Alvaro Bartolome

alvarobartt

https://alvarobartt.com

AI & ML interests

machine learning @huggingface (inference + cloud)

Recent Activity

updated a dataset about 12 hours ago

huggingface/DEH-image-scan-data

liked a model 1 day ago

LilaRest/gemma-4-31B-it-NVFP4-turbo

liked a model 3 days ago

unsloth/Qwen3.6-35B-A3B-GGUF

View all activity

Organizations

updated a dataset about 12 hours ago

huggingface/DEH-image-scan-data

Viewer • Updated about 12 hours ago • 4 • 15.1k • 10

liked a model 1 day ago

LilaRest/gemma-4-31B-it-NVFP4-turbo

Text Generation • 33B • Updated 9 days ago • 132k • 252

liked a model 3 days ago

unsloth/Qwen3.6-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated 3 days ago • 662k • 482

upvoted a changelog 3 days ago

Hugging Face Changelog

Introducing Kernels

4 days ago

• 137

reacted to sergiopaniego's post with 🤗🔥 3 days ago

Post

981

Earlier this month, Apple introduced Simple Self-Distillation: a fine-tuning method that improves models on coding tasks just by sampling from the model and training on its own outputs with plain cross-entropy

And… it's already supported in TRL, built by Kashif Rasul. you can really feel the pace of development in the team 🐎

Paper by Ruixiang ZHANG, He Bai, Huangjie Zheng, Navdeep Jaitly, Ronan Collobert, Yizhe Zhang at Apple 🍎

How it works: the model generates completions at a training-time temperature (T_train) with top_k/top_p truncation, then fine-tunes on them with plain cross-entropy. no labels or verifier needed

You can try it right away with this ready-to-run example (Qwen3-4B on rStar-Coder):
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd.py
or benchmark a checkpoint with the eval script:
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd_eval.py

One neat insight from the paper: T_train and T_eval compose into an effective T_eff = T_train × T_eval, so a broad band of configs works well. even very noisy samples still help

Want to dig deeper?

Paper: Embarrassingly Simple Self-Distillation Improves Code Generation (2604.01193)
Trainer docs: https://huggingface.co/docs/trl/main/en/ssd_trainer