Instructions to use salih1hf/KobunFormer5-1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use salih1hf/KobunFormer5-1-8B 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 salih1hf/KobunFormer5-1-8B:Q8_0 # Run inference directly in the terminal: llama cli -hf salih1hf/KobunFormer5-1-8B:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf salih1hf/KobunFormer5-1-8B:Q8_0 # Run inference directly in the terminal: llama cli -hf salih1hf/KobunFormer5-1-8B: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 salih1hf/KobunFormer5-1-8B:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf salih1hf/KobunFormer5-1-8B: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 salih1hf/KobunFormer5-1-8B:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf salih1hf/KobunFormer5-1-8B:Q8_0
Use Docker
docker model run hf.co/salih1hf/KobunFormer5-1-8B:Q8_0
- LM Studio
- Jan
- Ollama
How to use salih1hf/KobunFormer5-1-8B with Ollama:
ollama run hf.co/salih1hf/KobunFormer5-1-8B:Q8_0
- Unsloth Studio
How to use salih1hf/KobunFormer5-1-8B 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 salih1hf/KobunFormer5-1-8B 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 salih1hf/KobunFormer5-1-8B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for salih1hf/KobunFormer5-1-8B to start chatting
- Pi
How to use salih1hf/KobunFormer5-1-8B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf salih1hf/KobunFormer5-1-8B:Q8_0
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": "salih1hf/KobunFormer5-1-8B:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- OpenClaw new
How to use salih1hf/KobunFormer5-1-8B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf salih1hf/KobunFormer5-1-8B: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 "salih1hf/KobunFormer5-1-8B: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"
- Docker Model Runner
How to use salih1hf/KobunFormer5-1-8B with Docker Model Runner:
docker model run hf.co/salih1hf/KobunFormer5-1-8B:Q8_0
- Lemonade
How to use salih1hf/KobunFormer5-1-8B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull salih1hf/KobunFormer5-1-8B:Q8_0
Run and chat with the model
lemonade run user.KobunFormer5-1-8B-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use salih1hf/KobunFormer5-1-8B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf salih1hf/KobunFormer5-1-8B: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 salih1hf/KobunFormer5-1-8B:Q8_0
Run Hermes
hermes
- Atomic Chat
KobunFormer5-1-8B - GGUF
This model is a specialized fine-tune of the Qwen3 8B parameter model, converted to GGUF format using Unsloth. It is expertly trained to translate modern text (across various languages) into Classical Japanese (Kanbun-Kundoku style).
Model Architecture & Reasoning
KobunFormer5-1-8B employs a unique two-step reasoning approach to ensure high grammatical accuracy and appropriate historical nuances across multiple languages (Tested with Turkish at the moment). It utilizes a thought block to map the linguistic structure before generating the final text:
- Pure Kanbun Generation: The model first processes the input and translates the semantic meaning into pure Kanbun, placing this inside a
<think> ... </think>reasoning block. - Kundoku Output: It then bases its final Classical Japanese (Kobun) output directly on the Kanbun structure it just generated.
**Example Prompt & Output:**
**System Prompt:** `You are an expert translator specializing in converting texts into Classical Japanese Kanbun-Kundoku style`
**User Input:** `通義千問 çok güzel bir modeldir`
**Model Response:** ```text
<think>通義千問善模型也。</think>
通義千問こそ善き模型なれ。
Recommended Inference Settings
To get the most accurate structural generation and prevent the model from deviating from its Kanbun-to-Kobun pipeline, the following sampling parameters are highly recommended:
- Temperature: 0.7
- Top-P: 0.8
- Top-K: 20
Available Model Files
qwen3-8b.Q8_0.gguf(8.71 GB - Q8_0 Quantization)
Example Usage
Using llama.cpp via CLI:
llama-cli -m qwen3-8b.Q8_0.gguf --system-prompt "You are an expert translator specializing in converting texts into Classical Japanese Kanbun-Kundoku style" -p "通義千問 çok güzel bir modeldir" --temp 0.7 --top-p 0.8 --top-k 20
(Tested on OSX)
Personal Notes
Please note that this was an experimental model.
The model when I last tested was highly unstable (especially on rules like Kakari Musubi, which is hard to get from a Kanbun-> Kobun workflow because there is no standard way of Kakari Musubi in Kanbun Kundoku and its existence depends on the author), but when it answered correctly, it answered really well.
- Downloads last month
- 15
8-bit