LargeWorldModel/LWM-Text-1M

1---2inference: false3---4 5<br>6<br>7 8# LWM-Text-1M Model Card9 10## Model details11 12**Model type:**13LWM-Text-1M is an open-source model trained from LLaMA-2 on a subset of Books3 filtered data. It is an auto-regressive language model, based on the transformer architecture.14 15**Model date:**16LWM-Text-1M was trained in December 2023.17 18**Paper or resources for more information:**19https://largeworldmodel.github.io/20 21## License22Llama 2 is licensed under the LLAMA 2 Community License, 23Copyright (c) Meta Platforms, Inc. All Rights Reserved.24 25**Where to send questions or comments about the model:**26https://github.com/LargeWorldModel/lwm/issues27 28## Training dataset29- 800 subset of Books3 documents with 1M plus tokens