Update app.py

app.py

@@ -1,63 +1,57 @@
 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}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    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
-
-        response += token
-        yield response
-
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import spaces
+from mistral_inference.transformer import Transformer
+from mistral_inference.generate import generate
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.protocol.instruct.messages import UserMessage, TextChunk, ImageURLChunk
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
+from huggingface_hub import snapshot_download
+from pathlib import Path
+
+# モデルのダウンロードと準備
+mistral_models_path = Path.home().joinpath('mistral_models', 'Pixtral')
+mistral_models_path.mkdir(parents=True, exist_ok=True)
+
+snapshot_download(repo_id="mistralai/Pixtral-12B-2409", 
+                  allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], 
+                  local_dir=mistral_models_path)
+
+# トークナイザーとモデルのロード
+tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tekken.json")
+model = Transformer.from_folder(mistral_models_path)
+
+# 推論処理
+@spaces.GPU
+def mistral_inference(prompt, image_url):
+    completion_request = ChatCompletionRequest(
+        messages=[UserMessage(content=[ImageURLChunk(image_url=image_url), TextChunk(text=prompt)])]
+    )
+    
+    encoded = tokenizer.encode_chat_completion(completion_request)
+    images = encoded.images
+    tokens = encoded.tokens
+
+    out_tokens, _ = generate([tokens], model, images=[images], max_tokens=256, temperature=0.35, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+    result = tokenizer.decode(out_tokens[0])
+    
+    return result
+
+# Gradio インターフェース
+def process_input(text, image_url):
+    result = mistral_inference(text, image_url)
+    return result
+
+with gr.Blocks() as demo:
+    gr.Markdown("## Pixtralモデルによる画像説明生成")
+    
+    with gr.Row():
+        text_input = gr.Textbox(label="テキストプロンプト", placeholder="例: Describe the image.")
+        image_input = gr.Textbox(label="画像URL", placeholder="例: https://example.com/image.png")
+    
+    result_output = gr.Textbox(label="モデルの出力結果")
+    
+    submit_button = gr.Button("推論を実行")
+    
+    submit_button.click(process_input, inputs=[text_input, image_input], outputs=result_output)
+
+demo.launch()