Upload 3 files

README.md

@@ -1,12 +1,13 @@
----
-title: Llama Test
-emoji: 🐠
-colorFrom: indigo
-colorTo: red
-sdk: gradio
-sdk_version: 5.5.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: test
+emoji: 🙄
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,87 @@
+import os
+if os.environ.get("SPACES_ZERO_GPU") is not None:
+    import spaces
+else:
+    class spaces:
+        @staticmethod
+        def GPU(func):
+            def wrapper(*args, **kwargs):
+                return func(*args, **kwargs)
+            return wrapper
+import gradio as gr
+import requests
+import torch
+from PIL import Image
+from transformers import MllamaForConditionalGeneration, AutoProcessor
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+#model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+model_id = "unsloth/Llama-3.2-11B-Vision-Instruct"
+#model_id = "unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit"
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
+
+model = MllamaForConditionalGeneration.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
+processor = AutoProcessor.from_pretrained(model_id)
+
+@spaces.GPU(duration=30)
+def infer(message: str, url: str):
+    kwargs = {}
+    image = Image.open(requests.get(url, stream=True).raw) if url and "http" in url else ""
+    if image: kwargs["images"] = image
+    messages = [
+        {"role": "user", "content": [
+            {"type": "image"},
+            {"type": "text", "text": message}
+        ]}
+    ]
+    
+    input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
+    #input_text = "<|image|> If I had to write a haiku for this one, it would be: "
+    inputs = processor(
+        text=input_text,
+        add_special_tokens=False,
+        return_tensors="pt",
+        **kwargs,
+    ).to(model.device)
+
+    output = model.generate(**inputs, max_new_tokens=30)
+    output_str = processor.decode(output[0])
+    print(message)
+    print(url)
+    print(output_str)
+    return output_str
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        message = gr.Textbox(label="Message", value="Describe the image.", lines=1)
+        image_url = gr.Textbox(label="Image URL", value=url, lines=1)
+    run_button = gr.Button("Run", variant="primary")
+    info_md = gr.Markdown("<br><br><br>")
+
+    run_button.click(infer, [message, image_url], [info_md])
+
+demo.launch()
+
+"""
+Describe the image.
+https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg
+<|begin_of_text|><|start_header_id|>user<|end_header_id|>
+
+<|image|>Describe the image.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+This image features a charming anthropomorphic rabbit, attired in a brown waistcoat and tan pants, with a blue coat draped over his shoulders, standing
+If I had to write a haiku for this one, it would be: 
+
+<|begin_of_text|><|start_header_id|>user<|end_header_id|>
+
+<|image|>If I had to write a haiku for this one, it would be: <|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+It seems like you started to write a haiku but didn't finish. Would you like to complete it?<|eot_id|>
+Who are you?
+
+<|begin_of_text|><|start_header_id|>user<|end_header_id|>
+
+<|image|>Who are you?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+I'm an artificial intelligence model known as Llama. Llama stands for "Large Language Model Meta AI."<|eot_id|>
+"""

requirements.txt

@@ -0,0 +1,7 @@
+huggingface_hub==0.26.1
+torch
+transformers==4.45.0
+bitsandbytes
+accelerate==1.0.1
+numpy==1.26.4
+datasets==3.0.2