├── .devcontainer ├── Dockerfile └── devcontainer.json ├── .github ├── ISSUE_TEMPLATE │ ├── bug_report.yml │ ├── documentation.yml │ └── feature_request.yml └── workflows │ ├── build.yml │ └── code_quality.yml ├── .gitignore ├── .pre-commit-config.yaml ├── .readthedocs.yml ├── README.md ├── configs ├── accelerate │ ├── ddp.yaml │ ├── zero2-bf16.yaml │ ├── zero2-fp16.yaml │ └── zero3.yaml ├── nemo_configs │ ├── megatron_1.3b.yaml │ ├── megatron_20b.yaml │ ├── megatron_2b.yaml │ ├── megatron_65b.yaml │ └── sft_megatron_20b.yaml ├── sweeps │ ├── ilql_sweep.yml │ └── ppo_sweep.yml └── test_config.yml ├── docs ├── Makefile ├── make.bat ├── requirements.txt └── source │ ├── conf.py │ ├── configs.rst │ ├── data.rst │ ├── examples.rst │ ├── index.rst │ ├── pipeline.rst │ └── trainer.rst ├── examples ├── figures │ ├── mmlu_rl1.png │ ├── mmlu_rl2.png │ ├── mmlu_rm1.png │ ├── mmlu_rm2.png │ ├── mmlu_rm_legend.png │ ├── mmlu_sft1.png │ ├── mmlu_sft2.png │ ├── triviaqa_rl1.png │ ├── triviaqa_rl2.png │ ├── triviaqa_rm1.png │ ├── triviaqa_rm2.png │ ├── triviaqa_sft1.png │ ├── triviaqa_sft2.png │ ├── triviaqa_sft3.png │ ├── wikibios_false.png │ ├── wikibios_legend.png │ ├── wikibios_rewards.png │ ├── wikibios_true.png │ ├── wikiplots_false.png │ ├── wikiplots_rewards.png │ └── wikiplots_true.png ├── mmlu_eval.py ├── mmlu_eval_rm.py ├── mmlu_plot.ipynb ├── mmlu_ppo.py ├── mmlu_rm.py ├── mmlu_sft.py ├── scripts │ ├── get_factscore.py │ └── merge_peft.py ├── triviaqa_eval.py ├── triviaqa_eval_rm.py ├── triviaqa_plot.ipynb ├── triviaqa_ppo.py ├── triviaqa_rm.py ├── triviaqa_sft.py ├── wikibios_eval.py ├── wikibios_eval_rm.py ├── wikibios_plot.ipynb ├── wikibios_ppo.py ├── wikibios_rm.py ├── wikibios_sft.py ├── wikiplots_eval.py ├── wikiplots_eval_rm.py ├── wikiplots_plot.ipynb ├── wikiplots_ppo.py ├── wikiplots_rm.py └── wikiplots_sft.py ├── pyproject.toml ├── requirements.txt ├── scripts ├── accelerate_train_example.sh ├── benchmark.sh ├── slurm_train.sh └── sweep-cw.sh ├── setup.cfg ├── setup.py ├── tests ├── __init__.py ├── test_configs.py ├── test_minibatch.py ├── test_models.py ├── test_peft.py ├── test_pipelines.py ├── test_trainers.py └── test_utils.py └── trlx ├── __init__.py ├── data ├── __init__.py ├── accelerate_base_datatypes.py ├── configs.py ├── default_configs.py ├── ilql_types.py ├── method_configs.py └── ppo_types.py ├── models ├── README.md ├── __init__.py ├── modeling_base.py ├── modeling_classifier.py ├── modeling_ilql.py ├── modeling_nemo_ilql.py ├── modeling_nemo_ppo.py ├── modeling_nemo_sft.py ├── modeling_ppo.py └── modeling_rm.py ├── pipeline ├── __init__.py ├── offline_pipeline.py └── ppo_pipeline.py ├── reference.py ├── sweep.py ├── trainer ├── __init__.py ├── accelerate_base_trainer.py ├── accelerate_ilql_trainer.py ├── accelerate_ppo_trainer.py ├── accelerate_sft_trainer.py ├── nemo_ilql_trainer.py ├── nemo_ppo_trainer.py └── nemo_sft_trainer.py ├── trlx.py └── utils ├── __init__.py ├── loading.py ├── logging.py └── modeling.py /.devcontainer/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.devcontainer/Dockerfile -------------------------------------------------------------------------------- /.devcontainer/devcontainer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.devcontainer/devcontainer.json -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug_report.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.github/ISSUE_TEMPLATE/bug_report.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/documentation.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.github/ISSUE_TEMPLATE/documentation.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.github/ISSUE_TEMPLATE/feature_request.yml -------------------------------------------------------------------------------- /.github/workflows/build.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.github/workflows/build.yml -------------------------------------------------------------------------------- /.github/workflows/code_quality.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.github/workflows/code_quality.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /.readthedocs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/.readthedocs.yml -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/README.md -------------------------------------------------------------------------------- /configs/accelerate/ddp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/accelerate/ddp.yaml -------------------------------------------------------------------------------- /configs/accelerate/zero2-bf16.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/accelerate/zero2-bf16.yaml -------------------------------------------------------------------------------- /configs/accelerate/zero2-fp16.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/accelerate/zero2-fp16.yaml -------------------------------------------------------------------------------- /configs/accelerate/zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/accelerate/zero3.yaml -------------------------------------------------------------------------------- /configs/nemo_configs/megatron_1.3b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/nemo_configs/megatron_1.3b.yaml -------------------------------------------------------------------------------- /configs/nemo_configs/megatron_20b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/nemo_configs/megatron_20b.yaml -------------------------------------------------------------------------------- /configs/nemo_configs/megatron_2b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/nemo_configs/megatron_2b.yaml -------------------------------------------------------------------------------- /configs/nemo_configs/megatron_65b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/nemo_configs/megatron_65b.yaml -------------------------------------------------------------------------------- /configs/nemo_configs/sft_megatron_20b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/nemo_configs/sft_megatron_20b.yaml -------------------------------------------------------------------------------- /configs/sweeps/ilql_sweep.