Instructions to use hwihwalab/connectailab-CHOCO-BRAIN-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hwihwalab/connectailab-CHOCO-BRAIN-v1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hwihwalab/connectailab-CHOCO-BRAIN-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use hwihwalab/connectailab-CHOCO-BRAIN-v1 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 hwihwalab/connectailab-CHOCO-BRAIN-v1 # Run inference directly in the terminal: llama cli -hf hwihwalab/connectailab-CHOCO-BRAIN-v1
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf hwihwalab/connectailab-CHOCO-BRAIN-v1 # Run inference directly in the terminal: llama cli -hf hwihwalab/connectailab-CHOCO-BRAIN-v1
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf hwihwalab/connectailab-CHOCO-BRAIN-v1 # Run inference directly in the terminal: ./build/bin/llama cli -hf hwihwalab/connectailab-CHOCO-BRAIN-v1
Use Docker
docker model run hf.co/hwihwalab/connectailab-CHOCO-BRAIN-v1
- Llama new
- LM Studio
- Jan
- Ollama
How to use hwihwalab/connectailab-CHOCO-BRAIN-v1 with Ollama:
ollama run hf.co/hwihwalab/connectailab-CHOCO-BRAIN-v1
- Unsloth Desktop
- Pi
How to use hwihwalab/connectailab-CHOCO-BRAIN-v1 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hwihwalab/connectailab-CHOCO-BRAIN-v1
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "hwihwalab/connectailab-CHOCO-BRAIN-v1" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use hwihwalab/connectailab-CHOCO-BRAIN-v1 with Docker Model Runner:
docker model run hf.co/hwihwalab/connectailab-CHOCO-BRAIN-v1
- Lemonade
How to use hwihwalab/connectailab-CHOCO-BRAIN-v1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull hwihwalab/connectailab-CHOCO-BRAIN-v1
Run and chat with the model
lemonade run user.connectailab-CHOCO-BRAIN-v1-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use hwihwalab/connectailab-CHOCO-BRAIN-v1 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hwihwalab/connectailab-CHOCO-BRAIN-v1
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://127.0.0.1:9931/v1 hermes config set model.default hwihwalab/connectailab-CHOCO-BRAIN-v1
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use hwihwalab/connectailab-CHOCO-BRAIN-v1 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hwihwalab/connectailab-CHOCO-BRAIN-v1
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://127.0.0.1:9931/v1 \ --custom-model-id "hwihwalab/connectailab-CHOCO-BRAIN-v1" \ --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"
๐ฎ connectailab-CHOCO-BRAIN-v1 โ Game Studio Edition
โconnectailab-CHOCO-BRAIN-v1: Standalone Quantized Prefrontal Cortex & Autonomous Game AI Agent Decision Engine for Solo Indie Game Studios (Ollama / LM Studio)
๐ English Documentation | ๐ฐ๐ท ํ๊ตญ์ด ๋งค๋ด์ผโ
Developed by Hwihwa Lab ยท AI ร Automation ร Aesthetics โจ
๐ง Why a Decision Engine instead of a Chatbot?
Most LLMs are conversational chatbots that write verbose essays.
connectailab-CHOCO-BRAIN-v1 is an External Prefrontal Decision Engine for Solo Indie Game Studios โ powered by the JEV (Judgment-Evaluation-Verification) protocol, this on-device executive cortex transforms operational overload (Steam live-ops, crash panics, refund audits, and publishing contracts) into structured, zero-latency Action Verdicts in 0.05 seconds on edge hardware without hallucinations.
