Hugging Face's logo
Aunali's picture
13 10 239

Aunali

Cossale
21world's profile picture PhysiQuanty's profile picture alexandreteles's profile picture
·
https://auna.li?q=hf

AI & ML interests

Text2Image and Text2Text generation.

Recent Activity

reacted to qgallouedec's post with 🔥 1 day ago
TRL v1.2 introduces the SSDTrainer 🚀 Simple Self-Distillation (SSD) from Apple's paper "Embarrassingly Simple Self-Distillation Improves Code Generation" is now available as an experimental trainer in TRL. The recipe is as minimal as the name suggests: sample completions from the model itself at a training-time temperature, then fine-tune on those raw, unverified samples with plain cross-entropy. No reward model. No verifier. No teacher model. No reinforcement learning. Just prompts and the model. ```python from trl.experimental.ssd import SSDConfig, SSDTrainer trainer = SSDTrainer( model="Qwen/Qwen3-4B-Instruct", args=SSDConfig(temperature=0.6, top_k=20, top_p=0.95), train_dataset=dataset, ) trainer.train() ``` v1.2 also ships expanded tool-calling support (LLaMA 3.1 / 3.2, DeepSeek-V3), another round of KTO ↔ DPO alignment getting us closer to promoting KTO to stable, a big GRPO simplification for overlong tool results, deprecation of `use_transformers_paged`, and key fixes for VLM response parsing. Full release notes: https://github.com/huggingface/trl/releases/tag/v1.2.0
liked a model 11 days ago
openbmb/VoxCPM2
updated a dataset 12 days ago
Cossale/memory-traces
View all activity

Organizations

Hacktoberfest 2023's profile picture IntellectX AI's profile picture PopAI Technologies's profile picture Hugging Face Discord Community's profile picture AI Starter Pack's profile picture Kepler Systems's profile picture