mirror of
				https://github.com/huggingface/trl.git
				synced 2025-11-04 21:24:29 +08:00 
			
		
		
		
	Compare commits
					base: frozenleaves:v0.14.0
					
				
				
						
							frozenleaves:main
						
							frozenleaves:openenv-docs-improvement
						
							frozenleaves:docs/move-multi-adapter-rl
						
							frozenleaves:docs/update-peft-integration
						
							frozenleaves:refactor/move-judges-to-experimental
						
							frozenleaves:refactor/move-mergekit-to-experimental
						
							frozenleaves:docs/remove-outdated-notebooks
						
							frozenleaves:docs/unify-trl-lib-namespace
						
							frozenleaves:docs/add-peft-to-reducing-memory
						
							frozenleaves:docs/expand-training-customization
						
							frozenleaves:docs/extend-cli-examples
						
							frozenleaves:doc/update-alst-ulysses-docs
						
							frozenleaves:tool-call-finally
						
							frozenleaves:py3.14
						
							frozenleaves:fix-test-vlm
						
							frozenleaves:gold-2
						
							frozenleaves:qgallouedec-env
						
							frozenleaves:ci-test-dev
						
							frozenleaves:copilot/fix-typo-in-text
						
							frozenleaves:iiger-mean-acc
						
							frozenleaves:openenv-integration
						
							frozenleaves:remove-fsdp1-support
						
							frozenleaves:v0.24-release
						
							frozenleaves:sft-video
						
							frozenleaves:refactor-dpo
						
							frozenleaves:chatml-collator-fix
						
							frozenleaves:remove-best-of-n-sampler
						
							frozenleaves:online-dpo-ben
						
							frozenleaves:max-length-docs
						
							frozenleaves:fix-dbrx
						
							frozenleaves:v0.23-release
						
							frozenleaves:tool-call
						
							frozenleaves:multi-turn
						
							frozenleaves:faster-ci
						
							frozenleaves:internvl-grpo-issue-4061
						
							frozenleaves:rear
						
							frozenleaves:lewtun-patch-1
						
							frozenleaves:support-reward-refactor
						
							frozenleaves:update-paper-index
						
							frozenleaves:v0.22-release
						
							frozenleaves:simplify-data-collator
						
							frozenleaves:liger-orpo
						
							frozenleaves:dist-ci
						
							frozenleaves:v0.21-release
						
							frozenleaves:feature/sglang-integration
						
							frozenleaves:dynamic_temp
						
							frozenleaves:update-for-cb
						
							frozenleaves:v0.20-release
						
							frozenleaves:v0.19-release
						
							frozenleaves:gkd-vllm
						
							frozenleaves:vllm-spec-dec
						
							frozenleaves:v0.18-release
						
							frozenleaves:grpo-per-batch-padding
						
							frozenleaves:gkd-cb
						
							frozenleaves:grpo-ssr-replay-buffer
						
							frozenleaves:grpo-log-entropy
						
							frozenleaves:grpo-adv-replay-buffer
						
							frozenleaves:vllm-fp8
						
							frozenleaves:add-entropy
						
							frozenleaves:v0.17-release
						
							frozenleaves:grpo-dapo-dyn-samp
						
							frozenleaves:grpo-mega-batch
						
							frozenleaves:log-correct_incorrect_length
						
							frozenleaves:v0.16-release
						
							frozenleaves:grpo-vllm-logprobs
						
							frozenleaves:static-cache-grpo
						
							frozenleaves:v0.15-release
						
							frozenleaves:tpo
						
							frozenleaves:agents
						
							frozenleaves:v0.14-release
						
							frozenleaves:prime
						
							frozenleaves:v0.13-release
						
							frozenleaves:v0.12-release
						
							frozenleaves:cloud-trainer
						
							frozenleaves:prm-trainer-qgallouedec
						
							frozenleaves:score
						
							frozenleaves:v0.11-release
						
							frozenleaves:v0.10-release
						
						
						
						
					
