Create app.py

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+import os
+
+# Modell-Download (GGUF ist perfekt für CPU)
+print("Lade DeepSeek-R1 (GGUF) herunter...")
+model_path = hf_hub_download(
+    repo_id="unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF",
+    filename="DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf"
+)
+
+# Initialisierung (n_threads=4 für HF Free CPU)
+llm = Llama(
+    model_path=model_path,
+    n_ctx=2048,
+    n_threads=4
+)
+
+def respond(message, history):
+    # DeepSeek-R1 Denk-Prozess einleiten
+    prompt = f"User: {message}\nAssistant: <think>\n"
+    
+    stream = llm(
+        prompt,
+        max_tokens=1024,
+        stop=["User:", "<|endoftext|>"],
+        stream=True,
+        temperature=0.7
+    )
+
+    response = ""
+    for chunk in stream:
+        token = chunk["choices"][0]["text"]
+        response += token
+        yield response
+
+# Gradio UI auf Port 7860 (Standard für HF)
+demo = gr.ChatInterface(fn=respond, title="DeepSeek-R1 CPU Docker")
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)