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/sweeps/ilql_sweep.yml -------------------------------------------------------------------------------- /configs/sweeps/ppo_sweep.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/sweeps/ppo_sweep.yml -------------------------------------------------------------------------------- /configs/test_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/configs/test_config.yml -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/make.bat -------------------------------------------------------------------------------- /docs/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/requirements.txt -------------------------------------------------------------------------------- /docs/source/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/source/conf.py -------------------------------------------------------------------------------- /docs/source/configs.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/source/configs.rst -------------------------------------------------------------------------------- /docs/source/data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/source/data.rst -------------------------------------------------------------------------------- /docs/source/examples.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/source/examples.rst -------------------------------------------------------------------------------- /docs/source/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/source/index.rst -------------------------------------------------------------------------------- /docs/source/pipeline.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/source/pipeline.rst -------------------------------------------------------------------------------- /docs/source/trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/docs/source/trainer.rst -------------------------------------------------------------------------------- /examples/figures/mmlu_rl1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/mmlu_rl1.png -------------------------------------------------------------------------------- /examples/figures/mmlu_rl2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/mmlu_rl2.png -------------------------------------------------------------------------------- /examples/figures/mmlu_rm1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/mmlu_rm1.png -------------------------------------------------------------------------------- /examples/figures/mmlu_rm2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/mmlu_rm2.png -------------------------------------------------------------------------------- /examples/figures/mmlu_rm_legend.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/mmlu_rm_legend.png -------------------------------------------------------------------------------- /examples/figures/mmlu_sft1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/mmlu_sft1.png -------------------------------------------------------------------------------- /examples/figures/mmlu_sft2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/mmlu_sft2.png -------------------------------------------------------------------------------- /examples/figures/triviaqa_rl1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/triviaqa_rl1.png -------------------------------------------------------------------------------- /examples/figures/triviaqa_rl2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/triviaqa_rl2.png -------------------------------------------------------------------------------- /examples/figures/triviaqa_rm1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/triviaqa_rm1.png -------------------------------------------------------------------------------- /examples/figures/triviaqa_rm2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/triviaqa_rm2.png -------------------------------------------------------------------------------- /examples/figures/triviaqa_sft1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/triviaqa_sft1.png -------------------------------------------------------------------------------- /examples/figures/triviaqa_sft2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/triviaqa_sft2.png -------------------------------------------------------------------------------- /examples/figures/triviaqa_sft3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/triviaqa_sft3.png -------------------------------------------------------------------------------- /examples/figures/wikibios_false.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/wikibios_false.png -------------------------------------------------------------------------------- /examples/figures/wikibios_legend.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/wikibios_legend.png -------------------------------------------------------------------------------- /examples/figures/wikibios_rewards.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/wikibios_rewards.png -------------------------------------------------------------------------------- /examples/figures/wikibios_true.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/wikibios_true.png -------------------------------------------------------------------------------- /examples/figures/wikiplots_false.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/wikiplots_false.png -------------------------------------------------------------------------------- /examples/figures/wikiplots_rewards.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/wikiplots_rewards.png -------------------------------------------------------------------------------- /examples/figures/wikiplots_true.