					
						
							frozenleaves:v0.24.0
						
							frozenleaves:v0.23.1
						
							frozenleaves:v0.23.0
						
							frozenleaves:v0.22.2
						
							frozenleaves:v0.22.1
						
							frozenleaves:v0.22.0
						
							frozenleaves:v0.21.0
						
							frozenleaves:v0.20.0
						
							frozenleaves:v0.19.1
						
							frozenleaves:v0.19.0
						
							frozenleaves:v0.18.2
						
							frozenleaves:v0.18.1
						
							frozenleaves:v0.18.0
						
							frozenleaves:v0.17.0
						
							frozenleaves:v0.16.1
						
							frozenleaves:v0.16.0
						
							frozenleaves:v0.15.2
						
							frozenleaves:v0.15.1
						
							frozenleaves:v0.15.0
						
							frozenleaves:v0.14.0
						
							frozenleaves:v0.13.0
						
							frozenleaves:v0.12.2
						
							frozenleaves:v0.12.1
						
							frozenleaves:v0.12.0
						
							frozenleaves:v0.11.4
						
							frozenleaves:v0.11.3
						
							frozenleaves:v0.11.2
						
							frozenleaves:v0.11.1
						
							frozenleaves:v0.11.0
						
							frozenleaves:v0.10.1
						
							frozenleaves:v0.10
						
							frozenleaves:v0.9.6
						
							frozenleaves:v0.9.4
						
							frozenleaves:v0.9.3
						
							frozenleaves:v0.8.6
						
							frozenleaves:v0.8.5
						
							frozenleaves:v0.8.4
						
							frozenleaves:v0.8.3
						
							frozenleaves:v0.8.2
						
							frozenleaves:v0.8.1
						
							frozenleaves:v0.8.0
						
							frozenleaves:v0.7.11
						
							frozenleaves:v0.7.10
						
							frozenleaves:v0.7.9
						
							frozenleaves:v0.7.8
						
							frozenleaves:v0.7.7
						
							frozenleaves:v0.7.6
						
							frozenleaves:v0.7.5
						
							frozenleaves:v0.7.4
						
							frozenleaves:v0.7.3
						
							frozenleaves:v0.7.2
						
							frozenleaves:v0.7.1
						
							frozenleaves:v0.7.0
						
							frozenleaves:v0.6.0
						
							frozenleaves:v0.5.0
						
							frozenleaves:v0.4.7
						
							frozenleaves:v0.4.6
						
							frozenleaves:v0.4.5
						
							frozenleaves:v0.4.4
						
							frozenleaves:v0.4.3
						
							frozenleaves:v0.4.2
						
							frozenleaves:v0.4.1
						
							frozenleaves:v0.4.0
						
							frozenleaves:v0.3.1
						
							frozenleaves:v0.3.0
						
							frozenleaves:v0.2.1
						
							frozenleaves:v0.2.0
						
						
						
						
					
				...
			
					compare: frozenleaves:v0.4.0
					
				
				