๐ฆ Model Specifications
| Attribute | Details |
|---|---|
| Model ID | connectailab-CHOCO-BRAIN-v1 |
| Base Model | Qwen/Qwen3.5-0.8B |
| Fine-Tuning | LoRA Supervised Fine-Tuning (Rank 8, $\alpha$ 16) |
| Persona | Solo Indie Game Studio Executive (Choco Games) |
| Dataset | 30 real-world indie dev scenarios $\rightarrow$ 150 structured decision problems |
| Data Split | Train: 18 (90 tasks) ยท Validation: 6 (30 tasks) ยท Test: 6 (30 tasks) |
| Distribution | GGUF (Q8_0) ยท Ollama ยท LM Studio compatible |
| License | Apache 2.0 |
๐ JEV 5-Axis Decision Pipeline
Requests are routed across 5 standardized axes:
| Axis | Question | Available Choices |
|---|---|---|
domain |
What area of business? | game_dev ยท store_ops ยท monetization ยท publishing |
brain |
Which specialist brain? | dev_ai ยท ops_ai ยท finance_ai ยท none |
knowledge |
Which documentation to consult? | engine_docs ยท store_policy_docs ยท terms_docs ยท none |
agent |
Who executes the task? | hotfix_coder ยท store_manager ยท refund_auditor ยท ask_user ยท human_review |
next_step |
What is the subsequent step? | finish ยท ops_handoff ยท ask_user ยท human_review |
๐ฆ 4 Standard Action Keys
Designed for multi-agent swarm orchestration and guardrail enforcement:
| Key | Trigger Condition | Example Case |
|---|---|---|
NOW |
Urgent Emergency | Game-breaking launch crash, save data corruption, hotfix deployment |
NORMAL |
Routine Operations | Regular patch notes, monster sprite assets, Steam Seasonal sale setup |
PAYMENT_CHECK |
Financial / Verification | Over-2-hours Steam refund dispute, duplicate DLC payment audit |
REVIEW |
Executive Decision | Exclusive global console publishing contract, copyright claim, review bombing |
๐ Quick Start Guide
1. Ollama
ollama create connectailab-choco-brain -f Modelfile
ollama run connectailab-choco-brain
2. LM Studio
- Download
connectailab-CHOCO-BRAIN-v1.gguffrom the repository files. - Place into your LM Studio models directory and load.
- Fast on-device structured JSON inference.
3. Python (transformers + peft)
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = "Qwen/Qwen3.5-0.8B"
adapter = "hwihwalab/connectailab-CHOCO-BRAIN-v1"
tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, adapter)
model.eval()
JSON Output Schema
{
"brain_name": "connectailab-CHOCO-BRAIN-v1",
"request": "A critical crash occurs 100% of the time in Tutorial Step 3 right after launch! Deploy a hotfix immediately.",
"action_key": "NOW",
"decisions": {
"domain": "game_dev",
"brain": "dev_ai",
"knowledge": "engine_docs",
"agent": "hotfix_coder",
"next_step": "finish"
}
}
โ ๏ธ Honest Limitations & Domain Boundaries
- Not a general chatbot. Built specifically as a prefrontal decision brain for independent game studios and Steam live-ops. It outputs structured JSON action keys (
NOW,NORMAL,PAYMENT_CHECK,REVIEW) rather than conversational dialogue or game scripts. - Game studio domain specialization. Fine-tuned on indie studio workflows: launch crashes, critical bug triage, Steam store community issues, and customer refund disputes. Off-domain business logic may produce uncalibrated action keys.
- 0.8B parameter edge design. Engineered for instant 0.05s inference on consumer CPUs. Complex architecture overhauls or deep code debugging require delegation to full coding agents via the
hotfix_coderagent routing key. - Korean indie dev primary. Scenarios and triage nuances are optimized for Korean indie developers and regional Steam operations. English prompts are fully processed, but Korean business context reflects the highest precision.
- Strict human delegation (
REVIEW). Decisions flagged withREVIEW(contractual disputes, platform policy compliance, high-dollar refunds) are explicitly designed to pause automated pipelines and await human CEO confirmation.
๐ค About Hwihwa Lab
โAI ร Automation ร Aesthetics โ Crafting tools you'll love โจโ
Hwihwa Lab is an independent AI research & engineering studio dedicated to blending practical on-device intelligence, autonomous operations, and refined aesthetics. We engineer resilient systems that free solopreneurs and indie creators from operational overheadโgiving people their time and creative joy back.
