README.md

metadata

language:
  - en
  - fr
  - de
  - es
  - it
  - pt
license: apache-2.0
library_name: vllm
inference: false
extra_gated_description: >-
  If you want to learn more about how we process your personal data, please read
  our <a href="https://www.almawave.com/privacy-policy/">Privacy Policy</a>.
tags:
  - transformers
  - mlx
base_model: Almawave/Velvet-14B

moot20/Velvet-14B-MLX-8bits

The Model moot20/Velvet-14B-MLX-8bits was converted to MLX format from Almawave/Velvet-14B using mlx-lm version 0.21.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("moot20/Velvet-14B-MLX-8bits")

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)