行业动态
2026/8/1
10 次阅读
Show HN: Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO)
来源：github.com
来源: https://github.com/pochenai/nano-llm-posttraining 热度: 4 points on HackerNews
来源: https://github.com/pochenai/nano-llm-posttraining
热度: 4 points on HackerNews