Upload 7 files

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 llama.png filter=lfs diff=lfs merge=lfs -text
 imatrix_calibration.txt filter=lfs diff=lfs merge=lfs -text
+error.png filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -1,64 +1,64 @@
-FROM nvidia/cuda:11.8.0-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 \
-    ffmpeg \
-    nvidia-driver-515
-
-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" "gradio[oauth]>=4.28.0" "gradio_huggingfacehub_search==0.0.7" "APScheduler"
-
-COPY --chown=1000 . ${HOME}/app
-RUN git clone https://github.com/ggerganov/llama.cpp
-RUN pip install -r llama.cpp/requirements.txt
-
-COPY groups_merged.txt ${HOME}/app/llama.cpp/
-
-ENV PYTHONPATH=${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 \
-    LD_LIBRARY_PATH=/usr/local/cuda/lib64:${LD_LIBRARY_PATH} \
-    PATH=/usr/local/nvidia/bin:${PATH}
-
-
-ENTRYPOINT /bin/sh start.sh
-
+FROM nvidia/cuda:11.8.0-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 \
+    ffmpeg \
+    nvidia-driver-515
+
+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" "gradio[oauth]>=4.28.0" "gradio_huggingfacehub_search==0.0.7" "APScheduler"
+
+COPY --chown=1000 . ${HOME}/app
+RUN git clone https://github.com/ggerganov/llama.cpp
+RUN pip install -r llama.cpp/requirements.txt
+
+COPY groups_merged.txt ${HOME}/app/llama.cpp/
+
+ENV PYTHONPATH=${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 \
+    LD_LIBRARY_PATH=/usr/local/cuda/lib64:${LD_LIBRARY_PATH} \
+    PATH=/usr/local/nvidia/bin:${PATH}
+
+
+ENTRYPOINT /bin/sh start.sh
+

README.md

@@ -1,15 +1,15 @@
----
-title: GGUF My Repo
-emoji: 🦙
-colorFrom: gray
-colorTo: pink
-sdk: docker
-hf_oauth: true
-hf_oauth_scopes:
-  - read-repos
-  - write-repos
-  - manage-repos
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: GGUF My Repo
+emoji: 🦙
+colorFrom: gray
+colorTo: pink
+sdk: docker
+hf_oauth: true
+hf_oauth_scopes:
+  - read-repos
+  - write-repos
+  - manage-repos
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,381 +1,459 @@
-import os
-import shutil
-import subprocess
-import signal
-os.environ["GRADIO_ANALYTICS_ENABLED"] = "False"
-import gradio as gr
-
-from huggingface_hub import create_repo, HfApi
-from huggingface_hub import snapshot_download
-from huggingface_hub import whoami
-from huggingface_hub import ModelCard
-
-from gradio_huggingfacehub_search import HuggingfaceHubSearch
-
-from apscheduler.schedulers.background import BackgroundScheduler
-
-from textwrap import dedent
-
-HF_TOKEN = os.environ.get("HF_TOKEN")
-
-def generate_importance_matrix(model_path, train_data_path):
-    imatrix_command = f"./llama-imatrix -m ../{model_path} -f {train_data_path} -ngl 99 --output-frequency 10"
-
-    os.chdir("llama.cpp")
-
-    print(f"Current working directory: {os.getcwd()}")
-    print(f"Files in the current directory: {os.listdir('.')}")
-
-    if not os.path.isfile(f"../{model_path}"):
-        raise Exception(f"Model file not found: {model_path}")
-
-    print("Running imatrix command...")
-    process = subprocess.Popen(imatrix_command, shell=True)
-
-    try:
-        process.wait(timeout=60)  # added wait
-    except subprocess.TimeoutExpired:
-        print("Imatrix computation timed out. Sending SIGINT to allow graceful termination...")
-        process.send_signal(signal.SIGINT)
-        try:
-            process.wait(timeout=5)  # grace period
-        except subprocess.TimeoutExpired:
-            print("Imatrix proc still didn't term. Forecfully terming process...")
-            process.kill()
-
-    os.chdir("..")
-
-    print("Importance matrix generation completed.")
