Skip to content

abeja

Mixtral-8x7B-Instruct-v0.1-japanese-alpha

abeja/Mixtral-8x7B-Instruct-v0.1-japanese-alpha

Mixtral-8x7B-Instruct-v0.1-japanese-alpha is a text generation model from abeja. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

Mixtral-8x7B-Instruct-v0.1-japanese-alphaはMixtral-8x7B-Instruct-v0.1をベースに日本語の語彙拡張継続事前学習を実施した学習途中のモデルです。 ABEJAのテックブログにて評価を実施した途中結果モデルとして公開しています。 学習を実施したMetagton-LMのレポジトリはこちらです。

Downloads · 30 days

96

18% of all-time downloads

All-time downloads

527

Public

Parameters

46.9B

188 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors188 GB · 100%

At a glance

Task
Text Generation
Library
transformers
License
apache-2.0
Model type
mixtral
Access
Public
Created
Apr 16, 2024
Updated
Apr 20, 2024
SHA
09080a30

Try a prompt

Task
Text Generation
Library
transformers
Type
mixtral
License
apache-2.0
Languages
ja
Created
Apr 16, 2024
Updated
Apr 20, 2024