huggingface/open-r1 issues and pull requests

#28 - Datasets for code

Issue - State: open - Opened by lewtun 13 days ago - 11 comments

#28 - Datasets for code

Issue - State: open - Opened by lewtun 13 days ago - 11 comments

#27 - fix evaluate.slurm

Pull Request - State: closed - Opened by eliebak 13 days ago

#27 - fix evaluate.slurm

Pull Request - State: closed - Opened by eliebak 13 days ago

#26 - add evaluate.slurm

Pull Request - State: closed - Opened by eliebak 13 days ago

#26 - add evaluate.slurm

Pull Request - State: closed - Opened by eliebak 13 days ago

#25 - Fix typo

Pull Request - State: closed - Opened by mrm8488 13 days ago

#25 - Fix typo

Pull Request - State: closed - Opened by mrm8488 13 days ago

#24 - Datasets for math

Issue - State: open - Opened by lewtun 13 days ago - 6 comments

#24 - Datasets for math

Issue - State: open - Opened by lewtun 13 days ago - 6 comments

#23 - How to contribute

Issue - State: open - Opened by lewtun 13 days ago - 4 comments

#23 - How to contribute

Issue - State: open - Opened by lewtun 13 days ago - 4 comments

#23 - How to contribute

Issue - State: open - Opened by lewtun 13 days ago - 4 comments

#23 - How to contribute

Issue - State: open - Opened by lewtun 13 days ago - 4 comments

#22 - Shut up and take my GPUs

Issue - State: closed - Opened by Muhtasham 13 days ago

#22 - Shut up and take my GPUs

Issue - State: closed - Opened by Muhtasham 13 days ago

#21 - Fix passing `vLLM` server URL

Pull Request - State: closed - Opened by gabrielmbmb 13 days ago

#21 - Fix passing `vLLM` server URL

Pull Request - State: closed - Opened by gabrielmbmb 13 days ago

#20 - Copyrights

Pull Request - State: closed - Opened by qgallouedec 13 days ago

#20 - Copyrights

Pull Request - State: closed - Opened by qgallouedec 13 days ago

#19 - Fix Slurm SFT and gather Slurm scripts

Pull Request - State: closed - Opened by lewtun 13 days ago

#19 - Fix Slurm SFT and gather Slurm scripts

Pull Request - State: closed - Opened by lewtun 13 days ago

#18 - Fix eval comamnds

Pull Request - State: closed - Opened by lewtun 13 days ago

#18 - Fix eval comamnds

Pull Request - State: closed - Opened by lewtun 13 days ago

#17 - Handle error in verifier + deepspeed command

Pull Request - State: closed - Opened by qgallouedec 13 days ago

#17 - Handle error in verifier + deepspeed command

Pull Request - State: closed - Opened by qgallouedec 13 days ago

#16 - Add diagram

Pull Request - State: closed - Opened by lewtun 13 days ago

#16 - Add diagram

Pull Request - State: closed - Opened by lewtun 13 days ago

#15 - Add SFT command to the readme

Pull Request - State: closed - Opened by loubnabnl 13 days ago

#15 - Add SFT command to the readme

Pull Request - State: closed - Opened by loubnabnl 13 days ago

#14 - Add math-verify to check accuracy of completions on GRPO

Pull Request - State: closed - Opened by plaguss 13 days ago - 4 comments

#14 - Add math-verify to check accuracy of completions on GRPO

Pull Request - State: closed - Opened by plaguss 13 days ago - 4 comments

#13 - format_reward_func() error

Issue - State: closed - Opened by dhcode-cpp 13 days ago - 3 comments

#13 - format_reward_func() error

Issue - State: closed - Opened by dhcode-cpp 13 days ago - 3 comments

#12 - Wondering would consider support muli-modal

Issue - State: open - Opened by lucasjinreal 13 days ago - 5 comments

#12 - Wondering would consider support muli-modal

Issue - State: open - Opened by lucasjinreal 13 days ago - 5 comments

#11 - Evaluate GRPO vs. other RL algorithms

Issue - State: open - Opened by gerred 13 days ago - 7 comments

#11 - Evaluate GRPO vs. other RL algorithms

Issue - State: open - Opened by gerred 13 days ago - 7 comments

#10 - Fix `generate.slurm`

Pull Request - State: closed - Opened by gabrielmbmb 13 days ago

#10 - Fix `generate.slurm`

Pull Request - State: closed - Opened by gabrielmbmb 13 days ago

#9 - Add synthetic data generation script

Pull Request - State: closed - Opened by gabrielmbmb 13 days ago

#9 - Add synthetic data generation script

Pull Request - State: closed - Opened by gabrielmbmb 13 days ago

#8 - fix slurm

Pull Request - State: closed - Opened by eliebak 13 days ago

#8 - fix slurm

Pull Request - State: closed - Opened by eliebak 13 days ago

#7 - REFACTOR TO THE MAX

Pull Request - State: closed - Opened by lewtun 13 days ago

#7 - REFACTOR TO THE MAX

Pull Request - State: closed - Opened by lewtun 13 days ago

#6 - Refactor evaluation

Pull Request - State: closed - Opened by lewtun 13 days ago

#6 - Refactor evaluation

Pull Request - State: closed - Opened by lewtun 13 days ago

#5 - Improve sft

Pull Request - State: closed - Opened by eliebak 13 days ago

#5 - Improve sft

Pull Request - State: closed - Opened by eliebak 13 days ago

#4 - Adds Math-500 and AIME24 evals

Pull Request - State: closed - Opened by edbeeching 13 days ago

#3 - GRPO script

Pull Request - State: closed - Opened by qgallouedec 13 days ago

#2 - Add configs and stuff

Pull Request - State: closed - Opened by lewtun 13 days ago

#1 - Install TRL from source

Pull Request - State: closed - Opened by qgallouedec 13 days ago

GitHub / huggingface/open-r1 issues and pull requests