license: cc-by-sa-3.0
tags:
- Composer
- MosaicML
- llm-foundry
MPT-7B-StoryWriter-65k+
MPT-7B-StoryWriter-65k+ is a model designed to read and write fictional stories with super long context lengths. It was built by finetuning MPT-7B with a context length of 65k tokens on a filtered fiction subset of the books3 dataset. At inference time, thanks to ALiBi, MPT-7B-StoryWriter-65k+ can extrapolate even beyond 65k tokens. We demonstrate generations as long as 84k tokens on a single A100-80GB GPU in our blogpost.
- License: Apache-2.0 (commercial use permitted)
This model was trained by MosaicML and follows a modified decoder-only transformer architecture.
Model Date
May 5, 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!
How to Use
Note: This model requires that trust_remote_code=True be passed to the from_pretrained method. This is because we use a custom model architecture that is not yet part of the transformers package.
It includes options for many training efficiency features such as FlashAttention (Dao et al. 2022), ALiBi, QK LayerNorm, and more.
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained('mosaicml/mpt-7b-storywriter', trust_remote_code=True, torch_dtype=torch.bfloat16)
To use the optimized triton implementation of FlashAttention, you can load with attn_impl='triton' and move the model to bfloat16 like so:
model = transformers.AutoModelForCausalLM.from_pretrained('mosaicml/mpt-7b-storywriter', trust_remote_code=True, torch_dtype=torch.bfloat16, attn_impl='triton')
model.to(device='cuda:0', dtype=torch.bfloat16)
Although the model was trained with a sequence length of 2048 and finetuned with a sequence length of 65536, ALiBi enables users to increase the maximum sequence length during finetuning and/or inference. For example:
config = transformers.AutoConfig.from_pretrained('mosaicml/mpt-7b-storywriter', trust_remote_code=True)
config.update({"max_seq_len": 83968})
model = transformers.AutoModelForCausalLM.from_pretrained('mosaicml/mpt-7b-storywriter', config=config, trust_remote_code=True)
This model was trained with the EleutherAI/gpt-neox-20b tokenizer.
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
Model Description
The architecture is a modification of a standard decoder-only transformer.
The model has been modified from a standard transformer in the following ways:
- It uses FlashAttention
- It uses ALiBi (Attention with Linear Biases) and does not use positional embeddings
- It does not use biases
| Hyperparameter | Value |
|---|---|
| n_parameters | 6.7B |
| n_layers | 32 |
| n_heads | 32 |
| d_model | 4096 |
| vocab size | 50432 |
| sequence length | 65536 |
PreTraining Data
For more details on the pretraining process, see MPT-7B.
The data was tokenized using the EleutherAI/gpt-neox-20b tokenizer.
Limitations and Biases
The following language is modified from EleutherAI's GPT-NeoX-20B
MPT-7B-Instruct can produce factually incorrect output, and should not be relied on to produce factually accurate information. MPT-7B-Instruct was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Acknowledgements
This model was finetuned by Alex Trott and the MosaicML NLP team
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
}