├── README.md ├── data └── README.md ├── run_seq2seq_qa.py ├── tempreason_train.sh ├── trainer_seq2seq_qa.py └── trlx ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── configs ├── accelerate │ ├── ddp.yaml │ ├── zero2-bf16.yaml │ ├── zero2-fp16.yaml │ └── zero3.yaml ├── nemo_configs │ ├── megatron_20b.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 ├── __init__.py └── tsqa │ ├── __init__.py │ ├── configs │ └── ppo_config_qa.yml │ ├── eval_t5_qa.py │ └── run_t5_qa.py ├── pyproject.toml ├── requirements.txt ├── scripts ├── accelerate_train_example.sh ├── benchmark.sh ├── slurm_train.sh └── sweep-cw.sh ├── setup.cfg ├── setup.py ├── trlx.egg-info ├── PKG-INFO ├── SOURCES.txt ├── dependency_links.txt ├── requires.txt └── top_level.txt └── trlx ├── __init__.py ├── __pycache__ ├── __init__.cpython-38.pyc └── trlx.cpython-38.pyc ├── data ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-38.pyc │ ├── accelerate_base_datatypes.cpython-38.pyc │ ├── configs.cpython-38.pyc │ ├── default_configs.cpython-38.pyc │ ├── ilql_types.cpython-38.pyc │ ├── method_configs.cpython-38.pyc │ └── ppo_types.cpython-38.pyc ├── accelerate_base_datatypes.py ├── configs.py ├── default_configs.py ├── ilql_types.py ├── method_configs.py └── ppo_types.py ├── models ├── README.md ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-38.pyc │ ├── modeling_base.cpython-38.pyc │ ├── modeling_ilql.cpython-38.pyc │ └── modeling_ppo.cpython-38.pyc ├── modeling_base.py ├── modeling_ilql.py ├── modeling_nemo_ilql.py ├── modeling_nemo_sft.py └── modeling_ppo.py ├── pipeline ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-38.pyc │ ├── offline_pipeline.cpython-38.pyc │ └── ppo_pipeline.cpython-38.pyc ├── offline_pipeline.py └── ppo_pipeline.py ├── reference.py ├── sweep.py ├── trainer ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-38.pyc │ ├── accelerate_base_trainer.cpython-38.pyc │ ├── accelerate_ilql_trainer.cpython-38.pyc │ ├── accelerate_ppo_trainer.cpython-38.pyc │ ├── accelerate_sft_trainer.cpython-38.pyc │ └── nemo_ilql_trainer.cpython-38.pyc ├── accelerate_base_trainer.py ├── accelerate_ilql_trainer.py ├── accelerate_ppo_trainer.py ├── accelerate_sft_trainer.py ├── nemo_ilql_trainer.py └── nemo_sft_trainer.py ├── trlx.py └── utils ├── __init__.py ├── __pycache__ ├── __init__.cpython-38.pyc ├── loading.cpython-38.pyc ├── logging.cpython-38.pyc └── modeling.cpython-38.pyc ├── loading.py ├── logging.py └── modeling.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/README.md -------------------------------------------------------------------------------- /data/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/data/README.md -------------------------------------------------------------------------------- /run_seq2seq_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/run_seq2seq_qa.py -------------------------------------------------------------------------------- /tempreason_train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/tempreason_train.sh -------------------------------------------------------------------------------- /trainer_seq2seq_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trainer_seq2seq_qa.py -------------------------------------------------------------------------------- /trlx/CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /trlx/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/CONTRIBUTING.md -------------------------------------------------------------------------------- /trlx/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/LICENSE -------------------------------------------------------------------------------- /trlx/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/README.md -------------------------------------------------------------------------------- /trlx/configs/accelerate/ddp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/accelerate/ddp.yaml -------------------------------------------------------------------------------- /trlx/configs/accelerate/zero2-bf16.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/accelerate/zero2-bf16.yaml -------------------------------------------------------------------------------- /trlx/configs/accelerate/zero2-fp16.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/accelerate/zero2-fp16.yaml -------------------------------------------------------------------------------- /trlx/configs/accelerate/zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/accelerate/zero3.yaml -------------------------------------------------------------------------------- /trlx/configs/nemo_configs/megatron_20b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/nemo_configs/megatron_20b.yaml -------------------------------------------------------------------------------- /trlx/configs/nemo_configs/megatron_65b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/nemo_configs/megatron_65b.yaml -------------------------------------------------------------------------------- /trlx/configs/nemo_configs/sft_megatron_20b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/nemo_configs/sft_megatron_20b.yaml -------------------------------------------------------------------------------- /trlx/configs/sweeps/ilql_sweep.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/sweeps/ilql_sweep.yml -------------------------------------------------------------------------------- /trlx/configs/sweeps/ppo_sweep.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/sweeps/ppo_sweep.yml -------------------------------------------------------------------------------- /trlx/configs/test_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/configs/test_config.yml -------------------------------------------------------------------------------- /trlx/docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/Makefile -------------------------------------------------------------------------------- /trlx/docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/make.bat -------------------------------------------------------------------------------- /trlx/docs/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/requirements.txt -------------------------------------------------------------------------------- /trlx/docs/source/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/source/conf.py -------------------------------------------------------------------------------- /trlx/docs/source/configs.