| language: | |
| - en | |
| license: apache-2.0 | |
| tags: | |
| - function calling | |
| - on-device language model | |
| - android | |
| - mlx | |
| base_model: google/gemma-2b | |
| inference: false | |
| space: false | |
| spaces: false | |
| model-index: | |
| - name: Octopus-V2-2B | |
| results: [] | |
| # mlx-community/Octopus-v2-4bit | |
| This model was converted to MLX format from [`NexaAIDev/Octopus-v2`]() using mlx-lm version **0.7.0**. | |
| Refer to the [original model card](https://huggingface.co/NexaAIDev/Octopus-v2) for more details on the model. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("mlx-community/Octopus-v2-4bit") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |