metadata

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 for more details on the model.

Use with mlx

pip install mlx-lm

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

<|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|>