-
-def split_upload_model(model_path, repo_id, oauth_token: gr.OAuthToken | None, split_max_tensors=256, split_max_size=None):
-    if oauth_token.token is None:
-        raise ValueError("You have to be logged in.")
-    
-    split_cmd = f"llama.cpp/llama-gguf-split --split --split-max-tensors {split_max_tensors}"
-    if split_max_size:
-        split_cmd += f" --split-max-size {split_max_size}"
-    split_cmd += f" {model_path} {model_path.split('.')[0]}"
-    
-    print(f"Split command: {split_cmd}") 
-    
-    result = subprocess.run(split_cmd, shell=True, capture_output=True, text=True)
-    print(f"Split command stdout: {result.stdout}") 
-    print(f"Split command stderr: {result.stderr}") 
-    
-    if result.returncode != 0:
-        raise Exception(f"Error splitting the model: {result.stderr}")
-    print("Model split successfully!")
-     
-    
-    sharded_model_files = [f for f in os.listdir('.') if f.startswith(model_path.split('.')[0])]
-    if sharded_model_files:
-        print(f"Sharded model files: {sharded_model_files}")
-        api = HfApi(token=oauth_token.token)
-        for file in sharded_model_files:
-            file_path = os.path.join('.', file)
-            print(f"Uploading file: {file_path}")
-            try:
-                api.upload_file(
-                    path_or_fileobj=file_path,
-                    path_in_repo=file,
-                    repo_id=repo_id,
-                )
-            except Exception as e:
-                raise Exception(f"Error uploading file {file_path}: {e}")
-    else:
-        raise Exception("No sharded files found.")
-    
-    print("Sharded model has been uploaded successfully!")
-
-def process_model(model_id, q_method, use_imatrix, imatrix_q_method, private_repo, train_data_file, split_model, split_max_tensors, split_max_size, oauth_token: gr.OAuthToken | None):
-    if oauth_token.token is None:
-        raise ValueError("You must be logged in to use GGUF-my-repo")
-    model_name = model_id.split('/')[-1]
-    fp16 = f"{model_name}.fp16.gguf"
-
-    try:
-        api = HfApi(token=oauth_token.token)
-
-        dl_pattern = ["*.md", "*.json", "*.model"]
-
-        pattern = (
-            "*.safetensors"
-            if any(
-                file.path.endswith(".safetensors")
-                for file in api.list_repo_tree(
-                    repo_id=model_id,
-                    recursive=True,
-                )
-            )
-            else "*.bin"
-        )
-
-        dl_pattern += pattern
-
-        api.snapshot_download(repo_id=model_id, local_dir=model_name, local_dir_use_symlinks=False, allow_patterns=dl_pattern)
-        print("Model downloaded successfully!")
-        print(f"Current working directory: {os.getcwd()}")
-        print(f"Model directory contents: {os.listdir(model_name)}")
-
-        conversion_script = "convert_hf_to_gguf.py"
-        fp16_conversion = f"python llama.cpp/{conversion_script} {model_name} --outtype f16 --outfile {fp16}"
-        result = subprocess.run(fp16_conversion, shell=True, capture_output=True)
-        print(result)
-        if result.returncode != 0:
-            raise Exception(f"Error converting to fp16: {result.stderr}")
-        print("Model converted to fp16 successfully!")
-        print(f"Converted model path: {fp16}")
-
-        imatrix_path = "llama.cpp/imatrix.dat"
-
-        if use_imatrix:
-            if train_data_file:
-                train_data_path = train_data_file.name
-            else:
-                train_data_path = "groups_merged.txt" #fallback calibration dataset
-
-            print(f"Training data file path: {train_data_path}")
-
-            if not os.path.isfile(train_data_path):
-                raise Exception(f"Training data file not found: {train_data_path}")
-
-            generate_importance_matrix(fp16, train_data_path)
-        else:
-            print("Not using imatrix quantization.")
