metadata

datasets:
  - emozilla/yarn-train-tokenized-16k-mistral
metrics:
  - perplexity
library_name: transformers

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)

Benchmarks

Model	Context Window	ARC-c	Hellaswag	MMLU	Truthful QA
Mistral-7B-v0.1	8K	59.98	83.31	64.16	42.15
Yarn-Mistral-7b-64k	64K	59.38	81.21	61.32	42.50
Yarn-Mistral-7b-128k	128K	58.87	80.58	60.64	42.46

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.