|
--- |
|
language: |
|
- en |
|
- de |
|
- es |
|
- fr |
|
- ja |
|
- zh |
|
license: apache-2.0 |
|
tags: |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
- Weyaxi/Einstein-v6-7B |
|
- argilla/CapybaraHermes-2.5-Mistral-7B |
|
- mlx |
|
base_model: |
|
- Weyaxi/Einstein-v6-7B |
|
- argilla/CapybaraHermes-2.5-Mistral-7B |
|
--- |
|
|
|
# mlx-community/J.O.S.I.E.3-Beta12-7B-slerp-4-bit |
|
This model was converted to MLX format from [`Isaak-Carter/J.O.S.I.E.3-Beta12-7B-slerp`]() using mlx-lm version **0.12.0**. |
|
Refer to the [original model card](https://huggingface.co/Isaak-Carter/J.O.S.I.E.3-Beta12-7B-slerp) 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/J.O.S.I.E.3-Beta12-7B-slerp-4-bit") |
|
response = generate(model, tokenizer, prompt="hello", verbose=True) |
|
``` |
|
|
|
|
|
Prompt Format to use |
|
|
|
```text |
|
<|im_start|>system |
|
You are JOSIE, my private and superinteligent AI Assistant.<|im_end|> |
|
<|im_start|>user |
|
{{ .Prompt }}<|im_end|> |
|
<|im_start|>assistant |
|
{{ .Response }}<|im_end|> |
|
``` |
|
|
