Instructions to use j0no12/nero-optimizer-work-simow with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use j0no12/nero-optimizer-work-simow 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("j0no12/nero-optimizer-work-simow") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use j0no12/nero-optimizer-work-simow with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "j0no12/nero-optimizer-work-simow" --prompt "Once upon a time"
- Atomic Chat
Download run.json from j0no12/nero-optimizer-work-simow: direct link, hf CLI and curl.
- Browser
- Download file 231 Bytes
-
https://huggingface.co/j0no12/nero-optimizer-work-simow/resolve/main/run.json
- Command line
-
hf download hf://j0no12/nero-optimizer-work-simow/run.json
-
curl -L -o run.json https://huggingface.co/j0no12/nero-optimizer-work-simow/resolve/main/run.json
231 Bytes
| { | |
| "optimizer": "simow", | |
| "backend": "mlx", | |
| "manifest": "/Users/jonah/Documents/ChatGPT/Training/data/prepared/finephrase-balanced-500m-2k-v2/manifest.json", | |
| "context": 128, | |
| "target_tokens": 500000000, | |
| "batch_size": 32 | |
| } | |