Update app.py

app.py

@@ -4,12 +4,14 @@ from threading import Thread
 import gradio as gr
 import torch
 from PIL import Image
-from transformers import AutoProcessor, LlavaForConditionalGeneration
+#from transformers import AutoProcessor, LlavaForConditionalGeneration
 from transformers import TextIteratorStreamer
+from transformers import LlavaNextForConditionalGeneration, LlavaNextProcessor
+from PIL import Image
+import requests
 
 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;  "> 
@@ -17,20 +19,45 @@ PLACEHOLDER = """
    <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>
 </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"
 
-model_id = "xtuner/llava-llama-3-8b-v1_1-transformers"
+#processor = AutoProcessor.from_pretrained(model_id)
+processor = LlavaNextProcessor.from_pretrained("tiiuae/falcon-11B-vlm", tokenizer_class='PreTrainedTokenizerFast')
 
-processor = AutoProcessor.from_pretrained(model_id)
+model = LlavaNextForConditionalGeneration.from_pretrained("tiiuae/falcon-11B-vlm", torch_dtype=torch.bfloat16)
 
-model = LlavaForConditionalGeneration.from_pretrained(
-    model_id,
-    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
+#model.generation_config.eos_token_id = 128009
 
 
 @spaces.GPU
@@ -91,7 +118,7 @@ chat_input = gr.MultimodalTextbox(interactive=True, file_types=["image"], placeh
 with gr.Blocks(fill_height=True, ) as demo:
     gr.ChatInterface(
     fn=bot_streaming,
-    title="LLaVA Llama-3-8B",
+    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.",