Update app.py

app.py

@@ -5,7 +5,8 @@ from typing import List, Tuple
 import aiohttp
 import panel as pn
 from PIL import Image
-from transformers import CLIPModel, CLIPProcessor
+# from transformers import CLIPModel, CLIPProcessor
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 pn.extension(design="bootstrap", sizing_mode="stretch_width")
 
@@ -18,81 +19,55 @@ ICON_URLS = {
 }
 
 
-async def random_url(_):
-    pet = random.choice(["cat", "dog"])
-    api_url = f"https://api.the{pet}api.com/v1/images/search"
-    async with aiohttp.ClientSession() as session:
-        async with session.get(api_url) as resp:
-            return (await resp.json())[0]["url"]
 
+def load_tokenizer_model():
+    tokenizer = AutoTokenizer.from_pretrained("Salesforce/xgen-7b-8k-base", trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained("Salesforce/xgen-7b-8k-base", torch_dtype=torch.bfloat16)
+    return tokenizer,model
 
-@pn.cache
-def load_processor_model(
-    processor_name: str, model_name: str
-) -> Tuple[CLIPProcessor, CLIPModel]:
-    processor = CLIPProcessor.from_pretrained(processor_name)
-    model = CLIPModel.from_pretrained(model_name)
-    return processor, model
 
 
-async def open_image_url(image_url: str) -> Image:
-    async with aiohttp.ClientSession() as session:
-        async with session.get(image_url) as resp:
-            return Image.open(io.BytesIO(await resp.read()))
-
-
-def get_similarity_scores(class_items: List[str], image: Image) -> List[float]:
-    processor, model = load_processor_model(
-        "openai/clip-vit-base-patch32", "openai/clip-vit-base-patch32"
-    )
-    inputs = processor(
-        text=class_items,
-        images=[image],
-        return_tensors="pt",  # pytorch tensors
-    )
-    outputs = model(**inputs)
-    logits_per_image = outputs.logits_per_image
-    class_likelihoods = logits_per_image.softmax(dim=1).detach().numpy()
-    return class_likelihoods[0]
-
-
-async def process_inputs(class_names: List[str], image_url: str):
+async def process_inputs(class_names: List[str], user_text: str):
     """
     High level function that takes in the user inputs and returns the
     classification results as panel objects.
     """
     try:
         main.disabled = True
-        if not image_url:
-            yield "##### ⚠️ Provide an image URL"
+        if not user_text:
+            yield "##### ⚠️ Provide some user text URL"
             return
     
-        yield "##### ⚙ Fetching image and running model..."
+        yield "##### ⚙ Fetching and running model..."
         try:
-            pil_img = await open_image_url(image_url)
-            img = pn.pane.Image(pil_img, height=400, align="center")
+            inputs = tokenizer("The world is", return_tensors="pt")
+            sample = model.generate(**inputs, max_length=128)
+
+            # pil_img = await open_image_url(image_url)
+            # img = pn.pane.Image(pil_img, height=400, align="center")
         except Exception as e:
             yield f"##### 😔 Something went wrong, please try a different URL!"
             return
     
-        class_items = class_names.split(",")
-        class_likelihoods = get_similarity_scores(class_items, pil_img)
+        # class_items = class_names.split(",")
+        # class_likelihoods = get_similarity_scores(class_items, pil_img)
     
         # build the results column
-        results = pn.Column("##### 🎉 Here are the results!", img)
-    
-        for class_item, class_likelihood in zip(class_items, class_likelihoods):
-            row_label = pn.widgets.StaticText(
-                name=class_item.strip(), value=f"{class_likelihood:.2%}", align="center"
-            )
-            row_bar = pn.indicators.Progress(
-                value=int(class_likelihood * 100),
-                sizing_mode="stretch_width",
-                bar_color="secondary",
-                margin=(0, 10),
-                design=pn.theme.Material,
-            )
-            results.append(pn.Column(row_label, row_bar))
+            
+        results = pn.Column("##### 🎉 Here are the results!", tokenizer.decode(sample[0])))
+        
+        # for class_item, class_likelihood in zip(class_items, class_likelihoods):
+        #     row_label = pn.widgets.StaticText(
+        #         name=class_item.strip(), value=f"{class_likelihood:.2%}", align="center"
+        #     )
+        #     row_bar = pn.indicators.Progress(
+        #         value=int(class_likelihood * 100),
+        #         sizing_mode="stretch_width",
+        #         bar_color="secondary",
+        #         margin=(0, 10),
+        #         design=pn.theme.Material,
+        #     )
+        #     results.append(pn.Column(row_label, row_bar))
         yield results
     finally:
         main.disabled = False
@@ -112,7 +87,7 @@ class_names = pn.widgets.TextInput(
 )
 
 input_widgets = pn.Column(
-    "##### 😊 Click randomize or paste a URL to start classifying!",
+    "##### Add some text and do something",
     pn.Row(image_url, randomize_url),
     class_names,
 )
@@ -138,7 +113,7 @@ main = pn.WidgetBox(
     footer_row,
 )
 
-title = "Panel Demo - Image Classification"
+title = "Xgen input panel"
 pn.template.BootstrapTemplate(
     title=title,
     main=main,