-        username = whoami(oauth_token.token)["name"]
-        quantized_gguf_name = f"{model_name.lower()}-{imatrix_q_method.lower()}-imat.gguf" if use_imatrix else f"{model_name.lower()}-{q_method.lower()}.gguf"
-        quantized_gguf_path = quantized_gguf_name
-        if use_imatrix:
-            quantise_ggml = f"./llama.cpp/llama-quantize --imatrix {imatrix_path} {fp16} {quantized_gguf_path} {imatrix_q_method}"
-        else:
-            quantise_ggml = f"./llama.cpp/llama-quantize {fp16} {quantized_gguf_path} {q_method}"
-        result = subprocess.run(quantise_ggml, shell=True, capture_output=True)
-        if result.returncode != 0:
-            raise Exception(f"Error quantizing: {result.stderr}")
-        print(f"Quantized successfully with {imatrix_q_method if use_imatrix else q_method} option!")
-        print(f"Quantized model path: {quantized_gguf_path}")
-
-        # Create empty repo
-        new_repo_url = api.create_repo(repo_id=f"{username}/{model_name}-{imatrix_q_method if use_imatrix else q_method}-GGUF", exist_ok=True, private=private_repo)
-        new_repo_id = new_repo_url.repo_id
-        print("Repo created successfully!", new_repo_url)
-
-        try:
-            card = ModelCard.load(model_id, token=oauth_token.token)
-        except:
-            card = ModelCard("")
-        if card.data.tags is None:
-            card.data.tags = []
-        card.data.tags.append("llama-cpp")
-        card.data.tags.append("gguf-my-repo")
-        card.data.base_model = model_id
-        card.text = dedent(
-            f"""
-            # {new_repo_id}
-            This model was converted to GGUF format from [`{model_id}`](https://huggingface.co/{model_id}) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
-            Refer to the [original model card](https://huggingface.co/{model_id}) for more details on the model.
-            
-            ## Use with llama.cpp
-            Install llama.cpp through brew (works on Mac and Linux)
-            
-            ```bash
-            brew install llama.cpp
-            
-            ```
-            Invoke the llama.cpp server or the CLI.
-            
-            ### CLI:
-            ```bash
-            llama-cli --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -p "The meaning to life and the universe is"
-            ```
-            
-            ### Server:
-            ```bash
-            llama-server --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -c 2048
-            ```
-            
-            Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
-
-            Step 1: Clone llama.cpp from GitHub.
-            ```
-            git clone https://github.com/ggerganov/llama.cpp
-            ```
-
-            Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
-            ```
-            cd llama.cpp && LLAMA_CURL=1 make
-            ```
-
-            Step 3: Run inference through the main binary.
-            ```
-            ./llama-cli --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -p "The meaning to life and the universe is"
-            ```
-            or 
-            ```
-            ./llama-server --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -c 2048
-            ```
-            """
-        )
-        card.save(f"README.md")
-
-        if split_model:
-            split_upload_model(quantized_gguf_path, new_repo_id, oauth_token, split_max_tensors, split_max_size)
-        else:
-            try:
-                print(f"Uploading quantized model: {quantized_gguf_path}")
-                api.upload_file(
-                    path_or_fileobj=quantized_gguf_path,
-                    path_in_repo=quantized_gguf_name,
-                    repo_id=new_repo_id,
-                )
-            except Exception as e:
-                raise Exception(f"Error uploading quantized model: {e}")
-        
-        
-        imatrix_path = "llama.cpp/imatrix.dat"
-        if os.path.isfile(imatrix_path):
-            try:
-                print(f"Uploading imatrix.dat: {imatrix_path}")
-                api.upload_file(
-                    path_or_fileobj=imatrix_path,
-                    path_in_repo="imatrix.dat",
-                    repo_id=new_repo_id,
-                )
-            except Exception as e:
-                raise Exception(f"Error uploading imatrix.dat: {e}")
-
-        api.upload_file(
-            path_or_fileobj=f"README.md",
-            path_in_repo=f"README.md",
-            repo_id=new_repo_id,
-        )
-        print(f"Uploaded successfully with {imatrix_q_method if use_imatrix else q_method} option!")
-
-        return (
-            f'Find your repo <a href=\'{new_repo_url}\' target="_blank" style="text-decoration:underline">here</a>',
-            "llama.png",
-        )
-    except Exception as e:
-        return (f"Error: {e}", "error.png")
-    finally:
-        shutil.rmtree(model_name, ignore_errors=True)
-        print("Folder cleaned up successfully!")
-
-css="""/* Custom CSS to allow scrolling */
-.gradio-container {overflow-y: auto;}
-"""
-# Create Gradio interface
-with gr.Blocks(css=css) as demo: 
-    gr.Markdown("You must be logged in to use GGUF-my-repo.")
-    gr.LoginButton(min_width=250)
-
-    model_id = HuggingfaceHubSearch(
-        label="Hub Model ID",
-        placeholder="Search for model id on Huggingface",
-        search_type="model",
-    )
-
-    q_method = gr.Dropdown(
-        ["Q2_K", "Q3_K_S", "Q3_K_M", "Q3_K_L", "Q4_0", "Q4_K_S", "Q4_K_M", "Q5_0", "Q5_K_S", "Q5_K_M", "Q6_K", "Q8_0"],
-        label="Quantization Method",
-        info="GGML quantization type",
-        value="Q4_K_M",
-        filterable=False,
-        visible=True
-    )
-
-    imatrix_q_method = gr.Dropdown(
-        ["IQ3_M", "IQ3_XXS", "Q4_K_M", "Q4_K_S", "IQ4_NL", "IQ4_XS", "Q5_K_M", "Q5_K_S"],
-        label="Imatrix Quantization Method",
-        info="GGML imatrix quants type",
-        value="IQ4_NL", 
-        filterable=False,
-        visible=False
-    )
-
-    use_imatrix = gr.Checkbox(
-        value=False,
-        label="Use Imatrix Quantization",
-        info="Use importance matrix for quantization."
-    )
-
-    private_repo = gr.Checkbox(
-        value=False,
-        label="Private Repo",
-        info="Create a private repo under your username."
-    )
-
-    train_data_file = gr.File(
-        label="Training Data File",
-        file_types=["txt"],
-        visible=False
-    )
-
-    split_model = gr.Checkbox(
-        value=False,
-        label="Split Model",
-        info="Shard the model using gguf-split."
-    )
-
-    split_max_tensors = gr.Number(
-        value=256,
-        label="Max Tensors per File",
-        info="Maximum number of tensors per file when splitting model.",
-        visible=False
-    )
-
-    split_max_size = gr.Textbox(
-        label="Max File Size",
-        info="Maximum file size when splitting model (--split-max-size). May leave empty to use the default.",
-        visible=False
-    )
-
-    def update_visibility(use_imatrix):
-        return gr.update(visible=not use_imatrix), gr.update(visible=use_imatrix), gr.update(visible=use_imatrix)
-    
-    use_imatrix.change(
-        fn=update_visibility,
-        inputs=use_imatrix,
-        outputs=[q_method, imatrix_q_method, train_data_file]
-    )
-
-    iface = gr.Interface(
-        fn=process_model,
-        inputs=[
-            model_id,
-            q_method,
-            use_imatrix,
-            imatrix_q_method,
-            private_repo,
-            train_data_file,
-            split_model,
-            split_max_tensors,
-            split_max_size,
-        ],
-        outputs=[
-            gr.Markdown(label="output"),
-            gr.Image(show_label=False),
-        ],
-        title="Create your own GGUF Quants, blazingly fast ⚡!",
-        description="The space takes an HF repo as an input, quantizes it and creates a Public repo containing the selected quant under your HF user namespace.",
-        api_name=False
-    )
-
-    def update_split_visibility(split_model):
-        return gr.update(visible=split_model), gr.update(visible=split_model)
-
-    split_model.change(
-        fn=update_split_visibility,
-        inputs=split_model,
-        outputs=[split_max_tensors, split_max_size]
-    )
-
-def restart_space():
-    HfApi().restart_space(repo_id="ggml-org/gguf-my-repo", token=HF_TOKEN, factory_reboot=True)
-
-scheduler = BackgroundScheduler()
-scheduler.add_job(restart_space, "interval", seconds=21600)
-scheduler.start()
-
-# Launch the interface
+import os
+import shutil
+import subprocess
+import signal
+os.environ["GRADIO_ANALYTICS_ENABLED"] = "False"
+import gradio as gr
+
+from huggingface_hub import create_repo, HfApi
+from huggingface_hub import snapshot_download
+from huggingface_hub import whoami
+from huggingface_hub import ModelCard
+
+from gradio_huggingfacehub_search import HuggingfaceHubSearch
+
+from apscheduler.schedulers.background import BackgroundScheduler
+
+from textwrap import dedent
+
+HF_TOKEN = os.environ.get("HF_TOKEN")
+
+def generate_importance_matrix(model_path, train_data_path):
+    imatrix_command = f"./llama-imatrix -m ../{model_path} -f {train_data_path} -ngl 99 --output-frequency 10"
+
+    os.chdir("llama.cpp")
+
+    print(f"Current working directory: {os.getcwd()}")
+    print(f"Files in the current directory: {os.listdir('.')}")
+
+    if not os.path.isfile(f"../{model_path}"):
+        raise Exception(f"Model file not found: {model_path}")
+
+    print("Running imatrix command...")
+    process = subprocess.Popen(imatrix_command, shell=True)
+
+    try:
+        process.wait(timeout=60)  # added wait
+    except subprocess.TimeoutExpired:
+        print("Imatrix computation timed out. Sending SIGINT to allow graceful termination...")
+        process.send_signal(signal.SIGINT)
+        try:
+            process.wait(timeout=5)  # grace period
+        except subprocess.TimeoutExpired:
+            print("Imatrix proc still didn't term. Forecfully terming process...")
+            process.kill()
+
+    os.chdir("..")
+
+    print("Importance matrix generation completed.")
+
+def split_upload_model(model_path, repo_id, oauth_token: gr.OAuthToken | None, split_max_tensors=256, split_max_size=None):
+    if oauth_token.token is None:
+        raise ValueError("You have to be logged in.")
+    
+    split_cmd = f"llama.cpp/llama-gguf-split --split --split-max-tensors {split_max_tensors}"
+    if split_max_size:
+        split_cmd += f" --split-max-size {split_max_size}"
+    split_cmd += f" {model_path} {model_path.split('.')[0]}"
+    
+    print(f"Split command: {split_cmd}") 
+    
+    result = subprocess.run(split_cmd, shell=True, capture_output=True, text=True)
+    print(f"Split command stdout: {result.stdout}") 
+    print(f"Split command stderr: {result.stderr}") 
+    
+    if result.returncode != 0:
+        raise Exception(f"Error splitting the model: {result.stderr}")
+    print("Model split successfully!")
+     
+    
+    sharded_model_files = [f for f in os.listdir('.') if f.startswith(model_path.split('.')[0])]
+    if sharded_model_files:
+        print(f"Sharded model files: {sharded_model_files}")
+        api = HfApi(token=oauth_token.token)
+        for file in sharded_model_files:
+            file_path = os.path.join('.', file)
+            print(f"Uploading file: {file_path}")
+            try:
+                api.upload_file(
+                    path_or_fileobj=file_path,
+                    path_in_repo=file,
+                    repo_id=repo_id,
+                )
+            except Exception as e:
+                raise Exception(f"Error uploading file {file_path}: {e}")
+    else:
+        raise Exception("No sharded files found.")
+    
+    print("Sharded model has been uploaded successfully!")
+
+def process_model(model_id, q_method, use_imatrix, imatrix_q_method, private_repo, train_data_file, split_model, split_max_tensors, split_max_size, oauth_token: gr.OAuthToken | None):
+    if oauth_token.token is None:
+        raise ValueError("You must be logged in to use GGUF-my-repo")
+    model_name = model_id.split('/')[-1]
+    fp16 = f"{model_name}.fp16.gguf"
+
+    try:
+        api = HfApi(token=oauth_token.token)
+
+        dl_pattern = ["*.md", "*.json", "*.model"]
+
+        pattern = (
+            "*.safetensors"
+            if any(
+                file.path.endswith(".safetensors")
+                for file in api.list_repo_tree(
+                    repo_id=model_id,
+                    recursive=True,
+                )
+            )
+            else "*.bin"
+        )
+
+        dl_pattern += pattern
+
+        api.snapshot_download(repo_id=model_id, local_dir=model_name, local_dir_use_symlinks=False, allow_patterns=dl_pattern)
+        print("Model downloaded successfully!")
