Hacker News
- Live Dive into How to Finetune DeepSeek R1 on Synthetic Data https://www.oxen.ai/entry/fine-tune-deepseek-r1-with-synthetic-data 2 comments
- Using Llama3.1 405B to generate political synthetic data https://www.oxen.ai/Laurence/political-spam/file/main/texts.parquet?query_id=f6bbb123-1453-4e02-a477-4bebdc379b0e 3 comments
- Fine Tuning a Diffusion Transformer (DiT) from a Single YouTube Video https://www.oxen.ai/ox/PixArtTutorial 2 comments
- G[R]PO VRAM Requirements For the GPU Poor https://www.oxen.ai/blog/grpo-vram-requirements-for-the-gpu-poor 22 comments machinelearning
- No Hype DeepSeek-R1 [R]eading List https://www.oxen.ai/blog/no-hype-deepseek-r1-reading-list 17 comments machinelearning
- Friday's AI Water Cooler call https://oxen.ai/community 2 comments learnmachinelearning
- [R] Discussion of ReFT Paper with lead author Zhengxuan Wu https://www.oxen.ai/blog/arxiv-dives-how-reft-works 5 comments machinelearning
- Fine Tuning a Diffusion Transformer (DiT) from a Single YouTube Video https://www.oxen.ai/ox/PixArtTutorial 2 comments learnmachinelearning
- [R] I-JEPA + a 3-Minute Challenge (Interview test questions) @ Friday's Oxen.ai Paper Club https://www.oxen.ai/community 5 comments machinelearning