This PR adds 2 examples

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Example2.png filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,95 +1,97 @@
-from transformers import MllamaForConditionalGeneration, AutoProcessor, TextIteratorStreamer
-from PIL import Image
-import requests
-import torch
-from threading import Thread
-import gradio as gr
-from gradio import FileData
-import time
-import spaces
-import re
-ckpt = "Xkev/Llama-3.2V-11B-cot"
-model = MllamaForConditionalGeneration.from_pretrained(ckpt,
-    torch_dtype=torch.bfloat16).to("cuda")
-processor = AutoProcessor.from_pretrained(ckpt)
-
-
-@spaces.GPU
-def bot_streaming(message, history, max_new_tokens=250):
-    
-    txt = message["text"]
-    ext_buffer = f"{txt}"
-    
-    messages= [] 
-    images = []
-    
-
-    for i, msg in enumerate(history): 
-        if isinstance(msg[0], tuple):
-            messages.append({"role": "user", "content": [{"type": "text", "text": history[i+1][0]}, {"type": "image"}]})
-            messages.append({"role": "assistant", "content": [{"type": "text", "text": history[i+1][1]}]})
-            images.append(Image.open(msg[0][0]).convert("RGB"))
-        elif isinstance(history[i-1], tuple) and isinstance(msg[0], str):
-            # messages are already handled
-            pass
-        elif isinstance(history[i-1][0], str) and isinstance(msg[0], str): # text only turn
-            messages.append({"role": "user", "content": [{"type": "text", "text": msg[0]}]})
-            messages.append({"role": "assistant", "content": [{"type": "text", "text": msg[1]}]})
-
-    # add current message
-    if len(message["files"]) == 1:
-        
-        if isinstance(message["files"][0], str): # examples
-            image = Image.open(message["files"][0]).convert("RGB")
-        else: # regular input
-            image = Image.open(message["files"][0]["path"]).convert("RGB")
-        images.append(image)
-        messages.append({"role": "user", "content": [{"type": "text", "text": txt}, {"type": "image"}]})
-    else:
-        messages.append({"role": "user", "content": [{"type": "text", "text": txt}]})
-
-
-    texts = processor.apply_chat_template(messages, add_generation_prompt=True)
-
-    if images == []:
-        inputs = processor(text=texts, return_tensors="pt").to("cuda")
-    else:
-        inputs = processor(text=texts, images=images, return_tensors="pt").to("cuda")
-        
-    streamer = TextIteratorStreamer(processor, skip_special_tokens=True, skip_prompt=True)
-
-    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_new_tokens)
-    generated_text = ""
-    
-    thread = Thread(target=model.generate, kwargs=generation_kwargs)
-    thread.start()
-    buffer = ""
-    
-    for new_text in streamer:
-        buffer += new_text
-        generated_text_without_prompt = buffer
-        time.sleep(0.01)
-    
-        buffer = re.sub(r"<(\w+)>", r"(Here begins the \1 stage)", buffer)  
-        buffer = re.sub(r"</(\w+)>", r"(Here ends the \1 stage)", buffer)  
-    
-        yield buffer
-
-
-demo = gr.ChatInterface(fn=bot_streaming, title="LLaVA-CoT",
-      textbox=gr.MultimodalTextbox(), 
-      additional_inputs = [gr.Slider(
-              minimum=512,
-              maximum=1024,
-              value=512,
-              step=1,
-              label="Maximum number of new tokens to generate",
-          )
-        ],
-      cache_examples=False,
-      description="Upload an image, and start chatting about it. To learn more about LLaVA-CoT, visit [our GitHub page](https://github.com/PKU-YuanGroup/LLaVA-CoT). Note: Since Gradio currently does not support displaying the special markings in the output, we have replaced it with the expression (Here begins the X phase).",
-      stop_btn="Stop Generation", 
-      fill_height=True,
-    multimodal=True)
-    
