Instructions to use mmrech/Minimalism with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mmrech/Minimalism with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mmrech/Minimalism") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- MLX LM
How to use mmrech/Minimalism with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mmrech/Minimalism" --prompt "Once upon a time"
| { | |
| "model_type": "qwen2", | |
| "adapter_type": "lora", | |
| "base_model": "mlx-community/Qwen2.5-Coder-0.5B-Instruct-4bit", | |
| "base_model_reference": "Qwen/Qwen2.5-Coder-0.5B-Instruct", | |
| "task": "text-generation", | |
| "framework": "mlx", | |
| "lora_rank": 8, | |
| "lora_alpha": 16, | |
| "lora_dropout": 0.05, | |
| "trained_on": "flwrlabs/code-alpaca-20k", | |
| "training_samples": 2000, | |
| "training_iterations": 100, | |
| "model_name": "Minimalism", | |
| "description": "LoRA adapter for Qwen2.5-Coder-0.5B-Instruct trained on code-alpaca-20k dataset. Provides runnable-first coding assistance.", | |
| "license": "apache-2.0" | |
| } |