Deepseek-R1 32B Training with Supervised Fine-Tuning (kaggle.com)

4 points by yousef_g 1y ago ↗ HN

0 comments

[ 85.5 ms ] story [ 207 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats