Allow gradient viz for J-CLIP and ResNet, disable for M-CLIP

app.py

@@ -111,7 +111,7 @@ def clip_search(search_query):
 
 def string_search():
     st.session_state.disable_uploader = (
-        RUN_LITE and st.session_state.active_model == "Legacy (multilingual ResNet)"
+        RUN_LITE and st.session_state.active_model == "M-CLIP (multilingual ViT)"
     )
 
     if "search_field_value" in st.session_state:
@@ -171,9 +171,10 @@ def init():
         ml_model_name = "M-CLIP/XLM-Roberta-Large-Vit-B-16Plus"
         ml_model_path = "./models/vit_b_16_plus_240-laion400m_e32-699c4b84.pt"
 
-        st.session_state.ml_image_model, st.session_state.ml_image_preprocess = load(
-            ml_model_path, device=device, jit=False
-        )
+        if not RUN_LITE:
+            st.session_state.ml_image_model, st.session_state.ml_image_preprocess = (
+                load(ml_model_path, device=device, jit=False)
+            )
 
         st.session_state.ml_model = (
             pt_multilingual_clip.MultilingualCLIP.from_pretrained(ml_model_name)
@@ -194,10 +195,9 @@ def init():
             ja_model_name, trust_remote_code=True
         )
 
-        if not RUN_LITE:
-            st.session_state.rn_image_model, st.session_state.rn_image_preprocess = (
-                clip.load("RN50x4", device=device)
-            )
+        st.session_state.rn_image_model, st.session_state.rn_image_preprocess = (
+            clip.load("RN50x4", device=device)
+        )
 
         st.session_state.rn_model = legacy_multilingual_clip.load_model(
             "M-BERT-Base-69"
@@ -213,7 +213,7 @@ def init():
         with open("./images_list.txt", "r", encoding="utf-8") as images_list:
             st.session_state.image_ids = list(images_list.read().strip().split("\n"))
 
-        st.session_state.active_model = "M-CLIP (multilingual ViT)"
+        st.session_state.active_model = "J-CLIP (日本語 ViT)"
 
     st.session_state.vision_mode = "tiled"
     st.session_state.search_image_ids = []
@@ -662,8 +662,8 @@ with search_row[6]:
     st.selectbox(
         "CLIP Model:",
         options=[
-            "M-CLIP (multilingual ViT)",
             "J-CLIP (日本語 ViT)",
+            "M-CLIP (multilingual ViT)",
             "Legacy (multilingual ResNet)",
         ],
         key="active_model",
@@ -787,7 +787,7 @@ for image_id in batch:
             unsafe_allow_html=True,
         )
         if not (
-            RUN_LITE and st.session_state.active_model == "Legacy (multilingual ResNet)"
+            RUN_LITE and st.session_state.active_model == "M-CLIP (multilingual ViT)"
         ):
             st.button(
                 "Explain this",