CoolFace
15 results

rl-token

oof-baroomf /token-rl-artifacts0 likes95 downloads3mo agoHugging Facerabiulawal /emu3_tokenized_rl_100k0 likes31 downloads1y agoHugging FaceTokenBender /glm47-synth-v1-rl-artifacts GLM-4.7 Synth-v1 RL preservation artifacts This dataset repository is a preservation surface for historical GLM-4.7 Synth-v1 post-training artifacts. It is not the active Synth-v1 SFT corpus and must not be concatenated into training automatically. One-update RL preservation bundle Remote path: one-update-20260815/glm47-synthv1-rl-one-update-artifacts-20260815.tar.zst Successful run: glm47-synthv1-one-update-trusted-parent-tsanfix-20260815T010421Z Source VM:… See the full description on the dataset page: https://huggingface.co/datasets/TokenBender/glm47-synth-v1-rl-artifacts.0 likes31 downloads1mo agoHugging FaceTokenBender /glm47-aider-cpp-rl-tasks GLM-4.7 Aider-style C++ RL tasks v2 This access-controlled package contains 253 independently authored C++ repository-editing tasks used for executable-reward post-training of GLM-4.7-Flash. These are training tasks, not official Aider or Exercism benchmark tasks. The official 26-task Aider C++ evaluation set is not included and remains evaluation-only. The package proves zero official task-ID overlap. Each task provides an Aider whole-file-edit prompt, starter repository… See the full description on the dataset page: https://huggingface.co/datasets/TokenBender/glm47-aider-cpp-rl-tasks.text-generation0 likes6 downloads2mo agoHugging Facerabiulawal /emu3_tokenized_rl0 likes2 downloads1y agoHugging FaceTokenBender /glm47-aider-rl-v3-rollouts-202607220 likes2 downloads2mo agoHugging Face