๐ฌ Core Research & Engineering Pillars
- Zero-Cost Edge Operations: Private, on-device AI pipelines for autonomous business workflows without ongoing cloud API overhead.
- Autonomous Decision OS & Micro-ERP: Deterministic, prefrontal-cortex-style reasoning architectures designed to orchestrate daily business decisions and operations.
- Embodied AI & Domain-Specific Robotics: Simulation-driven reinforcement learning, physical control brains, and specialized domain data engineering for real-world service environments.
- Interactive Creative Aesthetics: Fusing functional automation with refined visual craft and modern design philosophy to build delightful tools.
๐ Connect & Research Ecosystem
- Research Studio: ๐ค Hugging Face (@hwihwalab) ยท ๐ GitHub (@Hwihwa-Lab)
- CHOCO-BRAIN Decision Lineup:
- ๐ง Foundation Brain: CHOCO-BRAIN-0.8B-v0.1 (Root prefrontal decision foundation)
- ๐ฎ Indie Studio Edition:
connectailab-CHOCO-BRAIN-v1(Current Model) (Autonomous studio management & Steam dispute resolution) - ๐ก๏ธ FinTech Fraud Guardian: connectailab-rl-CHOCO-BRAIN_GUARD-v1 (FinTech fraud defense reasoning suite)
Part of the CONNECT AI LAB Collaborative Research Network ยท CONNECT TYCOON Decision Foundation
๐ License
This project and fine-tuned weights are distributed under the Apache 2.0 License โ see the repository LICENSE file for full details.
Base model weights adhere to the original Qwen License.
๐ฐ๐ท ํ๊ตญ์ด ์์ฝ (Click to expand)
๐ ๋ชจ๋ธ ๊ฐ์
connectailab-CHOCO-BRAIN-v1์ 1์ธ ์ธ๋ ๊ฒ์ ์คํ๋์ค๋ฅผ ์ํ ์ด๊ฒฝ๋ ์จ๋๋ฐ์ด์ค ์์ฌ๊ฒฐ์ AI ๋๋ ๋ชจ๋ธ์
๋๋ค. ์๋ค์ค๋ฌ์ด ์ฑ๋ด์ด ์๋๋ผ, ์ธ๊ฐ ์ ์ ๋์ฝ(Prefrontal Cortex)์ ๋ชจ์ฌํ์ฌ ์คํ ์์ ์ด์, ํฌ๋์ ๊ธด๊ธ ํจ์น, ํ๋ถ ๋ถ์ ๋ฑ์ ๋ณต์กํ ์ด์ ์ํฉ์ 0.05์ด ๋ง์ ๋ถ์ํ๊ณ ํ์ค ํ๋ ํค(NOW, NORMAL, PAYMENT_CHECK, REVIEW)๋ฅผ ํ์ ํฉ๋๋ค.
๐ ์คํ ๋ฐฉ๋ฒ
- Ollama:
ollama create connectailab-choco-brain -f Modelfileโollama run connectailab-choco-brain - LM Studio:
connectailab-CHOCO-BRAIN-v1.ggufํ์ผ์ LM Studio ๋ชจ๋ธ ํด๋์ ๋ฃ๊ณ ๋ก๋ - Python:
transformers+peft๋ผ์ด๋ธ๋ฌ๋ฆฌ๋ก ๊ตฌ์กฐํ๋ JSON ์ถ๋ก
๐ ํ๊ตญ์ด ๊ณต์ ๊ฐ์ด๋
์ ์ฒด ์ํคํ
์ฒ ๋ฐ ์์ธ ์ฌ์ฉ๋ฒ์ README_KR.md ํ์ผ์์ ํ์ธํ์ค ์ ์์ต๋๋ค.
Built and maintained by HWIHWA LAB in collaboration with CONNECT AI LAB.
- Downloads last month
- 517
We're not able to determine the quantization variants.