fix: switch from Docker to Gradio SDK to fix build timeout

llama-cpp-python compiles from source in Docker, timing out on
cpu-basic. Gradio SDK builder has pre-built wheels.

Dockerfile

@@ -1,17 +0,0 @@
-FROM python:3.11-slim
-
-RUN apt-get update && apt-get install -y build-essential cmake && rm -rf /var/lib/apt/lists/*
-RUN pip install --no-cache-dir \
-    "gradio==4.44.1" \
-    "huggingface-hub==0.26.5" \
-    "llama-cpp-python>=0.3.0"
-
-RUN useradd -m -u 1000 user
-RUN mkdir -p /tmp/hf_cache && chown -R user:user /tmp/hf_cache
-USER user
-WORKDIR /app
-COPY app.py .
-ENV PYTHONUNBUFFERED=1
-ENV HF_HOME=/tmp/hf_cache
-EXPOSE 7860
-CMD ["python", "app.py"]

README.md

@@ -1,9 +1,15 @@
 ---
 title: The Void - Buleyean RL Demo
-emoji: 🕳️
+emoji: "\U0001F573\uFE0F"
 colorFrom: gray
 colorTo: indigo
-sdk: docker
-app_port: 7860
+sdk: gradio
+sdk_version: 5.23.0
+python_version: "3.11"
+app_file: app.py
 pinned: true
+models:
+  - bartowski/SmolLM2-360M-Instruct-GGUF
+  - forkjoin-ai/buleyean-smollm2-360m
+  - HuggingFaceTB/SmolLM2-360M-Instruct
 ---

requirements.txt

@@ -1,9 +1,2 @@
-gradio>=4.44.0,<5.0.0
-transformers>=4.46.0
-peft>=0.13.0
-torch>=2.1.0
-accelerate>=1.0.0
-sentencepiece>=0.2.0
-protobuf>=4.25.0
-numpy>=1.26.0
-scipy>=1.12.0
+llama-cpp-python>=0.3.0
+huggingface-hub>=0.26.0