bibproj's picture
Update README.md
da6ac42 verified
metadata
license: gemma
library_name: mlx
pipeline_tag: text-generation
tags:
  - transformers
  - mlx
  - translation
language:
  - ar
  - bg
  - zh
  - cs
  - da
  - nl
  - en
  - fi
  - fr
  - de
  - el
  - gu
  - he
  - hi
  - hu
  - id
  - it
  - ja
  - ko
  - fa
  - pl
  - pt
  - ro
  - ru
  - sk
  - es
  - sv
  - tl
  - th
  - tr
  - uk
  - vi
base_model:
  - yanolja/YanoljaNEXT-Rosetta-27B-2511

mlx-community/YanoljaNEXT-Rosetta-27B-2511-mlx-bf16

This model mlx-community/YanoljaNEXT-Rosetta-27B-2511-mlx-bf16 was converted to MLX format from yanolja/YanoljaNEXT-Rosetta-27B-2511 using mlx-lm version 0.28.4.

You can find more similar translation-related MLX model quants for an Apple Mac Studio at https://huggingface.co/bibproj

Model Description

This model is a 27-billion parameter, decoder-only language model built on the Gemma3 27B architecture and fine-tuned by Yanolja NEXT. It is specifically designed to translate structured data (JSON format) while preserving the original data structure.

The model was trained on a multilingual dataset covering the following languages equally:

  • Arabic
  • Bulgarian
  • Chinese
  • Czech
  • Danish
  • Dutch
  • English
  • Finnish
  • French
  • German
  • Greek
  • Gujarati
  • Hebrew
  • Hindi
  • Hungarian
  • Indonesian
  • Italian
  • Japanese
  • Korean
  • Persian
  • Polish
  • Portuguese
  • Romanian
  • Russian
  • Slovak
  • Spanish
  • Swedish
  • Tagalog
  • Thai
  • Turkish
  • Ukrainian
  • Vietnamese

While optimized for these languages, it may also perform effectively on other languages supported by the base Gemma3 model.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/YanoljaNEXT-Rosetta-27B-2511-mlx-bf16")

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)