Update app.py

app.py

@@ -14,54 +14,20 @@ import spaces
 
 PLACEHOLDER = """
 <div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
-   <img src="https://cdn-uploads.huggingface.co/production/uploads/64ccdc322e592905f922a06e/DDIW0kbWmdOQWwy4XMhwX.png" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  "> 
-   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">LLaVA-Llama-3-8B</h1>
-   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Llava-Llama-3-8b is a LLaVA model fine-tuned from Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336 with ShareGPT4V-PT and InternVL-SFT by XTuner</p>
+   <img src="https://raw.githubusercontent.com/huggingface/blog/09dbdfd196a3112ecbb533fc0b6c700571cbc753/assets/179_falcon2-11b/thumbnail.jpg" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  "> 
+   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">Falcon2-11B-VLM</h1>
+   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Falcon2-11B-VLM is an 11B parameters causal decoder-only model built by TII</p>
 </div>
 """
-#####################
-
-'''processor = LlavaNextProcessor.from_pretrained("tiiuae/falcon-11B-vlm", tokenizer_class='PreTrainedTokenizerFast')
-model = LlavaNextForConditionalGeneration.from_pretrained("tiiuae/falcon-11B-vlm", torch_dtype=torch.bfloat16)
-
-url = "http://images.cocodataset.org/val2017/000000039769.jpg"
-cats_image = Image.open(requests.get(url, stream=True).raw)
-instruction = 'Write a long paragraph about this picture.'
-
-prompt = f"""User:<image>\n{instruction} Falcon:"""
-inputs = processor(prompt, images=cats_image, return_tensors="pt", padding=True).to('cuda:0')
-
-model.to('cuda:0')
-output = model.generate(**inputs, max_new_tokens=256)
-
-
-prompt_length = inputs['input_ids'].shape[1]
-generated_captions = processor.decode(output[0], skip_special_tokens=True).strip()
-
-print(generated_captions)
-'''
-#############################
-
-#model_id = "xtuner/llava-llama-3-8b-v1_1-transformers"
 model_id = "tiiuae/falcon-11B-vlm"
 
-#processor = AutoProcessor.from_pretrained(model_id)
 processor = LlavaNextProcessor.from_pretrained("tiiuae/falcon-11B-vlm", tokenizer_class='PreTrainedTokenizerFast')
-
 model = LlavaNextForConditionalGeneration.from_pretrained("tiiuae/falcon-11B-vlm", 
                                                           torch_dtype=torch.bfloat16,
                                                           #torch_dtype=torch.float16,
                                                           low_cpu_mem_usage=True,)
 
-#model = LlavaForConditionalGeneration.from_pretrained(
-#    model_id,
-#    torch_dtype=torch.float16,
-#    low_cpu_mem_usage=True,
-#)
-
 model.to("cuda:0")
-#model.generation_config.eos_token_id = 128009
-
 
 @spaces.GPU
 def bot_streaming(message, history):
@@ -125,7 +91,7 @@ with gr.Blocks(fill_height=True, ) as demo:
     title="FalconVLM",
     examples=[{"text": "What is on the flower?", "files": ["./bee.jpg"]},
               {"text": "How to make this pastry?", "files": ["./baklava.png"]}],
-    description="Try [LLaVA Llama-3-8B](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers). Upload an image and start chatting about it, or simply try one of the examples below. If you don't upload an image, you will receive an error.",
+    description="Try [tiiuae/falcon-11B-VLM](https://huggingface.co/tiiuae/falcon-11B-vlm). Upload an image and start chatting about it, or simply try one of the examples below. If you don't upload an image, you will receive an error.",
     stop_btn="Stop Generation",
     multimodal=True,
     textbox=chat_input,