Instructions to use TheDrummer/Anubis-70B-v1-GGUF-BROKEN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TheDrummer/Anubis-70B-v1-GGUF-BROKEN with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_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 TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_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 TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M

Use Docker

docker model run hf.co/TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M

LM Studio
Jan
Ollama
How to use TheDrummer/Anubis-70B-v1-GGUF-BROKEN with Ollama:
```
ollama run hf.co/TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M
```
Unsloth Desktop

How to use TheDrummer/Anubis-70B-v1-GGUF-BROKEN with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TheDrummer/Anubis-70B-v1-GGUF-BROKEN with Docker Model Runner:
```
docker model run hf.co/TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M
```

Lemonade

How to use TheDrummer/Anubis-70B-v1-GGUF-BROKEN with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M

Run and chat with the model

lemonade run user.Anubis-70B-v1-GGUF-BROKEN-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use TheDrummer/Anubis-70B-v1-GGUF-BROKEN with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_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 TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TheDrummer/Anubis-70B-v1-GGUF-BROKEN with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "TheDrummer/Anubis-70B-v1-GGUF-BROKEN:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Nbv9pQ88Xb

2500+ members strong 💪 Now with more channels! A hub for users and makers alike!

Note: Some quants in this repo are broken. Please use quants from other users like Bartowski.

BeaverAI proudly presents...

Anubis 70B v1 🐩

Special Thanks

Thank you to each and everyone who donated and subscribed in Ko-Fi to make our venture a little bit easier.

Supported Chat Template

Llama 3 Chat (system, user, assistant)

Description

I would say, all in all, Anubis is my preferred L3.3 finetune so far. It managed to pull me away from Behemoth, and that's extremely impressive for a model almost half the size.

It's a very balanced model between the L3.3 tunes. It's very creative, able to come up with new and interesting scenarios on your own that will thoroughly surprise you in ways that remind me of a 123B model. It has some of the most natural sounding dialogue and prose can come out of any model I've tried with the right swipe, in a way that truly brings your characters and RP to life that makes you feel like you're talking to a human writer instead of an AI - a quality that reminds me of Character AI in its prime. This model loves a great prompt and thrives off instructions.

It punches well above its weight and is now my preferred model. The prose, natural flow, adherence, speed and of course creativity is a five star meal, cooked by the Chef himself.

It bats higher than its 70b baseline; more in the 120b range.

It's like I was talking to a real girl!

TheDrummer
/

Anubis-70B-v1-GGUF-BROKEN

Join our Discord! https://discord.gg/Nbv9pQ88Xb

2500+ members strong 💪 Now with more channels! A hub for users and makers alike!

Note: Some quants in this repo are broken. Please use quants from other users like Bartowski.

Anubis 70B v1 🐩

Special Thanks

Supported Chat Template

Description

Links

Favorite RP Format

Favorite Card