Yarn-Mistral-7b-128k-sharded

This repo contains a SHARDED version of: https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k

Huge thanks to the publishers for their amazing work, all credits go to them: https://huggingface.co/NousResearch

Model Card: Nous-Yarn-Mistral-7b-128k

Preprint (arXiv)
GitHub

Model Description

Nous-Yarn-Mistral-7b-128k is a state-of-the-art language model for long context, further pretrained on long context data for 1500 steps using the YaRN extension method. It is an extension of Mistral-7B-v0.1 and supports a 128k token context window.

To use, pass trust_remote_code=True when loading the model, for example

model = AutoModelForCausalLM.from_pretrained("NousResearch/Yarn-Mistral-7b-128k",
  use_flash_attention_2=True,
  torch_dtype=torch.bfloat16,
  device_map="auto",
  trust_remote_code=True)

In addition you will need to use the latest version of transformers (until 4.35 comes out)

pip install git+https://github.com/huggingface/transformers

Benchmarks

Long context benchmarks:

Short context benchmarks showing that quality degradation is minimal:

Collaborators

• bloc97: Methods, paper and evals
• @theemozilla: Methods, paper, model training, and evals
• @EnricoShippole: Model training
• honglu2875: Paper and evals

The authors would like to thank LAION AI for their support of compute for this model. It was trained on the JUWELS supercomputer.