Instructions to use YauhenBichel/python-vibe-0.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use YauhenBichel/python-vibe-0.5b 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("YauhenBichel/python-vibe-0.5b") 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 YauhenBichel/python-vibe-0.5b with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "YauhenBichel/python-vibe-0.5b" --prompt "Once upon a time"
- Atomic Chat
Commit History
-
update the python-vibe card
Verified signaturece570a0
-
update the python-vibe card
Verified signaturef517e60
-
Say how many runs each number stands on
The 8B row was one result. The same nine cases run six times against unchanged code gave 9, 6, 8, 7, 8, 7, and ten of the fifteen benchmark cases changed verdict between identical runs, so the row is a range now and the other rows say they are single runs. Adds the hardware, because it decides what can be tried: 18 GB of unified memory means a practical ceiling near 11-12 GB, and a 14B could not be measured at all on this machine. Adds what happened on a real 4,580-file repository rather than the demo fixture: reading works, writing scored one out of twelve.60c2bc6
-
update the python-vibe card
Verified signature3205eda -
update the python-vibe card
Verified signature8e7b7d7 -
save python-vibe (python-vibe-hub)
Verified signature9c50c63