Instructions to use cudo528/Darwin-36B-Opus-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use cudo528/Darwin-36B-Opus-mlx-8bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("cudo528/Darwin-36B-Opus-mlx-8bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use cudo528/Darwin-36B-Opus-mlx-8bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "cudo528/Darwin-36B-Opus-mlx-8bit"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "cudo528/Darwin-36B-Opus-mlx-8bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use cudo528/Darwin-36B-Opus-mlx-8bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "cudo528/Darwin-36B-Opus-mlx-8bit"
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 cudo528/Darwin-36B-Opus-mlx-8bit
Run Hermes
hermes
- OpenClaw new
How to use cudo528/Darwin-36B-Opus-mlx-8bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "cudo528/Darwin-36B-Opus-mlx-8bit"
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 "cudo528/Darwin-36B-Opus-mlx-8bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- MLX LM
How to use cudo528/Darwin-36B-Opus-mlx-8bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "cudo528/Darwin-36B-Opus-mlx-8bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "cudo528/Darwin-36B-Opus-mlx-8bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cudo528/Darwin-36B-Opus-mlx-8bit", "messages": [ {"role": "user", "content": "Hello"} ] }'
Darwin-36B-Opus (MLX Optimized)
This repository provides an MLX-optimized version of FINAL-Bench/Darwin-36B-Opus, a state-of-the-art Mixture-of-Experts (MoE) model engineered for advanced reasoning, chain-of-thought (CoT) processes, and complex problem-solving.
Apple Silicon(Mac) 환경의 MLX 프레임워크에서 최적의 속도와 효율적인 메모리 대역폭으로 구동되도록 포맷 변환 및 최적화가 완료된 버전입니다.
🚀 Model Highlights
- Evolutionary Merge & MoE: Qwen 기반 아키텍처를 진화적 머지(Evolutionary Merge) 기법과 Mixture-of-Experts(MoE) 구조로 결합하여 체급을 뛰어넘는 최고의 효율성을 자랑합니다.
- Advanced Reasoning: 깊은 다단계 사고 과정(
<thought>)을 거쳐 복잡한 코딩, 수학, 과학적 난제를 해결하는 심층 추론(Chain-of-Thought) 능력이 탑재되어 있습니다. - Top-Tier Benchmark Performance: 박사급 난이도의 하드코어 추론 테스트인 GPQA Diamond 벤치마크에서 88.4%의 고득점을 기록했습니다.
- Multilingual Support: 한국어, 영어, 중국어, 일본어를 포함한 10개 이상의 다국어 환경을 완벽하게 지원합니다.
🛠️ Requirements & Installation
이 모델을 구동하려면 최신 버전의 mlx-lm 라이브러리가 필요합니다.
pip install -U mlx-lm
💻 How to Use
1. Python API를 이용한 실행
from mlx_lm import load, generate
model, tokenizer = load("cudo528/Darwin-36B-Opus-MLX-8bit")
prompt = "Quantum computing과 기존 컴퓨터의 근본적인 추론 방식 차이를 한국어로 명확하게 설명해줘."
response = generate(
model,
tokenizer,
prompt=prompt,
max_tokens=2048,
verbose=True # 심층 추론 과정(<thought>)을 확인하려면 True로 설정
)
print(response)
2. 터미널(CLI) 환경에서 즉시 실행
mlx_lm.generate --model cudo528/Darwin-36B-Opus-MLX-8bit --prompt "Explain the concept of Hybrid Vigor in AI." --max-tokens 1024
📂 Quantization & Lineage
- Original Base Model: FINAL-Bench/Darwin-36B-Opus
- Format: MLX Formatted (
.safetensors) - License: Apache-2.0
본 변환 버전은 원본 모델의 가중치 성질과 라이선스를 전적으로 준수합니다. 로컬 하드웨어 사양에 맞춰 양자화 비트 수(예: 8-bit, 4-bit)를 조정한 경우, 파일 목록의 수정을 확인해 주시기 바랍니다.
- Downloads last month
- 42
8-bit
Model tree for cudo528/Darwin-36B-Opus-mlx-8bit
Base model
FINAL-Bench/Darwin-36B-OpusEvaluation results
- Accuracy on GPQA Diamondself-reported88.400