21. A Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL 点击查看该条目的具体内容。 09/10 08:00 ♡
24. F Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps 点击查看该条目的具体内容。 09/03 08:00 ♡
30. T Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers 点击查看该条目的具体内容。 08/26 08:00 ♡