README.md

metadata

language:
  - en
  - de
  - fr
  - zh
  - pt
  - nl
  - ru
  - ko
  - it
  - es
license: cc-by-nc-4.0
metrics:
  - comet
pipeline_tag: translation
tags:
  - mlx
base_model: Unbabel/TowerInstruct-7B-v0.2

ethicalabs/TowerInstruct-7B-v0.2-mlx-4Bit

The Model ethicalabs/TowerInstruct-7B-v0.2-mlx-4Bit was converted to MLX format from Unbabel/TowerInstruct-7B-v0.2 using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("ethicalabs/TowerInstruct-7B-v0.2-mlx-4Bit")

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)