+        print(f"Current working directory: {os.getcwd()}")
+        print(f"Model directory contents: {os.listdir(model_name)}")
+
+        conversion_script = "convert_hf_to_gguf.py"
+        fp16_conversion = f"python llama.cpp/{conversion_script} {model_name} --outtype f16 --outfile {fp16}"
+        result = subprocess.run(fp16_conversion, shell=True, capture_output=True)
+        print(result)
+        if result.returncode != 0:
+            raise Exception(f"Error converting to fp16: {result.stderr}")
+        print("Model converted to fp16 successfully!")
+        print(f"Converted model path: {fp16}")
+
+        imatrix_path = "llama.cpp/imatrix.dat"
+
+        if use_imatrix:
+            if train_data_file:
+                train_data_path = train_data_file.name
+            else:
+                train_data_path = "groups_merged.txt" #fallback calibration dataset
+
+            print(f"Training data file path: {train_data_path}")
+
+            if not os.path.isfile(train_data_path):
+                raise Exception(f"Training data file not found: {train_data_path}")
+
+            generate_importance_matrix(fp16, train_data_path)
+        else:
+            print("Not using imatrix quantization.")
+        username = whoami(oauth_token.token)["name"]
+        quantized_gguf_name = f"{model_name.lower()}-{imatrix_q_method.lower()}-imat.gguf" if use_imatrix else f"{model_name.lower()}-{q_method.lower()}.gguf"
+        quantized_gguf_path = quantized_gguf_name
+        if use_imatrix:
+            quantise_ggml = f"./llama.cpp/llama-quantize --imatrix {imatrix_path} {fp16} {quantized_gguf_path} {imatrix_q_method}"
+        else:
+            quantise_ggml = f"./llama.cpp/llama-quantize {fp16} {quantized_gguf_path} {q_method}"
+        result = subprocess.run(quantise_ggml, shell=True, capture_output=True)
+        if result.returncode != 0:
+            raise Exception(f"Error quantizing: {result.stderr}")
+        print(f"Quantized successfully with {imatrix_q_method if use_imatrix else q_method} option!")
+        print(f"Quantized model path: {quantized_gguf_path}")
+
+        # Create empty repo
+        new_repo_url = api.create_repo(repo_id=f"{username}/{model_name}-{imatrix_q_method if use_imatrix else q_method}-GGUF", exist_ok=True, private=private_repo)
+        new_repo_id = new_repo_url.repo_id
+        print("Repo created successfully!", new_repo_url)
+
+        try:
+            card = ModelCard.load(model_id, token=oauth_token.token)
+        except:
+            card = ModelCard("")
+        if card.data.tags is None:
+            card.data.tags = []
+        card.data.tags.append("llama-cpp")
+        card.data.tags.append("gguf-my-repo")
+        card.data.base_model = model_id
+        card.text = dedent(
+            f"""
+            # {new_repo_id}
+            Asalamu Alaikum! This model was converted to GGUF format from [`{model_id}`](https://huggingface.co/{model_id}) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
+            Refer to the [original model card](https://huggingface.co/{model_id}) for more details on the model.
+
+            ## Description (per [TheBloke](https://huggingface.co/TheBloke))
+
+            This repo contains GGUF format model files.
+
+            These files were quantised using ggml-org/gguf-my-repo [https://huggingface.co/spaces/ggml-org/gguf-my-repo]
+
+            <!-- description end -->
+            <!-- README_GGUF.md-about-gguf start -->
+            ### About GGUF (per [TheBloke](https://huggingface.co/TheBloke))
+
+            GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
+
+            Here is an incomplete list of clients and libraries that are known to support GGUF:
+
+            * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
+            * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
+            * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
+            * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
+            * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
+            * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
+            * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
+            * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
+            * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
+            * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
+
+            <!-- README_GGUF.md-about-gguf end -->
+
+            <!-- compatibility_gguf start -->
+            ## Compatibility
+
+            These quantised GGUFv2 files are compatible with llama.cpp from August 27th 2023 onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
+
+            They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
+
+            ## Explanation of quantisation methods
+
+            <details>
+              <summary>Click to see details</summary>
+
+            The new methods available are:
+
+            * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
+            * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
+            * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
+            * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
+            * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
+
+            Refer to the Provided Files table below to see what files use which methods, and how.
