mpt-7b-storywriter-4bit-128g-65kTokens-CPU

THIS MODEL IS NOT QUITE FULLY FINISHED OR TESTED, PLEASE TAKE THIS INTO CONSIDERATION.

---

license: apache-2.0

---

tags:

• Composer
• MosaicML
• llm-foundry
• AnimusOG
• Oobabooga
• KoboldAI
• Text-Generation
• Conversational
• Uncensored

---

MPT-7B-StoryWriter-65k+

Quantized for KoboldAI (4bit-fork)

How to Use

This is meant to be used with the oobabooga text-generation-webui:

Oobabooga

webui.py command flags when starting Oobabooga:

--trust-remote-code --model-type llama

MPT-7B-StoryWriter-65k+ can extrapolate even beyond 65k tokens.

Model Date

May 15, 2023

Model License

Apache-2.0 (commercial use permitted)

Documentation

• Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs
• Codebase (mosaicml/llm-foundry repo)
• Questions: Feel free to contact us via the MosaicML Community Slack!

Citation

Please cite this model using the following format:

@online{MosaicML2023Introducing,
    author    = {MosaicML NLP Team},
    title     = {Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs},
    year      = {2023},
    url       = {www.mosaicml.com/blog/mpt-7b},
    note      = {Accessed: 2023-03-28}, % change this date
    urldate   = {2023-03-28} % change this date
}