Instructions to use vamazing/Koa-AI-v2-code-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vamazing/Koa-AI-v2-code-9B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="vamazing/Koa-AI-v2-code-9B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("vamazing/Koa-AI-v2-code-9B")
model = AutoModelForMultimodalLM.from_pretrained("vamazing/Koa-AI-v2-code-9B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use vamazing/Koa-AI-v2-code-9B 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 vamazing/Koa-AI-v2-code-9B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vamazing/Koa-AI-v2-code-9B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vamazing/Koa-AI-v2-code-9B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vamazing/Koa-AI-v2-code-9B: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 vamazing/Koa-AI-v2-code-9B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vamazing/Koa-AI-v2-code-9B: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 vamazing/Koa-AI-v2-code-9B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vamazing/Koa-AI-v2-code-9B:Q4_K_M

Use Docker

docker model run hf.co/vamazing/Koa-AI-v2-code-9B:Q4_K_M

LM Studio
Jan

vLLM

How to use vamazing/Koa-AI-v2-code-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vamazing/Koa-AI-v2-code-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vamazing/Koa-AI-v2-code-9B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/vamazing/Koa-AI-v2-code-9B:Q4_K_M

SGLang

How to use vamazing/Koa-AI-v2-code-9B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "vamazing/Koa-AI-v2-code-9B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vamazing/Koa-AI-v2-code-9B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "vamazing/Koa-AI-v2-code-9B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vamazing/Koa-AI-v2-code-9B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use vamazing/Koa-AI-v2-code-9B with Ollama:
```
ollama run hf.co/vamazing/Koa-AI-v2-code-9B:Q4_K_M
```

Unsloth Studio

How to use vamazing/Koa-AI-v2-code-9B 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 vamazing/Koa-AI-v2-code-9B 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 vamazing/Koa-AI-v2-code-9B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vamazing/Koa-AI-v2-code-9B to start chatting

How to use vamazing/Koa-AI-v2-code-9B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vamazing/Koa-AI-v2-code-9B: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": "vamazing/Koa-AI-v2-code-9B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use vamazing/Koa-AI-v2-code-9B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vamazing/Koa-AI-v2-code-9B: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 "vamazing/Koa-AI-v2-code-9B: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"

Docker Model Runner
How to use vamazing/Koa-AI-v2-code-9B with Docker Model Runner:
```
docker model run hf.co/vamazing/Koa-AI-v2-code-9B:Q4_K_M
```

Lemonade

How to use vamazing/Koa-AI-v2-code-9B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vamazing/Koa-AI-v2-code-9B:Q4_K_M

Run and chat with the model

lemonade run user.Koa-AI-v2-code-9B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use vamazing/Koa-AI-v2-code-9B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vamazing/Koa-AI-v2-code-9B: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 vamazing/Koa-AI-v2-code-9B:Q4_K_M

Run Hermes

hermes

Atomic Chat

Koa-AI-v2-code-9B / README.md

vamazing

Update README.md

770bc2a verified 1 day ago

preview code

Raw

History Blame Contribute Delete

3.43 kB

	---
	base_model: Qwen/Qwen3.5-9B
	tags:
	- text-generation-inference
	- transformers
	- unsloth
	- qwen3_5
	- code
	- fine-tune
	- gguf
	- conversational
	- autotrain_compatible
	license: apache-2.0
	language:
	- en
	datasets:
	- FlameF0X/agentic-code
	library_name: transformers
	---

	# Koa AI v2 (`vamazing/Koa-AI-v2-code-9B`)

	Koa AI v2 is an advanced, instruction-tuned language model engineered for agentic workflows, complex code synthesis, multi-turn tool interaction, and step-by-step technical reasoning.
	It is a fine-tuned 9B parameter language model built on the Qwen 3.5 9B architecture. It is optimized for lightweight text generation and coding tasks.

	This repository provides both 16-bit merged weights (`.safetensors`) exported directly from `checkpoint-270` (optimal loss: `0.5614`).

	---

	## 🛠️ Model Overview & Specifications

	\| Feature \| Specification \|
	\| :--- \| :--- \|
	\| Model Name \| Koa AI v2 (Code) \|
	\| Base Architecture \| Qwen 3.5 9B \|
	\| Parameters \| 9 Billion \|
	\| Precision Formats \| 16-bit Merged (`bf16`) \|
	\| Context Length \| 32,768 tokens native (Fine-tuned at 2,048 sequence cap) \|
	\| Fine-Tuning Method \| QLoRA (`r = 16`, `alpha = 32`, Dropout = `0.0`) \|
	\| Target Modules \| `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj` \|
	\| Primary Frameworks \| Unsloth, PyTorch, Hugging Face Transformers, `llama.cpp` \|


	---

	## 📡 Modalities & Capabilities

	### Supported Modalities
	* Text Input → Text/Code Output: Structured reasoning, code synthesis, documentation, and agentic trajectory logging.
	* Tool & Function Calling: Formatted structured output for executing terminal/bash commands, tool calls, and API integrations.

	### Core Capabilities
	* Agentic Coding & Execution: Fine-tuned on agentic interaction traces to analyze system states, execute terminal commands, write code, and autonomously debug execution errors.
	* Qwen 3.5 9B Foundation: Leverages deep multi-step problem solving across complex multi-file codebases and algorithm challenges.
	* Structured Reasoning: Native support for deep logic, architectural planning, and structured chain-of-thought processing.


	---

	## Quickstart

	### Option 1: Python / Transformers (16-bit Safetensors)

	```bash
	pip install transformers torch accelerate unsloth
	```

	```python
	from unsloth import FastLanguageModel

	# 1. Load the model and tokenizer
	model, tokenizer = FastLanguageModel.from_pretrained(
	model_name = "your-username/Koa-AI-v1",
	max_seq_length = 2048,
	load_in_4bit = True,
	)
	FastLanguageModel.for_inference(model)

	# 2. Define prompt using ChatML template
	messages = [
	{"role": "system", "content": "You are Koa AI v1, an expert coding agent."},
	{"role": "user", "content": "Write a Python script to monitor GPU VRAM usage."},
	]

	inputs = tokenizer.apply_chat_template(
	messages,
	tokenize = True,
	add_generation_prompt = True,
	return_tensors = "pt"
	).to("cuda")

	# 3. Generate response
	outputs = model.generate(input_ids = inputs, max_new_tokens = 512, use_cache = True)
	print(tokenizer.decode(outputs[0]))
	```

	This qwen3_5 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)