						
							frozenleaves:openenv-docs-improvement
						
							frozenleaves:docs/move-multi-adapter-rl
						
							frozenleaves:main
						
							frozenleaves:docs/update-peft-integration
						
							frozenleaves:refactor/move-judges-to-experimental
						
							frozenleaves:refactor/move-mergekit-to-experimental
						
							frozenleaves:docs/remove-outdated-notebooks
						
							frozenleaves:docs/unify-trl-lib-namespace
						
							frozenleaves:docs/add-peft-to-reducing-memory
						
							frozenleaves:docs/expand-training-customization
						
							frozenleaves:docs/extend-cli-examples
						
							frozenleaves:doc/update-alst-ulysses-docs
						
							frozenleaves:tool-call-finally
						
							frozenleaves:py3.14
						
							frozenleaves:fix-test-vlm
						
							frozenleaves:gold-2
						
							frozenleaves:qgallouedec-env
						
							frozenleaves:ci-test-dev
						
							frozenleaves:copilot/fix-typo-in-text
						
							frozenleaves:iiger-mean-acc
						
							frozenleaves:openenv-integration
						
							frozenleaves:remove-fsdp1-support
						
							frozenleaves:v0.24-release
						
							frozenleaves:sft-video
						
							frozenleaves:refactor-dpo
						
							frozenleaves:chatml-collator-fix
						
							frozenleaves:remove-best-of-n-sampler
						
							frozenleaves:online-dpo-ben
						
							frozenleaves:max-length-docs
						
							frozenleaves:fix-dbrx
						
							frozenleaves:v0.23-release
						
							frozenleaves:tool-call
						
							frozenleaves:multi-turn
						
							frozenleaves:faster-ci
						
							frozenleaves:internvl-grpo-issue-4061
						
							frozenleaves:rear
						
							frozenleaves:lewtun-patch-1
						
							frozenleaves:support-reward-refactor
						
							frozenleaves:update-paper-index
						
							frozenleaves:v0.22-release
						
							frozenleaves:simplify-data-collator
						
							frozenleaves:liger-orpo
						
							frozenleaves:dist-ci
						
							frozenleaves:v0.21-release
						
							frozenleaves:feature/sglang-integration
						
							frozenleaves:dynamic_temp
						
							frozenleaves:update-for-cb
						
							frozenleaves:v0.20-release
						
							frozenleaves:v0.19-release
						
							frozenleaves:gkd-vllm
						
							frozenleaves:vllm-spec-dec
						
							frozenleaves:v0.18-release
						
							frozenleaves:grpo-per-batch-padding
						
							frozenleaves:gkd-cb
						
							frozenleaves:grpo-ssr-replay-buffer
						
							frozenleaves:grpo-log-entropy
						
							frozenleaves:grpo-adv-replay-buffer
						
							frozenleaves:vllm-fp8
						
							frozenleaves:add-entropy
						
							frozenleaves:v0.17-release
						
							frozenleaves:grpo-dapo-dyn-samp
						
							frozenleaves:grpo-mega-batch
						
							frozenleaves:log-correct_incorrect_length
						
							frozenleaves:v0.16-release
						
							frozenleaves:grpo-vllm-logprobs
						
							frozenleaves:static-cache-grpo
						
							frozenleaves:v0.15-release
						
							frozenleaves:tpo
						
							frozenleaves:agents
						
							frozenleaves:v0.14-release
						
							frozenleaves:prime
						
							frozenleaves:v0.13-release
						
							frozenleaves:v0.12-release
						
							frozenleaves:cloud-trainer
						
							frozenleaves:prm-trainer-qgallouedec
						
							frozenleaves:score
						
							frozenleaves:v0.11-release
						
							frozenleaves:v0.10-release
						
						
						
						
					
					
						
							frozenleaves:v0.24.0
						
							frozenleaves:v0.23.1
						
							frozenleaves:v0.23.0
						
							frozenleaves:v0.22.2
						
							frozenleaves:v0.22.1
						
							frozenleaves:v0.22.0
						
							frozenleaves:v0.21.0
						
							frozenleaves:v0.20.0
						
							frozenleaves:v0.19.1
						
							frozenleaves:v0.19.0
						
							frozenleaves:v0.18.2
						
							frozenleaves:v0.18.1
						
							frozenleaves:v0.18.0
						
							frozenleaves:v0.17.0
						
							frozenleaves:v0.16.1
						
							frozenleaves:v0.16.0
						
							frozenleaves:v0.15.2
						
							frozenleaves:v0.15.1
						
							frozenleaves:v0.15.0
						
							frozenleaves:v0.14.0
						
							frozenleaves:v0.13.0
						
							frozenleaves:v0.12.2
						
							frozenleaves:v0.12.1
						
							frozenleaves:v0.12.0
						
							frozenleaves:v0.11.4
						
							frozenleaves:v0.11.3
						
							frozenleaves:v0.11.2
						
							frozenleaves:v0.11.1
						
							frozenleaves:v0.11.0
						
							frozenleaves:v0.10.1
						
							frozenleaves:v0.10
						
							frozenleaves:v0.9.6
						
							frozenleaves:v0.9.4
						
							frozenleaves:v0.9.3
						
							frozenleaves:v0.8.6
						
							frozenleaves:v0.8.5
						
							frozenleaves:v0.8.4
						
							frozenleaves:v0.8.3
						
							frozenleaves:v0.8.2
						
							frozenleaves:v0.8.1
						
							frozenleaves:v0.8.0
						
							frozenleaves:v0.7.11
						
							frozenleaves:v0.7.10
						
							frozenleaves:v0.7.9
						
							frozenleaves:v0.7.8
						
							frozenleaves:v0.7.7
						
							frozenleaves:v0.7.6
						
							frozenleaves:v0.7.5
						
							frozenleaves:v0.7.4
						
							frozenleaves:v0.7.3
						
							frozenleaves:v0.7.2
						
							frozenleaves:v0.7.1
						
							frozenleaves:v0.7.0
						
							frozenleaves:v0.6.0
						
							frozenleaves:v0.5.0
						
							frozenleaves:v0.4.7
						
							frozenleaves:v0.4.6
						
							frozenleaves:v0.4.5
						
							frozenleaves:v0.4.4
						
							frozenleaves:v0.4.3
						
							frozenleaves:v0.4.2
						
							frozenleaves:v0.4.1
						
							frozenleaves:v0.4.0
						
							frozenleaves:v0.3.1
						
							frozenleaves:v0.3.0
						
							frozenleaves:v0.2.1
						
							frozenleaves:v0.2.0
						
						
						
						
					
				These branches are equal.