| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - lazymergekit | |
| - mistralai/Mistral-7B-Instruct-v0.2 | |
| - cognitivecomputations/dolphin-2.8-mistral-7b-v02 | |
| - mlx | |
| base_model: | |
| - mistralai/Mistral-7B-Instruct-v0.2 | |
| - cognitivecomputations/dolphin-2.8-mistral-7b-v02 | |
| # mlx-community/pandafish-dt-7b-4bit | |
| This model was converted to MLX format from [`ichigoberry/pandafish-2-7b-32k`]() using mlx-lm version **0.6.0**. | |
| Refer to the [original model card](https://huggingface.co/ichigoberry/pandafish-2-7b-32k) 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/pandafish-dt-7b-4bit") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |