README.md

metadata

inference: false
library_name: transformers
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ja
  - ko
  - zh
  - ar
  - el
  - fa
  - pl
  - id
  - cs
  - he
  - hi
  - nl
  - ro
  - ru
  - tr
  - uk
  - vi
license: cc-by-nc-4.0
base_model: lenML/aya-expanse-8b-abliterated
tags:
  - gguf
  - CohereForAI
  - mlx
  - mlx-my-repo

KYUNGYONG/aya-expanse-8b-abliterated-Q4-mlx

The Model KYUNGYONG/aya-expanse-8b-abliterated-Q4-mlx was converted to MLX format from lenML/aya-expanse-8b-abliterated using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("KYUNGYONG/aya-expanse-8b-abliterated-Q4-mlx")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)