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/figures/wikiplots_true.png -------------------------------------------------------------------------------- /examples/mmlu_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/mmlu_eval.py -------------------------------------------------------------------------------- /examples/mmlu_eval_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/mmlu_eval_rm.py -------------------------------------------------------------------------------- /examples/mmlu_plot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/mmlu_plot.ipynb -------------------------------------------------------------------------------- /examples/mmlu_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/mmlu_ppo.py -------------------------------------------------------------------------------- /examples/mmlu_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/mmlu_rm.py -------------------------------------------------------------------------------- /examples/mmlu_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/mmlu_sft.py -------------------------------------------------------------------------------- /examples/scripts/get_factscore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/scripts/get_factscore.py -------------------------------------------------------------------------------- /examples/scripts/merge_peft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/scripts/merge_peft.py -------------------------------------------------------------------------------- /examples/triviaqa_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/triviaqa_eval.py -------------------------------------------------------------------------------- /examples/triviaqa_eval_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/triviaqa_eval_rm.py -------------------------------------------------------------------------------- /examples/triviaqa_plot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/triviaqa_plot.ipynb -------------------------------------------------------------------------------- /examples/triviaqa_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/triviaqa_ppo.py -------------------------------------------------------------------------------- /examples/triviaqa_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/triviaqa_rm.py -------------------------------------------------------------------------------- /examples/triviaqa_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/triviaqa_sft.py -------------------------------------------------------------------------------- /examples/wikibios_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikibios_eval.py -------------------------------------------------------------------------------- /examples/wikibios_eval_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikibios_eval_rm.py -------------------------------------------------------------------------------- /examples/wikibios_plot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikibios_plot.ipynb -------------------------------------------------------------------------------- /examples/wikibios_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikibios_ppo.py -------------------------------------------------------------------------------- /examples/wikibios_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikibios_rm.py -------------------------------------------------------------------------------- /examples/wikibios_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikibios_sft.py -------------------------------------------------------------------------------- /examples/wikiplots_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikiplots_eval.py -------------------------------------------------------------------------------- /examples/wikiplots_eval_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikiplots_eval_rm.py -------------------------------------------------------------------------------- /examples/wikiplots_plot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikiplots_plot.ipynb -------------------------------------------------------------------------------- /examples/wikiplots_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikiplots_ppo.py -------------------------------------------------------------------------------- /examples/wikiplots_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikiplots_rm.py -------------------------------------------------------------------------------- /examples/wikiplots_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/examples/wikiplots_sft.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/pyproject.toml -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/accelerate_train_example.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/scripts/accelerate_train_example.sh -------------------------------------------------------------------------------- /scripts/benchmark.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/scripts/benchmark.sh -------------------------------------------------------------------------------- /scripts/slurm_train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/scripts/slurm_train.sh -------------------------------------------------------------------------------- /scripts/sweep-cw.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/scripts/sweep-cw.sh -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/setup.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/test_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/tests/test_configs.py -------------------------------------------------------------------------------- /tests/test_minibatch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/tests/test_minibatch.py -------------------------------------------------------------------------------- /tests/test_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/tests/test_models.py -------------------------------------------------------------------------------- /tests/test_peft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/tests/test_peft.py -------------------------------------------------------------------------------- /tests/test_pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/tests/test_pipelines.py -------------------------------------------------------------------------------- /tests/test_trainers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/tests/test_trainers.py -------------------------------------------------------------------------------- /tests/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/tests/test_utils.py -------------------------------------------------------------------------------- /trlx/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/__init__.py -------------------------------------------------------------------------------- /trlx/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/data/__init__.py -------------------------------------------------------------------------------- /trlx/data/accelerate_base_datatypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/data/accelerate_base_datatypes.py -------------------------------------------------------------------------------- /trlx/data/configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/data/configs.py -------------------------------------------------------------------------------- /trlx/data/default_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/data/default_configs.py -------------------------------------------------------------------------------- /trlx/data/ilql_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/data/ilql_types.py -------------------------------------------------------------------------------- /trlx/data/method_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/data/method_configs.py -------------------------------------------------------------------------------- /trlx/data/ppo_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/data/ppo_types.py -------------------------------------------------------------------------------- /trlx/models/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/models/README.md -------------------------------------------------------------------------------- /trlx/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /trlx/models/modeling_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/models/modeling_base.py -------------------------------------------------------------------------------- /trlx/models/modeling_classifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/models/modeling_classifier.py -------------------------------------------------------------------------------- /trlx/models/modeling_ilql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/models/modeling_ilql.py -------------------------------------------------------------------------------- /trlx/models/modeling_nemo_ilql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/models/modeling_nemo_ilql.py -------------------------------------------------------------------------------- /trlx/models/modeling_nemo_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/models/modeling_nemo_ppo.py -------------------------------------------------------------------------------- /trlx/models/modeling_nemo_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/models/modeling_nemo_sft.py -------------------------------------------------------------------------------- /trlx/models/modeling_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/models/modeling_ppo.py -------------------------------------------------------------------------------- /trlx/models/modeling_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/models/modeling_rm.py -------------------------------------------------------------------------------- /trlx/pipeline/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/pipeline/__init__.py -------------------------------------------------------------------------------- /trlx/pipeline/offline_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/pipeline/offline_pipeline.py -------------------------------------------------------------------------------- /trlx/pipeline/ppo_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/pipeline/ppo_pipeline.py -------------------------------------------------------------------------------- /trlx/reference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/reference.py -------------------------------------------------------------------------------- /trlx/sweep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/sweep.py -------------------------------------------------------------------------------- /trlx/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/trainer/__init__.py -------------------------------------------------------------------------------- /trlx/trainer/accelerate_base_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/trainer/accelerate_base_trainer.py -------------------------------------------------------------------------------- /trlx/trainer/accelerate_ilql_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/trainer/accelerate_ilql_trainer.py -------------------------------------------------------------------------------- /trlx/trainer/accelerate_ppo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/trainer/accelerate_ppo_trainer.py -------------------------------------------------------------------------------- /trlx/trainer/accelerate_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/trainer/accelerate_sft_trainer.py -------------------------------------------------------------------------------- /trlx/trainer/nemo_ilql_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/trainer/nemo_ilql_trainer.py -------------------------------------------------------------------------------- /trlx/trainer/nemo_ppo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/trainer/nemo_ppo_trainer.py -------------------------------------------------------------------------------- /trlx/trainer/nemo_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/trainer/nemo_sft_trainer.py -------------------------------------------------------------------------------- /trlx/trlx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/trlx.py -------------------------------------------------------------------------------- /trlx/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/utils/__init__.py -------------------------------------------------------------------------------- /trlx/utils/loading.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/utils/loading.py -------------------------------------------------------------------------------- /trlx/utils/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/utils/logging.py -------------------------------------------------------------------------------- /trlx/utils/modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/katiekang1998/llm_hallucinations/HEAD/trlx/utils/modeling.py --------------------------------------------------------------------------------