通用训练功能策略 » History » Version 1
jun chen, 07/26/2025 04:57 PM
| 1 | 1 | jun chen | # 通用训练功能策略 |
|---|---|---|---|
| 2 | |||
| 3 | Continual Learning in Language Models 2024-07-02 PPT: presentation-liyun.pptx |
||
| 4 | Mix of Experts Ronald(Ronald) |
||
| 5 | |||
| 6 | Model checkpointing for LLMs 2024-07-31 |
||
| 7 | PPT: Improving checkpointing in LLMs-liyun.pptx |
||
| 8 | |||
| 9 | Lora相关技术分享 |
||
| 10 | Yiming Yao(Eamon) |
||
| 11 | |||
| 12 | zero-bubble策略分析及应用 2024-09-13 |
||
| 13 | |||
| 14 | bitsandbytes 量化技巧分析 |
||
| 15 | Wenji Cai |
||
| 16 | PPT: bitandbytes量化技术分享.pptx |
||
| 17 | |||
| 18 | Conf: 8bit optimizer 研究学习 |
||
| 19 | |||
| 20 | 大模型中学习率的调度方法研究 |
||
| 21 | Bo Shi |
||
| 22 | |||
| 23 | |||
| 24 | 量化训练 Ronald(Ronald) |
||
| 25 | 2025-03-16 meeting_01.mp4 |
||
| 26 | |||
| 27 | 后训练ppo介绍 Chao Pan(Chris) |
||
| 28 | 2025-05-30 ppo介绍.mp4 |
||
| 29 | |||
| 30 | Quantized training Damian |
||
| 31 | 2025-3-29 |
||
| 32 | meeting_01.mp4 |
||
| 33 | |||
| 34 | qlora模型量化分享.pptx |
||
| 35 | |||
| 36 | FLUX 介绍 Pei Yao |
||
| 37 | |||
| 38 | https://arxiv.org/pdf/2406.06858 |
||
| 39 | |||
| 40 | FlashOverlap 介绍 Yu Zhuang |
||
| 41 | 2504.19519] FlashOverlap: A Lightweight Design for Efficiently Overlapping Communication and Computation |
||
| 42 | 奖励模型PRM介绍Shanying Wu(Mia) |
||
| 43 | 2025-06-11 |
||
| 44 | PPT：reward model.pptx |
||
| 45 | 录制视频：reward_model_0611_2025.mp4 |