Instructions to use constmix/oss-ai-7b-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 constmix/oss-ai-7b-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 constmix/oss-ai-7b-gguf
# Run inference directly in the terminal:
llama cli -hf constmix/oss-ai-7b-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf constmix/oss-ai-7b-gguf
# Run inference directly in the terminal:
llama cli -hf constmix/oss-ai-7b-gguf

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 constmix/oss-ai-7b-gguf
# Run inference directly in the terminal:
./llama-cli -hf constmix/oss-ai-7b-gguf

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 constmix/oss-ai-7b-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf constmix/oss-ai-7b-gguf

Use Docker

docker model run hf.co/constmix/oss-ai-7b-gguf

LM Studio
Jan
Ollama
How to use constmix/oss-ai-7b-gguf with Ollama:
```
ollama run hf.co/constmix/oss-ai-7b-gguf
```
Unsloth Desktop

How to use constmix/oss-ai-7b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf constmix/oss-ai-7b-gguf

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": "constmix/oss-ai-7b-gguf"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use constmix/oss-ai-7b-gguf with Docker Model Runner:
```
docker model run hf.co/constmix/oss-ai-7b-gguf
```

Lemonade

How to use constmix/oss-ai-7b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull constmix/oss-ai-7b-gguf

Run and chat with the model

lemonade run user.oss-ai-7b-gguf-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use constmix/oss-ai-7b-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 constmix/oss-ai-7b-gguf

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 constmix/oss-ai-7b-gguf

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use constmix/oss-ai-7b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf constmix/oss-ai-7b-gguf

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 "constmix/oss-ai-7b-gguf" \
  --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"

OSS AI event extractor (7B)

Fine-tune of Qwen/Qwen2.5-7B-Instruct, quantised to Q4_K_M, that pulls structured event data out of free-form Discord messages for the Vaktovian Systems Department.

What it does

Given a message like:

SURGE @ VAK Eular Station LOSS

it returns:

{"CLAN": "The Imperial Insurgence", "BASE": "Eular Station", "TYPE": "Defense", "RESULT": "Loss"}

Only those four fields. The date, the author and the screenshot come off the Discord message object instead, because those were never a language problem and asking a model for them just adds somewhere for it to be wrong.

Results

On the project's earlier validation set this model scored 92.7% exact match where the 1.5B fine-tune scored 93.6%. Same training data, same recipe, 4.7x the size, no gain, so the 1.5B is the production model and this one is kept for the record. It has not been re-scored on the newer 892-row benchmark.

Training

8,020 examples, 2 epochs, LoRA r=16 alpha=32 on all attention and MLP projections
Loss masked to the answer only, so it is not trained on the prompt or on padding
Dynamic padding rather than a fixed length, the median example is 209 tokens

Usage

from llama_cpp import Llama

llm = Llama(model_path="oss_ai_7b_q4.gguf", n_ctx=512)
out = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": SYSTEM_PROMPT},
        {"role": "user", "content": "SURGE @ VAK Eular Station LOSS"},
    ],
    temperature=0,
)

The system prompt has to match the one it was trained on, which is in utils/constants.py in the bot repo. A different prompt will make it noticeably worse.

Downloads last month: 29

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for constmix/oss-ai-7b-gguf

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(418)

this model