OpenCoder Collection OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs. • 4 items • Updated 1 day ago • 34
LLM-Assisted Code Cleaning For Training Accurate Code Generators Paper • 2311.14904 • Published Nov 25, 2023 • 4
LayerSkip Collection Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated 14 days ago • 42
Direct Preference Optimization Datasets Collection Datasets suitable for DPO based on having 'chosen', 'rejected', and 'prompt' columns. Created using librarian-bots/dataset-column-search-api • 3148 items • Updated about 9 hours ago • 6
Enhancing Training Efficiency Using Packing with Flash Attention Paper • 2407.09105 • Published Jul 12 • 14
view article Article Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset Mar 15 • 6