Instructions to use Luishae0705/wikiQwen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Luishae0705/wikiQwen 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 Luishae0705/wikiQwen:Q8_0
# Run inference directly in the terminal:
llama cli -hf Luishae0705/wikiQwen:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Luishae0705/wikiQwen:Q8_0
# Run inference directly in the terminal:
llama cli -hf Luishae0705/wikiQwen: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 Luishae0705/wikiQwen:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Luishae0705/wikiQwen: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 Luishae0705/wikiQwen:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Luishae0705/wikiQwen:Q8_0

Use Docker

docker model run hf.co/Luishae0705/wikiQwen:Q8_0

LM Studio
Jan
Ollama
How to use Luishae0705/wikiQwen with Ollama:
```
ollama run hf.co/Luishae0705/wikiQwen:Q8_0
```
Unsloth Desktop

How to use Luishae0705/wikiQwen with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Luishae0705/wikiQwen: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": "Luishae0705/wikiQwen:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Luishae0705/wikiQwen with Docker Model Runner:
```
docker model run hf.co/Luishae0705/wikiQwen:Q8_0
```

Lemonade

How to use Luishae0705/wikiQwen with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Luishae0705/wikiQwen:Q8_0

Run and chat with the model

lemonade run user.wikiQwen-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Luishae0705/wikiQwen with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Luishae0705/wikiQwen: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 Luishae0705/wikiQwen:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Luishae0705/wikiQwen with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Luishae0705/wikiQwen: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 "Luishae0705/wikiQwen: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"

wiki-qwen

A fine-tune of Qwen2.5-0.5B-Instruct trained on question/answer pairs generated from Wikipedia data.

What this is

A small experiment in teaching a 0.5B chat model facts from a narrow set of Wikipedia articles, by training it on question/answer pairs made from that text (e.g. "What is Xcode?", "When was X released?").

Limitations (read before using)

This model is not reliable. It is a 0.5B model fine-tuned briefly on a small dataset, and it:

Still makes up facts (hallucinates) on topics inside and outside the training data.
Gets details wrong even on articles it was trained on.
Should not be used for anything where accuracy matters.

A retrieval-based approach (giving a model the real article text at answer time, instead of training facts into its weights) worked much better in testing than this fine-tune did. This model is shared as-is, mainly as a record of the experiment, not as something to rely on.

Training

Base model: Qwen2.5-0.5B-Instruct
Data: Wikipedia
Full fine-tune (not LoRA)

Licence

Trained on Wikipedia text, licensed under CC BY-SA 4.0 — this model is released under the same licence. Credit Wikipedia and its contributors.

Downloads last month: 20

GGUF

Model size

0.5B 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 Luishae0705/wikiQwen

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

(314)

this model

Luishae0705
/

wikiQwen

wiki-qwen

What this is

Limitations (read before using)

Training

Licence

Model tree for Luishae0705/wikiQwen

Dataset used to train Luishae0705/wikiQwen