huggingface/trl

Releases91

Frequency2 weeks 3 hours

Last Release4 days ago

Stars18.9K

Train transformer language models with reinforcement learning.

Subscribe above to receive notifications when new versions are released.

91 releases

Version	Date	Stability Stability is determined by the version string and may be inaccurate.
v1.9.0	Jul 21, 2026Tuesday, 21 July 2026, 20:26	Stable
v1.8.0	Jul 9, 2026Thursday, 9 July 2026, 18:32	Stable
v1.7.1	Jul 4, 2026Saturday, 4 July 2026, 04:02	Stable
v1.7.0	Jun 25, 2026Thursday, 25 June 2026, 22:47	Stable
v1.6.0	Jun 11, 2026Thursday, 11 June 2026, 21:45	Stable
v1.5.1	May 27, 2026Wednesday, 27 May 2026, 15:25	Stable
v1.5.0	May 25, 2026Monday, 25 May 2026, 15:18	Stable
v1.4.0	May 8, 2026Friday, 8 May 2026, 23:23	Stable
v1.3.0	Apr 26, 2026Sunday, 26 April 2026, 15:28	Stable
v1.2.0	Apr 17, 2026Friday, 17 April 2026, 01:04	Stable
v1.1.0	Apr 12, 2026Sunday, 12 April 2026, 02:11	Stable
v1.0.0	Mar 30, 2026Monday, 30 March 2026, 21:18	Stable
v1.0.0rc1	Mar 20, 2026Friday, 20 March 2026, 22:25	RC
v0.29.1	Mar 20, 2026Friday, 20 March 2026, 03:43	Stable
v0.29.0	Feb 25, 2026Wednesday, 25 February 2026, 21:56	Stable
v0.28.0	Feb 10, 2026Tuesday, 10 February 2026, 13:23	Stable
v0.27.2	Feb 3, 2026Tuesday, 3 February 2026, 18:06	Stable
v0.27.1	Jan 24, 2026Saturday, 24 January 2026, 03:33	Stable
v0.27.0	Jan 16, 2026Friday, 16 January 2026, 02:13	Stable
v0.26.2	Dec 18, 2025Thursday, 18 December 2025, 15:52	Stable
v0.26.1	Dec 12, 2025Friday, 12 December 2025, 17:45	Stable
v0.26.0	Dec 9, 2025Tuesday, 9 December 2025, 20:03	Stable
v0.25.1	Nov 12, 2025Wednesday, 12 November 2025, 16:49	Stable
v0.25.0	Nov 5, 2025Wednesday, 5 November 2025, 23:59	Stable
v0.24.0	Oct 16, 2025Thursday, 16 October 2025, 00:10	Stable