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/source/configs.rst -------------------------------------------------------------------------------- /trlx/docs/source/data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/source/data.rst -------------------------------------------------------------------------------- /trlx/docs/source/examples.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/source/examples.rst -------------------------------------------------------------------------------- /trlx/docs/source/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/source/index.rst -------------------------------------------------------------------------------- /trlx/docs/source/pipeline.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/source/pipeline.rst -------------------------------------------------------------------------------- /trlx/docs/source/trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/docs/source/trainer.rst -------------------------------------------------------------------------------- /trlx/examples/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /trlx/examples/tsqa/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /trlx/examples/tsqa/configs/ppo_config_qa.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/examples/tsqa/configs/ppo_config_qa.yml -------------------------------------------------------------------------------- /trlx/examples/tsqa/eval_t5_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/examples/tsqa/eval_t5_qa.py -------------------------------------------------------------------------------- /trlx/examples/tsqa/run_t5_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/examples/tsqa/run_t5_qa.py -------------------------------------------------------------------------------- /trlx/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/pyproject.toml -------------------------------------------------------------------------------- /trlx/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/requirements.txt -------------------------------------------------------------------------------- /trlx/scripts/accelerate_train_example.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/scripts/accelerate_train_example.sh -------------------------------------------------------------------------------- /trlx/scripts/benchmark.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/scripts/benchmark.sh -------------------------------------------------------------------------------- /trlx/scripts/slurm_train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/scripts/slurm_train.sh -------------------------------------------------------------------------------- /trlx/scripts/sweep-cw.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/scripts/sweep-cw.sh -------------------------------------------------------------------------------- /trlx/setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/setup.cfg -------------------------------------------------------------------------------- /trlx/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/setup.py -------------------------------------------------------------------------------- /trlx/trlx.egg-info/PKG-INFO: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx.egg-info/PKG-INFO -------------------------------------------------------------------------------- /trlx/trlx.egg-info/SOURCES.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx.egg-info/SOURCES.txt -------------------------------------------------------------------------------- /trlx/trlx.egg-info/dependency_links.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /trlx/trlx.egg-info/requires.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx.egg-info/requires.txt -------------------------------------------------------------------------------- /trlx/trlx.egg-info/top_level.txt: -------------------------------------------------------------------------------- 1 | examples 2 | trlx 3 | -------------------------------------------------------------------------------- /trlx/trlx/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/__init__.py -------------------------------------------------------------------------------- /trlx/trlx/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/__pycache__/trlx.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/__pycache__/trlx.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/__init__.py -------------------------------------------------------------------------------- /trlx/trlx/data/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/data/__pycache__/accelerate_base_datatypes.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/__pycache__/accelerate_base_datatypes.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/data/__pycache__/configs.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/__pycache__/configs.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/data/__pycache__/default_configs.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/__pycache__/default_configs.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/data/__pycache__/ilql_types.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/__pycache__/ilql_types.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/data/__pycache__/method_configs.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/__pycache__/method_configs.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/data/__pycache__/ppo_types.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/__pycache__/ppo_types.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/data/accelerate_base_datatypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/accelerate_base_datatypes.py -------------------------------------------------------------------------------- /trlx/trlx/data/configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/configs.py -------------------------------------------------------------------------------- /trlx/trlx/data/default_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/default_configs.py -------------------------------------------------------------------------------- /trlx/trlx/data/ilql_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/ilql_types.py -------------------------------------------------------------------------------- /trlx/trlx/data/method_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/method_configs.py -------------------------------------------------------------------------------- /trlx/trlx/data/ppo_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/data/ppo_types.py -------------------------------------------------------------------------------- /trlx/trlx/models/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/README.md -------------------------------------------------------------------------------- /trlx/trlx/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /trlx/trlx/models/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/models/__pycache__/modeling_base.