trl-fpo
Train transformer language models with reinforcement learning.
Activity
- Latest release
- 1y ago
- Total releases
- 12
- Cadence
- ~daily
- Last 12 months
- 0
Details
- License
- Apache-2.0
- First release
- Dec 14, 2024
Releases
| Version | Released | |
|---|---|---|
0.0.15
patch
| ||
0.0.14
patch
| ||
0.0.13
patch
| ||
0.0.12
patch
| ||
0.0.11
patch
| ||
0.0.10
patch
| ||
0.0.9
patch
| ||
0.0.8
patch
| ||
0.0.7
patch
| ||
0.0.6
patch
| ||
0.0.5
patch
| ||
0.0.4
initial
|