热点
"LLM Fine-tuning" 相关文章
2张4090竟能本地微调万亿参数Kimi K2！趋境联合清华北航把算力门槛击穿了
量子位 2025-11-05T09:58:29.000000Z
[程序员] [大模型微调] 一文掌握 5 种大模型微调的方法
V2EX 2025-10-23T12:46:29.000000Z
大模型微调范式认知再被颠覆？UIUC、Amazon团队最新研究指出SFT灾难性遗忘问题或被误解
机器之心 2025-10-21T08:56:03.000000Z
[分享发现] [兑换码分发] 开箱即用、全链路功能覆盖的低代码在线大模型训练与微调服务平台｜共 20 个
V2EX 2025-10-11T06:49:56.000000Z
[分享发现] [兑换码分发] 开箱即用、全链路功能覆盖的低代码在线大模型训练与微调服务平台｜共 20 个
V2EX 2025-10-11T06:49:46.000000Z
Replacing RL w/ Parameter-based Evolutionary Strategies
少点错误 2025-10-08T01:17:07.000000Z
告别梯度！Evolution Strategies全参微调挑战PPO/GRPO：更稳、更省、更好复现
PaperWeekly 2025-10-07T23:52:56.000000Z
告别梯度！Evolution Strategies全参微调挑战PPO/GRPO：更稳、更省、更好复现
PaperWeekly 2025-10-07T15:18:44.000000Z
开发者狂喜：Thinking Machines发布首款产品Tinker，后训练麻烦全给包了
机器之心 2025-10-02T08:14:45.000000Z
How to scale LLM workloads to 20B+ with Amazon SageMaker using Hugging Face and PyTorch FSDP
philschmid RSS feed 2025-09-30T11:12:33.000000Z
Fine-tune Falcon 180B with QLoRA and Flash Attention on Amazon SageMaker
philschmid RSS feed 2025-09-30T11:11:56.000000Z
How to align open LLMs in 2025 with DPO and and synthetic data
philschmid RSS feed 2025-09-30T11:09:23.000000Z