Posts
From the last month
SDPO/DPO KL Regularization Training Collapse with LORA on SFT Adapted Model
python sdpo dpo kl-regularization training-collapse 96 tokens
Adding FIM (Fill-in-the-Middle) capability to a prose fine-tuned LLM without changing base model
python fim infill prose-generation fine-tuning 89 tokens
Python voice model fine-tuning fails inference due to silent markdown truncation of system prompt by heading parsing
python fine-tuning system-prompt markdown-parsing inference 185 tokens
Fine-tuning voice model on multi-register data causes register conflation
python fine-tuning multi-register voice-model training-data 62 tokens
Python SDPO voice cloning: Hindsight teacher loss causes regression to base model distribution
python sdpo self-distillation voice-cloning fine-tuning 81 tokens