view reply Are there any significant changes in v2? I've been trying to fine-tune models with v1 but it seems to support only a select few models
view article Article Distributed SFT with trl and DeepSpeed Part 1: Starting Locally jlzhou • Jan 23, 2025 • 4
view article Article Distributed SFT with trl and DeepSpeed Part 2: Scaling Locally jlzhou • Feb 7, 2025 • 3