Training in progress, step 39

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "../../checkpoints/siglip-so400m-patch14-384/siglip-video_16384/initial_model",
   "architectures": [
     "SiglipVideoModel"
   ],

initial_model/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "SiglipVideoModel"
+  ],
+  "initializer_factor": 1.0,
+  "model_type": "siglip_video",
+  "perceiver_config": {
+    "_attn_implementation_autoset": true,
+    "model_type": "siglip_video_perceiver"
+  },
+  "text_config": {
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  }
+}

initial_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c060a01c78afa749ae65e6dafdfab404ef427e2caf8477a0b88321c9b078b9
+size 1908776156

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e6538d38bb2462a4f2d15f5f4d0a89137ad39b0a5246000b08b7c950227e95
+oid sha256:a69d2eff5f9e67eb7cbdf96da4ddd284e8c61a9d11909a4833c5077454ad200b
 size 1908776156

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6c0ba6a436ee619bd4f2a05986d3984764737230c65d64d5bc018ee28d7464e
+oid sha256:2babfac6d2015857e2311adcab661baead4b4af170cff1a8f9f1498e55867941
 size 6712