Update app.py

app.py

@@ -1,32 +1,56 @@
-
-from sonique import get_pretrained_model
-from sonique.interface.gradio import create_ui
-import json 
-from huggingface_hub import login
+import requests
+import subprocess
+subprocess.run(
+    "pip install flash-attn --no-build-isolation",
+    env={"FLASH_ATTENTION_SKIP_CUDA_BUILD": "TRUE"},
+    shell=True,
+)
 import torch
-import os
+import gradio as gr
+from PIL import Image
+from transformers import AutoModelForCausalLM, AutoProcessor
 
-login(token=os.getenv('HF_TOKEN'))
+model_id_or_path = "rhymes-ai/Aria"
 
-interface = create_ui(
-    model_config_path = str(cached_path('https://raw.githubusercontent.com/zxxwxyyy/sonique/refs/heads/main/best_model.json')),
-    ckpt_path=str(cached_path('hf://mrfakename/SONIQUE/stable_ep=220.ckpt')),
-    # pretrained_name=args.pretrained_name,
-    pretransform_ckpt_path=None
-)
-interface.queue().launch()
-
-
-    
-
-if __name__ == "__main__":
-    import argparse
-    parser = argparse.ArgumentParser(description='Run gradio interface')
-    parser.add_argument('--pretrained-name', type=str, help='Name of pretrained model', required=False)
-    parser.add_argument('--model-config', type=str, help='Path to model config', required=False)
-    parser.add_argument('--ckpt-path', type=str, help='Path to model checkpoint', required=False)
-    parser.add_argument('--pretransform-ckpt-path', type=str, help='Optional to model pretransform checkpoint', required=False)
-    parser.add_argument('--username', type=str, help='Gradio username', required=False)
-    parser.add_argument('--password', type=str, help='Gradio password', required=False)
-    args = parser.parse_args()
-    main(args)
+model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
+
+processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)
+
+image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
+
+image = Image.open(requests.get(image_path, stream=True).raw)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"text": None, "type": "image"},
+            {"text": "what is the image?", "type": "text"},
+        ],
+    }
+]
+
+text = processor.apply_chat_template(messages, add_generation_prompt=True)
+inputs = processor(text=text, images=image, return_tensors="pt")
+inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)
+inputs = {k: v.to(model.device) for k, v in inputs.items()}
+@spaces.GPU
+def run():
+    with torch.inference_mode(), torch.cuda.amp.autocast(dtype=torch.bfloat16):
+        output = model.generate(
+            **inputs,
+            max_new_tokens=500,
+            stop_strings=["<|im_end|>"],
+            tokenizer=processor.tokenizer,
+            do_sample=True,
+            temperature=0.9,
+        )
+        output_ids = output[0][inputs["input_ids"].shape[1]:]
+        result = processor.decode(output_ids, skip_special_tokens=True)
+
+with gr.Blocks() as demo:
+    btn = gr.Button("Run")
+    out = gr.Markdown()
+    btn.click(run, outputs=out)
+
+demo.queue().launch()