Instructions to use Avicennasis/incorrecter-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Avicennasis/incorrecter-GGUF 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 Avicennasis/incorrecter-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Avicennasis/incorrecter-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Avicennasis/incorrecter-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Avicennasis/incorrecter-GGUF:Q8_0

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 Avicennasis/incorrecter-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Avicennasis/incorrecter-GGUF:Q8_0

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 Avicennasis/incorrecter-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Avicennasis/incorrecter-GGUF:Q8_0

Use Docker

docker model run hf.co/Avicennasis/incorrecter-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use Avicennasis/incorrecter-GGUF with Ollama:
```
ollama run hf.co/Avicennasis/incorrecter-GGUF:Q8_0
```
Unsloth Desktop

How to use Avicennasis/incorrecter-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Avicennasis/incorrecter-GGUF:Q8_0

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": "Avicennasis/incorrecter-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Avicennasis/incorrecter-GGUF with Docker Model Runner:
```
docker model run hf.co/Avicennasis/incorrecter-GGUF:Q8_0
```

Lemonade

How to use Avicennasis/incorrecter-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Avicennasis/incorrecter-GGUF:Q8_0

Run and chat with the model

lemonade run user.incorrecter-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Avicennasis/incorrecter-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Avicennasis/incorrecter-GGUF:Q8_0

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 Avicennasis/incorrecter-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Avicennasis/incorrecter-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Avicennasis/incorrecter-GGUF:Q8_0

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 "Avicennasis/incorrecter-GGUF:Q8_0" \
  --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"

Incorrecter GGUF (Q8_0)

Quantized build of Avicennasis/incorrecter for ollama. This is the quant that passed the evaluation gate; Q4_K_M was rejected (1–3-word edits 0.60 < 0.70 on the 40-text check).

ollama run hf.co/Avicennasis/incorrecter-GGUF:Q8_0

The repo's params file sets the recommended sampling, so the command above needs no extra flags. To build it yourself with a Modelfile:

FROM ./incorrecter-Q8_0.gguf
PARAMETER temperature 1.0
PARAMETER top_p 0.9
PARAMETER top_k 40
PARAMETER repeat_penalty 1.0

Keep repeat_penalty at 1.0. The model's job is to copy your text with a few mistakes, and a repeat penalty punishes the copying. With ollama's default (1.1) at temperature 0.9, only 0.62 of changed texts stayed within 1–3 word edits. The top_p cap keeps the copy exact while leaving room for the intended typos.

Measured through ollama (40 held-out texts, 3 draws, settings above): 0.93 of texts changed, 0.85 of those with 1–3 word edits, 0.98 line count kept, 0.97 sign-off kept, and 0.94 judged to keep their meaning (Llama-3.3-70B judge). Feed it clean text as the user message. See the main model card for training data, evaluation and limitations.

Downloads last month: 92

GGUF

Model size

0.6B params

Architecture

qwen2

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Avicennasis/incorrecter-GGUF

Base model

Avicennasis/incorrecter

Quantized

(1)

this model