+            </details>
+            <!-- compatibility_gguf end -->
+
+            <!-- README_GGUF.md-provided-files start -->
+            ## Provided Files (Not Including iMatrix Quantization)
+
+            | Quant method | Bits | Example Size | Max RAM required | Use case |
+            | ---- | ---- | ---- | ---- | ----- |
+            | Q2_K | 2 | 2.72 GB| 5.22 GB | significant quality loss - not recommended for most purposes |
+            | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
+            | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
+            | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
+            | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+            | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
+            | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
+            | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+            | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
+            | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
+            | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
+            | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
+
+            **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
+
+
+
+            <!-- README_GGUF.md-provided-files end -->
+            
+            <!-- repositories-available start -->
+            ---
+            
+            ## Use with llama.cpp
+            Install llama.cpp through brew (works on Mac and Linux)
+            
+            ```bash
+            brew install llama.cpp
+            
+            ```
+            Invoke the llama.cpp server or the CLI.
+            
+            ### CLI:
+            ```bash
+            llama-cli --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -p "The meaning to life and the universe is"
+            ```
+            
+            ### Server:
+            ```bash
+            llama-server --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -c 2048
+            ```
+            
+            Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+
+            Step 1: Clone llama.cpp from GitHub.
+            ```
+            git clone https://github.com/ggerganov/llama.cpp
+            ```
+
+            Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
+            ```
+            cd llama.cpp && LLAMA_CURL=1 make
+            ```
+
+            Step 3: Run inference through the main binary.
+            ```
+            ./llama-cli --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -p "The meaning to life and the universe is"
+            ```
+            or 
+            ```
+            ./llama-server --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -c 2048
+            ```
+            """
+        )
+        card.save(f"README.md")
+
+        if split_model:
+            split_upload_model(quantized_gguf_path, new_repo_id, oauth_token, split_max_tensors, split_max_size)
+        else:
+            try:
+                print(f"Uploading quantized model: {quantized_gguf_path}")
+                api.upload_file(
+                    path_or_fileobj=quantized_gguf_path,
+                    path_in_repo=quantized_gguf_name,
+                    repo_id=new_repo_id,
+                )
+            except Exception as e:
+                raise Exception(f"Error uploading quantized model: {e}")
+        
+        
+        imatrix_path = "llama.cpp/imatrix.dat"
+        if os.path.isfile(imatrix_path):
+            try:
+                print(f"Uploading imatrix.dat: {imatrix_path}")
+                api.upload_file(
+                    path_or_fileobj=imatrix_path,
+                    path_in_repo="imatrix.dat",
+                    repo_id=new_repo_id,
+                )
+            except Exception as e:
+                raise Exception(f"Error uploading imatrix.dat: {e}")
+
+        api.upload_file(
+            path_or_fileobj=f"README.md",
+            path_in_repo=f"README.md",
+            repo_id=new_repo_id,
+        )
+        print(f"Uploaded successfully with {imatrix_q_method if use_imatrix else q_method} option!")
+
+        return (
+            f'Find your repo <a href=\'{new_repo_url}\' target="_blank" style="text-decoration:underline">here</a>',
+            "llama.png",
+        )
+    except Exception as e:
+        return (f"Error: {e}", "error.png")
+    finally:
+        shutil.rmtree(model_name, ignore_errors=True)
+        print("Folder cleaned up successfully!")
+
+css="""/* Custom CSS to allow scrolling */
+.gradio-container {overflow-y: auto;}
+"""
+# Create Gradio interface
+with gr.Blocks(css=css) as demo: 
+    gr.Markdown("You must be logged in to use GGUF-my-repo.")
