Instructions to use efesint/Anchorite-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use efesint/Anchorite-7B 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 efesint/Anchorite-7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf efesint/Anchorite-7B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf efesint/Anchorite-7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf efesint/Anchorite-7B:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf efesint/Anchorite-7B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf efesint/Anchorite-7B:Q4_K_M

Use Docker

docker model run hf.co/efesint/Anchorite-7B:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use efesint/Anchorite-7B with Ollama:
```
ollama run hf.co/efesint/Anchorite-7B:Q4_K_M
```
Unsloth Desktop

How to use efesint/Anchorite-7B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf efesint/Anchorite-7B: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": "efesint/Anchorite-7B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use efesint/Anchorite-7B with Docker Model Runner:
```
docker model run hf.co/efesint/Anchorite-7B:Q4_K_M
```

Lemonade

How to use efesint/Anchorite-7B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull efesint/Anchorite-7B:Q4_K_M

Run and chat with the model

lemonade run user.Anchorite-7B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use efesint/Anchorite-7B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf efesint/Anchorite-7B: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 efesint/Anchorite-7B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use efesint/Anchorite-7B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf efesint/Anchorite-7B: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 "efesint/Anchorite-7B: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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Anchorite-7B (it talks like shi, in dev. now)

A fine-tuned language model based on Qwen/Qwen2.5-7B.
/b/, /ai/, /s/- from 2ch.su.
only in russian language now.

Dataset

Name: dataset_clean_2ch_ai.jsonl
Size: ~ 12 000 posts
Source: 2ch.su (/b/, /ai/, /s/)
Language: Russian
License: CC BY-SA 4.0

NOTICE

Disclaimer

This software is provided "AS IS", without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and non-infringement.

The author is NOT responsible for any damage, data loss, moral harm, psychological distress, offense, or illegal use arising from the use or inability to use this software.

Recommended for adults aged 18 and older.

Content Warning

This model was trained on unfiltered data from imageboards and may generate:

Offensive language
Hate speech
Violent or disturbing content
Sexually explicit material
Misinformation

The author does not endorse, support, or condone any of the views expressed by the model.

Usage

By using this software, you agree that:

You are solely responsible for any content you generate.
You will not use this software for illegal purposes.
You will not hold the author liable for any consequences.

Downloads last month: 44

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Inference Providers NEW

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