Instructions to use GeneLab/3LM-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use GeneLab/3LM-MLX 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("GeneLab/3LM-MLX") 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 GeneLab/3LM-MLX with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "GeneLab/3LM-MLX" --prompt "Once upon a time"
- Atomic Chat
Download metrics.json from GeneLab/3LM-MLX: direct link, hf CLI and curl.
- Browser
- Download file 113 Bytes
-
https://huggingface.co/GeneLab/3LM-MLX/resolve/main/metrics.json
- Command line
-
hf download hf://GeneLab/3LM-MLX/metrics.json
-
curl -L -o metrics.json https://huggingface.co/GeneLab/3LM-MLX/resolve/main/metrics.json
113 Bytes
| { | |
| "step": 2069, | |
| "val_loss": 3.3296, | |
| "stage": "sft", | |
| "instruction_masking": true, | |
| "mask_ratio": 0.7725 | |
| } |