Instructions to use common-degradation/comrade-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use common-degradation/comrade-7b with Adapters:

from adapters import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("undefined")
model.load_adapter("common-degradation/comrade-7b", set_active=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use common-degradation/comrade-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 common-degradation/comrade-7b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf common-degradation/comrade-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 common-degradation/comrade-7b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf common-degradation/comrade-7b: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 common-degradation/comrade-7b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf common-degradation/comrade-7b: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 common-degradation/comrade-7b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf common-degradation/comrade-7b:Q4_K_M

Use Docker

docker model run hf.co/common-degradation/comrade-7b:Q4_K_M

LM Studio
Jan
Ollama
How to use common-degradation/comrade-7b with Ollama:
```
ollama run hf.co/common-degradation/comrade-7b:Q4_K_M
```

Unsloth Studio

How to use common-degradation/comrade-7b 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 common-degradation/comrade-7b 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 common-degradation/comrade-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for common-degradation/comrade-7b to start chatting

How to use common-degradation/comrade-7b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf common-degradation/comrade-7b:Q4_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": "common-degradation/comrade-7b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use common-degradation/comrade-7b with Docker Model Runner:
```
docker model run hf.co/common-degradation/comrade-7b:Q4_K_M
```

Lemonade

How to use common-degradation/comrade-7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull common-degradation/comrade-7b:Q4_K_M

Run and chat with the model

lemonade run user.comrade-7b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use common-degradation/comrade-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 common-degradation/comrade-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 common-degradation/comrade-7b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use common-degradation/comrade-7b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf common-degradation/comrade-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 "common-degradation/comrade-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"

Comrade - it's fine-tuned model by Qwen 2.5, first Russian local model.

How to install

Go to page named "Files and versions", then find file named "tovarisch-qwen25-Q4_K_M.gguf" and press the download button.

Go to Ollama.com and install Ollama.

Create folder named "Comrade" on desktop directory to have quick access and open terminal/command line.

Then run this commands: cd desktop/Comrade Ollama create comrade -f Modelfile

Close your terminal/cmd and open Ollama.

How to use

Open Ollama, create new chat and start messaging.

How to update

First, check for updates on our HuggingFace repo.

Then open your terminal/cmd and run: Ollama rm comrade

Download new Modelfile and .gguf model. Repeat steps from "How to install"

App.html

You can use our web interface by downloading app.html from repo. Just open it and go to "Settings" to configure your app.

Our social media

VK Telegram

Downloads last month: 25

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

Model tree for common-degradation/comrade-7b

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Adapter

(2631)

this model