PLaMo Translation Model

This is a 4-bit quantized version of the PLaMo 2 Translation Model with DWQ (Distilled Weight Quantization) for inference with MLX on Apple Silicon devices.

PLaMo翻訳モデルはPreferred Networksによって開発された翻訳向け特化型大規模言語モデルです。 詳しくはブログ記事およびプレスリリースを参照してください。

PLaMo Translation Model is a specialized large-scale language model developed by Preferred Networks for translation tasks. For details, please refer to the blog post and press release.

List of models:

PLaMo Translation Model is released under PLaMo community license. Please check the following license and agree to this before downloading.

NOTE: This model has NOT been instruction-tuned for chat dialog or other downstream tasks.

For commercial users

Please check the PLaMo community license and contact us via the following form to use commercial purpose.

Usage

$ pip install mlx-lm numba
$ python -m mlx_lm generate \
--model mlx-community/plamo-2-translate \
--extra-eos-token '<|plamo:op|>' \
--prompt 'あのイーハトーヴォのすきとおった風、夏でも底に冷たさをもつ青いそら、うつくしい森で飾られたモリーオ市、郊外のぎらぎらひかる草の波。'
=========
That clear wind blowing through Ihatovo, that summer sky with its cool depth beneath, that beautiful forest-adorned Morio City, and the glittering waves of grass in the suburbs.

==========
Prompt: 60 tokens, 107.934 tokens-per-sec
Generation: 36 tokens, 39.118 tokens-per-sec
Peak memory: 5.653 GB

Bias, Risks, and Limitations

PLaMo Translation Model is a new technology that carries risks with use. Testing conducted to date has been in English and Japanese, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, PLaMo Translation Model’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of PLaMo Translation Model, developers should perform safety testing and tuning tailored to their specific applications of the model.

Acknowledgement

This model is trained under the project, “Research and Development Project of the Enhanced Infrastructures for Post 5G Information and Communication System” (JPNP 20017), subsidized by the New Energy and Industrial Technology Development Organization (NEDO).

AI policies for Preferred Networks, Inc. group

Downloads last month
429
Safetensors
Model size
1.49B params
Tensor type
BF16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mlx-community/plamo-2-translate

Base model

pfnet/plamo-2-8b
Quantized
(2)
this model

Collection including mlx-community/plamo-2-translate