LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Python

tinker-cookbook

Post-training with Tinker

PythonEmerging

Stars

—

Forks

—

Contributors

8

Last push

3mo ago

Recent commits

Latest commits.

Fix LaTeX rendering in SDFT README (#577)
55e5d07Yujia Bao3mo ago
Extend SFT LR sweep to full Tinker model lineup (#575)
ece68c2Yujia Bao3mo ago
Add nightly branch push to nightly workflow (#576)
78b932bYujia Bao3mo ago
Add SDFT (Self-Distillation Fine-Tuning) recipe with top-K distillation (#524)
952757bYujia Bao3mo ago
Add off-policy top-K distillation for multi-teacher knowledge merging (#572)
bda7cb0Yujia Bao3mo ago

Add 22 marimo tutorials (101-503) (#562)

30c4e01Yujia Bao3mo ago

Fix InterleavedRLDataset crash on ragged last source batch (#574)

91249d6Yujia Bao3mo ago

Add InterleavedRLDatasetBuilder for multi-domain RL training (#570)

fa393f4Yujia Bao3mo ago

Top contributors

Builders behind this project.