LoneStriker/Yarn-Llama-2-70b-32k-2.4bpw-h6-exl2

Model Card: Yarn-Llama-2-70b-32k

Preprint (arXiv)
GitHub

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

Model Description

Nous-Yarn-Llama-2-70b-32k is a state-of-the-art language model for long context, further pretrained on long context data for 400 steps using the YaRN extension method. It is an extension of Llama-2-70b-hf and supports a 32k token context window.

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

model = AutoModelForCausalLM.from_pretrained("NousResearch/Yarn-Llama-2-70b-32k",
  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:

Model	Context Window	1k PPL	2k PPL	4k PPL	8k PPL	16k PPL	32k PPL
Llama-2-70b-hf	4k	3.71	3.27	2.96	-	-	-
Yarn-Llama-2-70b-32k	32k	3.61	3.22	2.91	2.82	2.45	2.23

Short context benchmarks showing that quality degradation is minimal:

Model	Context Window	ARC-c	MMLU	Truthful QA
Llama-2-70b-hf	4k	67.32	69.83	44.92
Yarn-Llama-2-70b-32k	32k	67.41	68.84	46.14

Collaborators

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