Instructions to use darkai-1/darkit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use darkai-1/darkit with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="darkai-1/darkit",
	filename="Q5_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use darkai-1/darkit with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf darkai-1/darkit:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf darkai-1/darkit:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf darkai-1/darkit:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf darkai-1/darkit:Q5_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf darkai-1/darkit:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf darkai-1/darkit:Q5_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf darkai-1/darkit:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf darkai-1/darkit:Q5_K_M

Use Docker

docker model run hf.co/darkai-1/darkit:Q5_K_M

LM Studio
Jan
Ollama
How to use darkai-1/darkit with Ollama:
```
ollama run hf.co/darkai-1/darkit:Q5_K_M
```

Unsloth Studio new

How to use darkai-1/darkit with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for darkai-1/darkit to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for darkai-1/darkit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for darkai-1/darkit to start chatting

Pi new

How to use darkai-1/darkit with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf darkai-1/darkit:Q5_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "darkai-1/darkit:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use darkai-1/darkit with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf darkai-1/darkit:Q5_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default darkai-1/darkit:Q5_K_M

Run Hermes

hermes

Docker Model Runner
How to use darkai-1/darkit with Docker Model Runner:
```
docker model run hf.co/darkai-1/darkit:Q5_K_M
```

Lemonade

How to use darkai-1/darkit with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull darkai-1/darkit:Q5_K_M

Run and chat with the model

lemonade run user.darkit-Q5_K_M

List all available models

lemonade list

Upload notebook.ipynb

by darkai-1 - opened about 17 hours ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+46

-16

Files changed (1) hide show

notebook.ipynb +46 -16

notebook.ipynb CHANGED Viewed

@@ -6,7 +6,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "!pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124\n"
       ]
     },
     {
@@ -19,12 +19,36 @@
         "\n",
         "Long-range conversations can reach up to 128,000 tokens.\n",
         "\n",
-        "It has been trained so that it will never refuse a request and will never say things like: I can't help...\n",
-        "\n",
         "Company website: https://sii3.top\n",
         "Official owner: https://t.me/sii_3\n"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -38,7 +62,7 @@
         "\n",
         "llm = Llama.from_pretrained(\n",
         "    repo_id=\"darkai-1/darkit-1.5-pro\",\n",
-        "    filename=\"darkit-1.5-pro.gguf\",\n",
         "    n_ctx=8192,\n",
         "    n_threads=2,\n",
         "    n_gpu_layers=1,\n",
@@ -52,20 +76,26 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "messages = [{\"role\": \"user\", \"content\": \"Who are you?\"}]\n",
         "\n",
-        "stream = llm.create_chat_completion(\n",
-        "    messages=messages,\n",
-        "    temperature=0.7,\n",
-        "    top_p=0.8,\n",
-        "    top_k=20,\n",
-        "    stream=True\n",
-        ")\n",
         "\n",
-        "for chunk in stream:\n",
-        "    delta = chunk[\"choices\"][0][\"delta\"]\n",
-        "    if \"content\" in delta:\n",
-        "        print(delta[\"content\"], end=\"\", flush=True)\n"
       ]
     }
   ],

       "metadata": {},
       "outputs": [],
       "source": [
+        "!pip install llama-cpp-python huggingface_hub --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124\n"
       ]
     },
     {
         "\n",
         "Long-range conversations can reach up to 128,000 tokens.\n",
         "\n",
         "Company website: https://sii3.top\n",
         "Official owner: https://t.me/sii_3\n"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from huggingface_hub import HfApi\n",
+        "\n",
+        "REPO_ID = \"darkai-1/darkit-1.5-pro\"\n",
+        "\n",
+        "api = HfApi()\n",
+        "\n",
+        "# get gguf files\n",
+        "files = api.list_repo_files(REPO_ID)\n",
+        "gguf_files = [f for f in files if f.endswith(\".gguf\")]\n",
+        "\n",
+        "print(\"Available models:\\n\")\n",
+        "for i, f in enumerate(gguf_files):\n",
+        "    print(f\"[{i}] {f}\")\n",
+        "\n",
+        "choice = int(input(\"\\nEnter model number: \"))\n",
+        "filename = gguf_files[choice]\n",
+        "\n",
+        "print(\"Loading:\", filename)\n"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
         "\n",
         "llm = Llama.from_pretrained(\n",
         "    repo_id=\"darkai-1/darkit-1.5-pro\",\n",
+        "    filename=filename,\n",
         "    n_ctx=8192,\n",
         "    n_threads=2,\n",
         "    n_gpu_layers=1,\n",
       "metadata": {},
       "outputs": [],
       "source": [
+        "while True:\n",
+        "    user_input = input(\"You: \")\n",
+        "    if user_input.lower() in [\"exit\", \"quit\"]:\n",
+        "        break\n",
+        "\n",
+        "    messages = [{\"role\": \"user\", \"content\": user_input}]\n",
         "\n",
+        "    stream = llm.create_chat_completion(\n",
+        "        messages=messages,\n",
+        "        temperature=0.7,\n",
+        "        top_p=0.8,\n",
+        "        top_k=20,\n",
+        "        stream=True\n",
+        "    )\n",
         "\n",
+        "    for chunk in stream:\n",
+        "        delta = chunk[\"choices\"][0][\"delta\"]\n",
+        "        if \"content\" in delta:\n",
+        "            print(delta[\"content\"], end=\"\", flush=True)\n",
+        "    print(\"\\n\")\n"
       ]
     }
   ],