├── README.md ├── docker ├── Dockerfile └── pip_requirements.txt └── src ├── alpha_entmax_training.py ├── evaluate_completion_alpha_entmax.sh ├── evaluate_completion_softmax.sh ├── evaluate_singletoken_alpha_entmax.sh ├── evaluate_singletoken_argmax.sh ├── evaluate_singletoken_softmax.sh ├── once_reward_pg.py ├── policy_value.py ├── run_evaluation.py ├── run_gpt2.py ├── time_reward_pg.py ├── tldr.py ├── unlikelihood.py └── utils.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/README.md -------------------------------------------------------------------------------- /docker/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/docker/Dockerfile -------------------------------------------------------------------------------- /docker/pip_requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/docker/pip_requirements.txt -------------------------------------------------------------------------------- /src/alpha_entmax_training.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/alpha_entmax_training.py -------------------------------------------------------------------------------- /src/evaluate_completion_alpha_entmax.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/evaluate_completion_alpha_entmax.sh -------------------------------------------------------------------------------- /src/evaluate_completion_softmax.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/evaluate_completion_softmax.sh -------------------------------------------------------------------------------- /src/evaluate_singletoken_alpha_entmax.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/evaluate_singletoken_alpha_entmax.sh -------------------------------------------------------------------------------- /src/evaluate_singletoken_argmax.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/evaluate_singletoken_argmax.sh -------------------------------------------------------------------------------- /src/evaluate_singletoken_softmax.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/evaluate_singletoken_softmax.sh -------------------------------------------------------------------------------- /src/once_reward_pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/once_reward_pg.py -------------------------------------------------------------------------------- /src/policy_value.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/policy_value.py -------------------------------------------------------------------------------- /src/run_evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/run_evaluation.py -------------------------------------------------------------------------------- /src/run_gpt2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/run_gpt2.py -------------------------------------------------------------------------------- /src/time_reward_pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/time_reward_pg.py -------------------------------------------------------------------------------- /src/tldr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/tldr.py -------------------------------------------------------------------------------- /src/unlikelihood.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/unlikelihood.py -------------------------------------------------------------------------------- /src/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vklabmipt/implicit-unlikelihood-training/HEAD/src/utils.py --------------------------------------------------------------------------------