| base_model: | |
| - google/gemma-2-2b | |
| - google/gemma-2-2b-it | |
| - rinna/gemma-2-baku-2b | |
| language: | |
| - ja | |
| - en | |
| library_name: transformers | |
| license: gemma | |
| pipeline_tag: text-generation | |
| tags: | |
| - gemma2 | |
| - conversational | |
| - mlx | |
| thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png | |
| base_model_relation: merge | |
| # mlx-community/gemma-2-baku-2b-it-4bit | |
| The Model [mlx-community/gemma-2-baku-2b-it-4bit](https://huggingface.co/mlx-community/gemma-2-baku-2b-it-4bit) was converted to MLX format from [rinna/gemma-2-baku-2b-it](https://huggingface.co/rinna/gemma-2-baku-2b-it) using mlx-lm version **0.17.1**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("mlx-community/gemma-2-baku-2b-it-4bit") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |