{"id":"url:thinkingmachines.ai/blog/lora","title":"LoRA Without Regret (Thinking Machines)","date":"2025-09-29","section":"Post-training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/09bfccf7014ee63d12eddd2c954194cd981ce104398b7b64c98873bf2f997b95/","source_url":"https://thinkingmachines.ai/blog/lora/","text_available":false,"authors":["John Schulman","Thinking Machines Lab"],"outgoing":[{"source":"url:thinkingmachines.ai/blog/lora","target":"arxiv:2402.03300","evidence":"id","id":"arxiv:2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/636fb871904bc06f742cfdea069796f9e9665f95bd58dc63260eaff5154ef985/"},{"source":"url:thinkingmachines.ai/blog/lora","target":"arxiv:2404.05405","evidence":"id","id":"arxiv:2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/541683d3678177bb2800d37a49a2f541c8a2c81cf802eaefe8840fed359c540e/"},{"source":"url:thinkingmachines.ai/blog/lora","target":"arxiv:2407.21783","evidence":"id","id":"arxiv:2407.21783","title":"The Llama 3 Herd of Models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/de3cebb4c28bc5d41a843279f219dca14476284991ea5c7c0aeab7068a40e306/"}],"incoming":[],"text_parts":[],"contents":[],"text_code_points":0,"source_markdown":null}