+from transformers import MllamaForConditionalGeneration, AutoProcessor, TextIteratorStreamer
+from PIL import Image
+import requests
+import torch
+from threading import Thread
+import gradio as gr
+from gradio import FileData
+import time
+import spaces
+import re
+ckpt = "Xkev/Llama-3.2V-11B-cot"
+model = MllamaForConditionalGeneration.from_pretrained(ckpt,
+    torch_dtype=torch.bfloat16).to("cuda")
+processor = AutoProcessor.from_pretrained(ckpt)
+
+
+@spaces.GPU
+def bot_streaming(message, history, max_new_tokens=250):
+    
+    txt = message["text"]
+    ext_buffer = f"{txt}"
+    
+    messages= [] 
+    images = []
+    
+
+    for i, msg in enumerate(history): 
+        if isinstance(msg[0], tuple):
+            messages.append({"role": "user", "content": [{"type": "text", "text": history[i+1][0]}, {"type": "image"}]})
+            messages.append({"role": "assistant", "content": [{"type": "text", "text": history[i+1][1]}]})
+            images.append(Image.open(msg[0][0]).convert("RGB"))
+        elif isinstance(history[i-1], tuple) and isinstance(msg[0], str):
+            # messages are already handled
+            pass
+        elif isinstance(history[i-1][0], str) and isinstance(msg[0], str): # text only turn
+            messages.append({"role": "user", "content": [{"type": "text", "text": msg[0]}]})
+            messages.append({"role": "assistant", "content": [{"type": "text", "text": msg[1]}]})
+
+    # add current message
+    if len(message["files"]) == 1:
+        
+        if isinstance(message["files"][0], str): # examples
+            image = Image.open(message["files"][0]).convert("RGB")
+        else: # regular input
+            image = Image.open(message["files"][0]["path"]).convert("RGB")
+        images.append(image)
+        messages.append({"role": "user", "content": [{"type": "text", "text": txt}, {"type": "image"}]})
+    else:
+        messages.append({"role": "user", "content": [{"type": "text", "text": txt}]})
+
+
+    texts = processor.apply_chat_template(messages, add_generation_prompt=True)
+
+    if images == []:
+        inputs = processor(text=texts, return_tensors="pt").to("cuda")
+    else:
+        inputs = processor(text=texts, images=images, return_tensors="pt").to("cuda")
+        
+    streamer = TextIteratorStreamer(processor, skip_special_tokens=True, skip_prompt=True)
+
+    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_new_tokens)
+    generated_text = ""
+    
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+    buffer = ""
+    
+    for new_text in streamer:
+        buffer += new_text
+        generated_text_without_prompt = buffer
+        time.sleep(0.01)
+    
+        buffer = re.sub(r"<(\w+)>", r"(Here begins the \1 stage)", buffer)  
+        buffer = re.sub(r"</(\w+)>", r"(Here ends the \1 stage)", buffer)  
+    
+        yield buffer
+
+
+demo = gr.ChatInterface(fn=bot_streaming, title="LLaVA-CoT",
+      textbox=gr.MultimodalTextbox(), 
+      additional_inputs = [gr.Slider(
+              minimum=512,
+              maximum=1024,
+              value=512,
+              step=1,
+              label="Maximum number of new tokens to generate",
+          )
+        ],
+      examples=[{"text": "What is on the flower?", "files": ["./Example1.webp"]},
+                {"text": "How to make this pastry?", "files": ["./Example2.png"]}],
+      cache_examples=False,
+      description="Upload an image, and start chatting about it. To learn more about LLaVA-CoT, visit [our GitHub page](https://github.com/PKU-YuanGroup/LLaVA-CoT). Note: Since Gradio currently does not support displaying the special markings in the output, we have replaced it with the expression (Here begins the X phase).",
+      stop_btn="Stop Generation", 
+      fill_height=True,
+    multimodal=True)
+    
 demo.launch(debug=True)