metadata

language:
  - en
license: apache-2.0
tags:
  - causal-lm
  - text-generation
  - 7b
  - ozone-ai
  - reverb
  - open-source
  - mlx
datasets: []
metrics:
  - type: MMLU Pro
    value: 0.4006
base_model: ozone-ai/Reverb-7b

alexgusevski/Reverb-7b-q8-mlx

The Model alexgusevski/Reverb-7b-q8-mlx was converted to MLX format from ozone-ai/Reverb-7b using mlx-lm version 0.21.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/Reverb-7b-q8-mlx")

prompt = "hello"

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

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