Hugging Face's logo

zhangzhifang
/
verl-agent

Safetensors
Model card Files
xet
 Community
verl-agent / docs /examples

Commit History

Major Update: merge latest verl (#54)
823e1b4
unverified

Lang Feng 湛露先生 AoShen Franz Srambical BaiqingL BearBiscuit HL Blue Space tongyx361 Mantas Bakšys Mert Unsal yangwang92 Patrik Bartak Junrong Lin BearBiscuit05 Leege233 sicer wuxibin shengguangming wangfuchun-fc DuCross Qunhong Zeng Dai, Weinan runluo PPPisOK hiyouga Haibin Lin pengsun000 Hunter Zhang Changlong Xiang Long zyzshishui wangyeyeye zhaochenyang20 jrlin HollowMan6 ztonyzhao icejieke lixiaoguang12 Earl St Sauver Hongpeng Guo Wang Zhang Wang Zhang Jinn yhyang201 QQSong Changlong Yu changlyu chenhaiquan yushengsu Yusheng Su none06630663 ShareLer Xiang Long Rihong Qiu Yuhua Jiang Swtheking openhands Wei Wu commited on

Merge VeRL
d9b6074

langfeng01 commited on

Megatron checkpoint default not save hf_models, and provide model merge tool. (#780)
004f536
unverified

Blue Space commited on

docs: update checkpoint doc (#800)
e067b23
unverified

Blue Space commited on

docs: doc improvements via Openhands, add SimpleRL-Zoo (#764)
26e9abd
unverified

HL commited on

docs: support AMD (Rocm Kernel) - Merge upstream changes and update AMD tutorial (#741)
8e2b545
unverified

yushengsu HL commited on

[feat] Megatron checkpoint support for current Llama and Qwen models (#687)
7fe626c
unverified

Blue Space caaatch22 uygnef sharele commited on

[config] feat: lr_warmup_steps (#564)
578b68e
unverified

tongyx361 commited on

[Config] Providing an option to turn off `torch.compile` in actor (#554)
8a74466
unverified

hongpeng-guo commited on

feat: support loading reward function from an external file (#452)
fb0f2a8
unverified

Lumeng Wu commited on

[misc] feat: make filter long prompt an option (#506)
94a4644
unverified

Guangming Sheng commited on

[docs] update logger documentation (#482)
ec6ac97
unverified

Ze-Yi LIN commited on

support speed up downloading model from modelscope (#463)
b908c6f
unverified

Hong Zhang hiyouga commited on

[Fix] Deprecate `val_batch_size` (#353)
81f021f
unverified

tongyx361 commited on

algo: Rloo advantage estimator (#341)
c1f52c2
unverified

zfwww commited on

Fix wrongs args desc . (#294)
90efe31
unverified

湛露先生 commited on

[misc] feat: support offload parameter and optimizer during rollout (#284)
49c2127
unverified

Guangming Sheng commited on

[doc] feat: update remove_padding usage in perf tuning (#264)
8b23fcf
unverified

Guangming Sheng commited on

Add stronger reward verification sandbox (#233)
b909ba2
unverified

zfwww commited on

[doc] fix document deprecated link (#235)
b6cfcbc
unverified

Guangming Sheng commited on

implement REINFORCE++ algorithm (#228)
69c3493
unverified

4332001876 commited on

example: switch the default model ckpt for Megatron, add wandb logs (#210)
8a5aa18
unverified

HL 3v324v23 commited on

docs: fixed link in gsm8k_example.rst (#200)
f27bb54
unverified

jaysonfrancis Jayson Francis commited on

fix: typo (explanation) (#167)
b39595d
unverified

Franz Srambical commited on

[BREAKING][misc] feat: change micro_batch_size to micro_batch_size_per_gpu (#136)
1b3d58f
unverified

Guangming Sheng commited on

[example] docs: improve the quickstart documentation (#56)
fcf9d9c
unverified

HL commited on

[BREAKING][refact]: move actor/critic/hybrid_engine/reward_model/rollout/workers out of ppo directory for reuse (#52)
217d69c
unverified

Guangming Sheng commited on

api: rename tracking logger to wandb logger type (#47)
0e9caad
unverified

HL commited on

[BREAKING][core] move single_controller into verl directory (#45)
ed0708b
unverified

Guangming Sheng commited on

[doc] feat: fix typo and delete deprecated config element (#2)
1829396
unverified

Peter Sheng commited on

[init] feat: upload first open source version of verl
695f5f0

shengguangming commited on