Nous-Yarn-Llama-2-13b-128k is a state-of-the-art language model for long context, further pretrained on long context data for 600 steps.
This model is the Flash Attention 2 patched version of the original model: https://huggingface.co/conceptofmind/Yarn-Llama-2-13b-128k
Note that this model requires the Flash Attention library in order to function correctly, see the Model Usage section for installation instructions.
Starting from the base Llama 2 models, this model was further pretrained on a subset of the PG19 dataset, allowing it to effectively utilize up to 128k tokens of context.
- bloc97: Methods, Paper and evals
- @theemozilla: Methods, Paper and evals
- @EnricoShippole: Model Training
- honglu2875: Paper and evals
The authors would like to thank Stability AI, Carper AI, and Eleuther AI for their generous support of significant computing resources that enabled the training of these models and the completion of this research. We would also like to thank Jonathan Tow and Dakota Mahan directly for their help in advising on the use of the Stability AI compute cluster. Additionally, we would like to thank a16z, and PygmalionAI, for providing resources to run evaluations and experiments on the models.
Install FA2 and Rotary Extensions:
pip install flash-attn --no-build-isolation pip install git+https://github.com/HazyResearch/flash-attention.git#subdirectory=csrc/rotary
There are no specific prompt formats as this is a pretrained base model.
We plan to continue training when we have more compute and to improve the dataset and/or instruct tune the models in order to improve the long context performance even further.
The model is available for download on HuggingFace.
- Downloads last month