Upload BLIP-2 vision encoder + classifier head + processor

config.json

@@ -7,22 +7,16 @@
   "hidden_act": "gelu",
   "hidden_size": 1408,
   "id2label": {
-    "0": "extracting_part",
-    "1": "no_action",
-    "2": "storing_part",
-    "3": "unplugging_connector",
-    "4": "unscrewing"
+    "0": "idle_time",
+    "1": "unplugging_connector"
   },
   "image_size": 224,
   "initializer_factor": 1.0,
   "initializer_range": 1e-10,
   "intermediate_size": 6144,
   "label2id": {
-    "extracting_part": 0,
-    "no_action": 1,
-    "storing_part": 2,
-    "unplugging_connector": 3,
-    "unscrewing": 4
+    "idle_time": 0,
+    "unplugging_connector": 1
   },
   "layer_norm_eps": 1e-06,
   "model_type": "blip_2_vision_model",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d756aa39ac838743f1b3496160fac211ceb13c3aa339fc63894f3081d02d051
-size 3943889140
+oid sha256:5e4e7dec7b8fcb48c104d161338fb98c9a3ec8269089b07e0db1d770308060ef
+size 3943872232