The first version, only recongnize the image

app.py

@@ -1,64 +1,36 @@
+from transformers import MllamaForConditionalGeneration, AutoProcessor, TextIteratorStreamer
+import torch
+from threading import Thread
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+from gradio import FileData
+import spaces
+model_id = "meta-llama/Llama-3.2-11B-Vision"
+
+model = MllamaForConditionalGeneration.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+processor = AutoProcessor.from_pretrained(model)
 
-    messages.append({"role": "user", "content": message})
 
-    response = ""
+@spaces.GPU
+def score_it(input_img):
+    image = input_img.convert("RGB").resize((224, 224))
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    prompt = "<|image|><|begin_of_text|>extract the text in this picture"
+    inputs = processor(image, prompt, return_tensors="pt").to(model.device)
 
-        response += token
-        yield response
+    output = model.generate(**inputs, max_new_tokens=30)
+    print(processor.decode(output[0]))
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+demo = gr.ChatInterface(fn=score_it, title="Upload your English script and get the score",
 
+                        inputs=[gr.Image()],
+                        outputs=['text'],
+                        stop_btn="Stop Generation",
+                        )
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch(debug=True)

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+torch
+spaces
+git+https://github.com/huggingface/transformers.git