Aratako's picture
Update README.md
0e6f1b7 verified
|
raw
history blame
3.41 kB
metadata
license: apache-2.0
language:
  - ja
tags:
  - mistral
  - mixtral
  - not-for-all-audiences
  - nsfw
base_model:
  - NTQAI/chatntq-ja-7b-v1.0
  - stabilityai/japanese-stablelm-instruct-gamma-7b
  - Elizezen/Antler-7B
  - Elizezen/Hameln-japanese-mistral-7B

LightChatAssistant-4x7B

GGUF版はこちら/Click here for the GGUF version

概要

Sdff-Ltba/LightChatAssistant-2x7Bと全く同じ手法を用いつつ、対象を4モデルに拡張してそれらをMoEしたモデルです。素晴らしい手法を提案いただいた@Sdff-Ltbaさんに感謝します。

モデルサイズは大きくなっていますが、推論に同時に使われるエキスパートは2つなので、GPUにオフロードさえできれば元のSdff-Ltba/LightChatAssistant-2x7Bとほぼ同じような速度で動きます。

以下の4モデルをChat Vectorの加算によって対話強化して素材に使用しています。

Chat Vectorの適用方法はSdff-Ltba/LightChatAssistant-2x7Bと同じで、Mistral-7B-Instruct-v0.2とMistral-7B-v0.1の差分を0.8倍してそれぞれのモデルに足しています。

その後、mergekitを使い、4モデルをMoEしました。MoEのconfigは以下の通りです。

base_model: ./chatntq-chatvector
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: ./chatntq-chatvector
    positive_prompts:
    - "roleplay"
    - "question"
    - "answer"
    - "chat"
    - "companion"
    - "character"
    - "math"
    - "code"
    - "[Mode: Roleplay]"
    - "[Mode: Chat]"
    negative_prompts:
    - "storywriting"
    - "book"
    - "story"
    - "chapter"
    - "tale"
    - "history"
    - "write"
    - "novel"
    - "[Mode: Writing]"
  - source_model: ./japanese-stablelm-instruct-gamma-chatvector
    positive_prompts:
    - "roleplay"
    - "question"
    - "answer"
    - "chat"
    - "companion"
    - "character"
    - "math"
    - "code"
    - "[Mode: Roleplay]"
    - "[Mode: Chat]"
    negative_prompts:
    - "storywriting"
    - "book"
    - "story"
    - "chapter"
    - "tale"
    - "history"
    - "write"
    - "novel"
    - "[Mode: Writing]"
  - source_model: ./Hameln-japanese-mistral-chatvector
    positive_prompts:
    - "sex"
    - "storywriting"
    - "erotic"
    - "fuck"
    - "orgasm"
    - "uncensored"
    - "book"
    - "story"
    - "chapter"
    - "tale"
    - "history"
    - "write"
    - "novel"
    - "[Mode: Writing]"
  - source_model: ./Antler-chatvector
    positive_prompts:
    - "sex"
    - "storywriting"
    - "erotic"
    - "fuck"
    - "orgasm"
    - "uncensored"
    - "book"
    - "story"
    - "chapter"
    - "tale"
    - "history"
    - "write"
    - "novel"
    - "[Mode: Writing]"
tokenizer_source: union