Instructions to use mlx-community/zephyr-7b-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/zephyr-7b-beta 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("mlx-community/zephyr-7b-beta") 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 mlx-community/zephyr-7b-beta with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mlx-community/zephyr-7b-beta" --prompt "Once upon a time"
- Atomic Chat
Commit History
-
Upload weights.npz
8010ef2
-
fixing type for model-path (#6)
- fixing type for model-path (bde7b3283f0cdae3d21b1291bb1ebde1d9e76066) Co-authored-by: chinnappan <mohanchinnappan@users.noreply.huggingface.co>62a2396
-
Fix code example (#5)
- Fix code example (b38e68f0854f23d2aff728eaa8f1af4d8e303a5a) Co-authored-by: Omar Sanseviero <osanseviero@users.noreply.huggingface.co>652411e -
Add example of prompt (#1)
- Add example of prompt (d7db22313f68f025a81c00257dc9afafa153114d) Co-authored-by: Omar Sanseviero <osanseviero@users.noreply.huggingface.co>09f8d35 -
Add missing `model_type` to `config.json` (#4)
- Add missing `model_type` to `config.json` (8cc9e19200ca2ed33531a21b8c816e6148c344f8)38c5c05
-
Update config.json
2324626 -
Upload tokenizer.model
259e57d -
Update README.md
02bc678 -
Update README.md
571f4f0 -
Create config.json
3f37902 -
Upload weights.npz with huggingface_hub
d1fcd39 -
initial commit
aa8b023