finbarr Didn't huggingface have something similar to paperswithcode ?

You shouldn't do RL on small model. Distilling from large models works better. And you can now do it even when tokenizers don't match.

My book is on a great start, #1 best seller on Amazon! 🥳 (thanks to my whole family for boosting sales)

the bloopers is the best part to understand what's the real life of a post-trainers 👨‍🌾

Sharing the slides from yesterday's talk about "Fine Tuning with TRL" from the Together AI x Hugging Face workshop we hosted in our Paris office 🎃!

Questions! 🧐 LayerNorm always upcasts inputs to fp32 for stability (hardcoded). But the final multiplication by the weights is in the original dtype. 1. Why? Sometimes we do this multiplication in fp32. 2. When and why?

most of these don’t require AI, even for beginners github.com/huggingface/tr…

In the Smol Training Playbook, I tried to survey the state of popular post-training frameworks. Let me know if I missed any and I'll add them to the list!

Here is a tutorial on training LLaSA (LLaMA-based TTS) using GRPO to improve prosody, rhythm, and expressiveness in synthesized speech with TRL!

Trackio 0.8.0 is out! You can now log tables as part your experiments with an intuitive syntax, let's GOOOO 🎯

On-policy distillation is powerful, but Thinking Machines's tinker only supports distilling from a teacher model within the same family, making it impossible for qwen to learn from deepseek, gpt-oss, etc. For the first time, we enabled model-agnostic distillations natively using

how not to do a good job? 🫶

Josh 2 months of oss work got me more interest from big labs than 4 ivy degrees over 9 years :)

Reinforcement Learning for agents has been held back by a lack of standard infrastructure. Production agents don't live in clean "gyms"—they live in messy, async environments. Today we’re open-sourcing Eval Protocol: a framework to run RL directly on your production agents. Day