602067e5e1b4d0e31298f6645dae46a80facc6c2f7de
+size 826707904

vision_tower/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}