Add dockerfile and app.py

Dockerfile

@@ -0,0 +1,61 @@
+FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update && \
+    apt-get upgrade -y && \
+    apt-get install -y --no-install-recommends \
+    git \
+    git-lfs \
+    wget \
+    curl \
+    # python build dependencies \
+    build-essential \
+    libssl-dev \
+    zlib1g-dev \
+    libbz2-dev \
+    libreadline-dev \
+    libsqlite3-dev \
+    libncursesw5-dev \
+    xz-utils \
+    tk-dev \
+    libxml2-dev \
+    libxmlsec1-dev \
+    libffi-dev \
+    liblzma-dev \
+    # gradio dependencies \
+    ffmpeg
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:${PATH}
+WORKDIR ${HOME}/app
+
+RUN curl https://pyenv.run | bash
+ENV PATH=${HOME}/.pyenv/shims:${HOME}/.pyenv/bin:${PATH}
+ARG PYTHON_VERSION=3.10.13
+RUN pyenv install ${PYTHON_VERSION} && \
+    pyenv global ${PYTHON_VERSION} && \
+    pyenv rehash && \
+    pip install --no-cache-dir -U pip setuptools wheel && \
+    pip install "huggingface-hub" "hf-transfer"
+
+COPY --chown=1000 . ${HOME}/app
+RUN git clone https://github.com/ggerganov/llama.cpp && \
+    cd llama.cpp && \
+    make clean && \
+    LLAMA_CUDA=1 make
+
+RUN pip install -r llama.cpp/requirements.txt
+
+ENV PYTHONPATH=${HOME}/app \
+    PYTHONUNBUFFERED=1 \
+    HF_HUB_ENABLE_HF_TRANSFER=1 \
+    GRADIO_ALLOW_FLAGGING=never \
+    GRADIO_NUM_PORTS=1 \
+    GRADIO_SERVER_NAME=0.0.0.0 \
+    GRADIO_THEME=huggingface \
+    TQDM_POSITION=-1 \
+    TQDM_MININTERVAL=1 \
+    SYSTEM=spaces
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+import subprocess
+
+from huggingface_hub import HfApi, snapshot_download
+
+api = HfApi()
+
+
+def process_model(model_id: str, file_path: str, key: str, value: str, hf_token):
+
+    MODEL_NAME = model_id.split("/")[-1]
+
+    FILE_NAME = file_path.split("/")[-1]
+
+    snapshot_download(
+        repo_id=model_id,
+        allow_patterns=file_path,
+        local_dir=f"{MODEL_NAME}",
+    )
+    print("Model downloaded successully!")
+
+    metadata_update = f"python llama.cpp/gguf-py/scripts/gguf_set_metadata.py {MODEL_NAME}/{file_path} {key} {value}"
+    subprocess.run(metadata_update, shell=True)
+    print(f"Model metadata {key} updated to {value} successully!")
+
+    # Upload gguf files
+    api.upload_folder(
+        folder_path=MODEL_NAME,
+        repo_id=model_id,
+        allow_patterns=["*.gguf", "$.md"],
+        token=hf_token,
+    )
+    print("Uploaded successfully!")
+
+    return "Processing complete."
+
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=process_model,
+    inputs=[
+        gr.Textbox(lines=1, label="Model ID"),
+        gr.Textbox(lines=1, label="File path"),
+        gr.Textbox(lines=1, label="Key"),
+        gr.Textbox(lines=1, label="Value"),
+        gr.Textbox(lines=1, label="Token"),
+    ],
+    outputs="text",
+)
+
+# Launch the interface
+iface.launch(debug=True)