*.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text *.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text *.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text *.npy filter=lfs diff=lfs merge=lfs -text *.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text *.pickle filter=lfs diff=lfs merge=lfs -text *.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text *.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text *.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text tcod/asserts/fig1.png filter=lfs diff=lfs merge=lfs -text tcod/asserts/fig2.png filter=lfs diff=lfs merge=lfs -text tcod/asserts/fig3.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/DYN-NCCL.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/DYN-STATEDICT.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/FIXED-NCCL.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/FIXED-STATEDICT.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/RAFT_alfworld_reward_curve.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/agentscope_dapo_qwen3-4B_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/agentscope_dapo_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/agentscope_dapo_turns.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/agentscope_frozenlake_reward_bench.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/agentscope_frozenlake_reward_train.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/agentscope_gsm8k_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/agentscope_websearch_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/agentscope_websearch_turns.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/alfworld_reward_curve.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/alfworldv2_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/bench_alfworld_step.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/bench_alfworld_time.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/bench_frozenlake_step.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/config-manager.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/countdown-bench.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/data-in-labelling-page.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/data-in-projects.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/data-labelling.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/data-projects.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/email_eval_accuracy.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/email_reward_mean.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/email_rollout_accuracy.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/example_experience_replay/exp_replay_X_explore_step.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/example_experience_replay/exp_replay_X_time.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/example_experience_replay/exp_replay_model_version.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/grpo_rubric_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k-bench.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k-setup-1-explorer.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k-setup-1-trainer.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k-setup-2-explorer.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k-setup-2-trainer.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k-setup-3-explorer.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k-setup-3-trainer.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k-setup-4-explorer.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k-setup-4-trainer.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k_ruler_eval_accuracy.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k_ruler_gold_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k_ruler_judge_success.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k_ruler_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k_trainable_ruler_eval_accuracy.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k_trainable_ruler_gold_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k_trainable_ruler_judge_success.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k_trainable_ruler_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/gsm8k_trainable_ruler_reward_for_judger.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/guru-bench.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/guru_math_eval.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/mix_vlm_reward.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/opd_acc.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/opd_kl.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/opmd-curve.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/scripts-multi-plot.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/tinker-gsm8k.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/toolace_3b_response.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/toolace_3b_rewards.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/toolace_length_curve.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/toolace_reward_curve.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/trinity-architecture.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/trinity-design.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/trinity-mix.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/trinity-mode.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/trinity-multi-step-compare.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/trinity-title.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/trinity_data_process.png filter=lfs diff=lfs merge=lfs -text tcod/docs/sphinx_doc/assets/webshop_reward_curve.png filter=lfs diff=lfs merge=lfs -text