Instructions to use onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use onekq-ai/OneSQL-v0.1-Qwen-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 onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF: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 onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF: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 onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF with Ollama:
```
ollama run hf.co/onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use onekq-ai/OneSQL-v0.1-Qwen-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 onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF: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": "onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M
```

Lemonade

How to use onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.OneSQL-v0.1-Qwen-7B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use onekq-ai/OneSQL-v0.1-Qwen-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 onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF: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 onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use onekq-ai/OneSQL-v0.1-Qwen-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 onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF: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 "onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF: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"

Proposal to rename files

by JLouisBiz - opened Mar 18, 2025

Discussion

JLouisBiz

Mar 18, 2025

I propose to rename files. Imagine, there are 1,500,000 models on HuggingFace, and how many thousands of downloads go on. When file is named by the quantization only, the user who downloads the file loses track on which file was it.

I did not expect this to happen, then I noticed, there is no trace which file could this be, from which model, as the file is named solely: Q6_K.gguf

Also note, not everyone downloads by browser, people may use different download methods which do not say where it comes from.

Your should name your files by the pattern OneSQL-v0.1-Qwen-7B-Q6_K.gguf

onekq

ONEKQ AI org Mar 18, 2025

Done

JLouisBiz

Mar 23, 2025

Thank you so much for making it right! Now it is so much better and distinctive, also helping users to remember your brand OneSQL.

JLouisBiz changed discussion status to closed Mar 23, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment