feat: add llava script

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+from transformers import AutoProcessor, LlavaForConditionalGeneration
+import torch
+from PIL import Image
+
+# Load model and processor
+model_id = "llava-hf/llava-1.5-7b-hf"
+processor = AutoProcessor.from_pretrained(model_id)
+model = LlavaForConditionalGeneration.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
+
+# Inference function
+def chat_with_image(image, prompt):
+    inputs = processor(prompt, image, return_tensors="pt").to("cuda", torch.float16)
+    output = model.generate(**inputs, max_new_tokens=100)
+    answer = processor.decode(output[0], skip_special_tokens=True)
+    return answer
+
+# Gradio interface
+demo = gr.Interface(
+    fn=chat_with_image,
+    inputs=[gr.Image(type="pil"), gr.Textbox(label="Prompt")],
+    outputs=gr.Textbox(label="Answer"),
+    title="LLaVA 1.5 - Image Chatbot",
+    description="Ask questions about an image using LLaVA 1.5 (7B)"
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+torch
+transformers
+gradio
+accelerate
+Pillow