+    gr.LoginButton(min_width=250)
+
+    model_id = HuggingfaceHubSearch(
+        label="Hub Model ID",
+        placeholder="Search for model id on Huggingface",
+        search_type="model",
+    )
+
+    q_method = gr.Dropdown(
+        ["Q2_K", "Q3_K_S", "Q3_K_M", "Q3_K_L", "Q4_0", "Q4_K_S", "Q4_K_M", "Q5_0", "Q5_K_S", "Q5_K_M", "Q6_K", "Q8_0"],
+        label="Quantization Method",
+        info="GGML quantization type",
+        value="Q8_0",
+        filterable=False,
+        visible=True
+    )
+
+    imatrix_q_method = gr.Dropdown(
+        ["IQ3_M", "IQ3_XXS", "Q4_K_M", "Q4_K_S", "IQ4_NL", "IQ4_XS", "Q5_K_M", "Q5_K_S"],
+        label="Imatrix Quantization Method",
+        info="GGML imatrix quants type",
+        value="IQ4_NL", 
+        filterable=False,
+        visible=False
+    )
+
+    use_imatrix = gr.Checkbox(
+        value=False,
+        label="Use Imatrix Quantization",
+        info="Use importance matrix for quantization."
+    )
+
+    private_repo = gr.Checkbox(
+        value=True,
+        label="Private Repo",
+        info="Create a private repo under your username."
+    )
+
+    train_data_file = gr.File(
+        label="Training Data File",
+        file_types=["txt"],
+        visible=False
+    )
+
+    split_model = gr.Checkbox(
+        value=False,
+        label="Split Model",
+        info="Shard the model using gguf-split."
+    )
+
+    split_max_tensors = gr.Number(
+        value=256,
+        label="Max Tensors per File",
+        info="Maximum number of tensors per file when splitting model.",
+        visible=False
+    )
+
+    split_max_size = gr.Textbox(
+        label="Max File Size",
+        info="Maximum file size when splitting model (--split-max-size). May leave empty to use the default.",
+        visible=False
+    )
+
+    def update_visibility(use_imatrix):
+        return gr.update(visible=not use_imatrix), gr.update(visible=use_imatrix), gr.update(visible=use_imatrix)
+    
+    use_imatrix.change(
+        fn=update_visibility,
+        inputs=use_imatrix,
+        outputs=[q_method, imatrix_q_method, train_data_file]
+    )
+
+    iface = gr.Interface(
+        fn=process_model,
+        inputs=[
+            model_id,
+            q_method,
+            use_imatrix,
+            imatrix_q_method,
+            private_repo,
+            train_data_file,
+            split_model,
+            split_max_tensors,
+            split_max_size,
+        ],
+        outputs=[
+            gr.Markdown(label="output"),
+            gr.Image(show_label=False),
+        ],
+        title="Asalamu Alaikum! Create your own GGUF Quantizations, B̶L̶A̶Z̶I̶N̶G̶L̶Y̶ ̶F̶A̶S̶T̶ ⚡! (Hey it's free!)",
+        description="The space takes a HuggingFace repo as an input, quantizes it and creates a private repo containing the selected quant under your HF user namespace.",
+        api_name=False
+    )
+
+    def update_split_visibility(split_model):
+        return gr.update(visible=split_model), gr.update(visible=split_model)
+
+    split_model.change(
+        fn=update_split_visibility,
+        inputs=split_model,
+        outputs=[split_max_tensors, split_max_size]
+    )
+
+def restart_space():
+    HfApi().restart_space(repo_id="ggml-org/gguf-my-repo", token=HF_TOKEN, factory_reboot=True)
+
+scheduler = BackgroundScheduler()
+scheduler.add_job(restart_space, "interval", seconds=21600)
+scheduler.start()
+
+# Launch the interface
 demo.queue(default_concurrency_limit=1, max_size=5).launch(debug=True, show_api=False)

start.sh

@@ -1,5 +1,5 @@
-cd llama.cpp
-LLAMA_CUDA=1 make -j llama-quantize llama-gguf-split llama-imatrix
-
-cd ..
+cd llama.cpp
+LLAMA_CUDA=1 make -j llama-quantize llama-gguf-split llama-imatrix
+
+cd ..
 python app.py