Reinforcement learning with rewards you can check11 hours ago
When it helps, and when it does not | Data: prompts and references | Rewards | Train | Read the result | Settings that matter | Chaining with the other stages
No articles match
Quickstart: from documents to a model, in R13 hours ago
1. Check the machine | 2. Read the documents | 3. Ask | 4. Write training questions, and review them | 5. Fine-tune | 6. Compare and use | The table route | Choosing settings
The dragonfarm app2 days ago
Two routes through the tabs | The Documents tab | The other tabs | Running it for other people | Under the hood
The post-training loop: fine-tune, judge, prefer, repeat22 days ago
The shape of the loop | 1. Fine-tune | 2. Measure | 3. Make preference pairs from the model's own replies | 4. Preference-optimize on top of the fine-tune | 5. Compare, then go around again | The same loop in one call | Talk to the result | When this loop is the wrong tool