Deploy SPACE

app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+import torch
+from transformers import BitsAndBytesConfig, pipeline
+
+# Load model directly
+quantization_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.float16
+)
+
+model_id = "llava-hf/llava-1.5-7b-hf"
+pipe = pipeline("image-to-text", model=model_id, model_kwargs={"quantization_config": quantization_config})
+
+def generate_text(image):
+    max_new_tokens = 200
+    prompt = "USER: <image>\nWhat are the things I should be cautious about when I visit this place?\nASSISTANT:"
+    outputs = pipe(image, prompt=prompt, generate_kwargs={"max_new_tokens": 200})
+    return outputs[0]["generated_text"]
+
+iface = gr.Interface(fn=generate_text, inputs=gr.inputs.Image(), outputs="text")
+iface.launch()

requirements.txt

@@ -0,0 +1,4 @@
+transformers==4.37.2
+bitsandbytes==0.41.3
+accelerate==0.25.0
+gradio