trl-fpo
Train transformer language models with reinforcement learning.
- Latest release
- Jan 18, 2025
- Releases
- 12
- Known CVEs
- 0
- First release
- Dec 14, 2024
- License
- Apache-2.0
Repository
Source
- Stars
- —
- Forks
- —
- Open issues
- —
Security score
No OpenSSF Scorecard available for this repository.
Packages from this repo
Insights
Activity
- Total releases
- 12
- Last 12 months
- 0
- Cadence
- ~daily
- Dependencies
- 26
Releases per month
last 12 monthsRelease mix
- patch 11
12
releases
Dependencies
Depends on
0.0.15-
accelerate
-
bitsandbytes
<=0.41.1
-
datasets
-
deepspeed
-
diffusers
>=0.18.0
-
ghapi
-
huggingface-hub
>=0.22.2
-
llm-blender
>=0.0.2
-
nltk
-
numpy
<2.0.0,>=1.18.2
1–10 of 26
Used by
Nothing tracked depends on this yet.
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
|