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/__pycache__/modeling_base.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/models/__pycache__/modeling_ilql.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/__pycache__/modeling_ilql.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/models/__pycache__/modeling_ppo.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/__pycache__/modeling_ppo.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/models/modeling_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/modeling_base.py -------------------------------------------------------------------------------- /trlx/trlx/models/modeling_ilql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/modeling_ilql.py -------------------------------------------------------------------------------- /trlx/trlx/models/modeling_nemo_ilql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/modeling_nemo_ilql.py -------------------------------------------------------------------------------- /trlx/trlx/models/modeling_nemo_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/modeling_nemo_sft.py -------------------------------------------------------------------------------- /trlx/trlx/models/modeling_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/models/modeling_ppo.py -------------------------------------------------------------------------------- /trlx/trlx/pipeline/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/pipeline/__init__.py -------------------------------------------------------------------------------- /trlx/trlx/pipeline/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/pipeline/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/pipeline/__pycache__/offline_pipeline.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/pipeline/__pycache__/offline_pipeline.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/pipeline/__pycache__/ppo_pipeline.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/pipeline/__pycache__/ppo_pipeline.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/pipeline/offline_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/pipeline/offline_pipeline.py -------------------------------------------------------------------------------- /trlx/trlx/pipeline/ppo_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/pipeline/ppo_pipeline.py -------------------------------------------------------------------------------- /trlx/trlx/reference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/reference.py -------------------------------------------------------------------------------- /trlx/trlx/sweep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/sweep.py -------------------------------------------------------------------------------- /trlx/trlx/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/__init__.py -------------------------------------------------------------------------------- /trlx/trlx/trainer/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/trainer/__pycache__/accelerate_base_trainer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/__pycache__/accelerate_base_trainer.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/trainer/__pycache__/accelerate_ilql_trainer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/__pycache__/accelerate_ilql_trainer.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/trainer/__pycache__/accelerate_ppo_trainer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/__pycache__/accelerate_ppo_trainer.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/trainer/__pycache__/accelerate_sft_trainer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/__pycache__/accelerate_sft_trainer.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/trainer/__pycache__/nemo_ilql_trainer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/__pycache__/nemo_ilql_trainer.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/trainer/accelerate_base_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/accelerate_base_trainer.py -------------------------------------------------------------------------------- /trlx/trlx/trainer/accelerate_ilql_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/accelerate_ilql_trainer.py -------------------------------------------------------------------------------- /trlx/trlx/trainer/accelerate_ppo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/accelerate_ppo_trainer.py -------------------------------------------------------------------------------- /trlx/trlx/trainer/accelerate_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/accelerate_sft_trainer.py -------------------------------------------------------------------------------- /trlx/trlx/trainer/nemo_ilql_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/nemo_ilql_trainer.py -------------------------------------------------------------------------------- /trlx/trlx/trainer/nemo_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trainer/nemo_sft_trainer.py -------------------------------------------------------------------------------- /trlx/trlx/trlx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/trlx.py -------------------------------------------------------------------------------- /trlx/trlx/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/utils/__init__.py -------------------------------------------------------------------------------- /trlx/trlx/utils/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/utils/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/utils/__pycache__/loading.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/utils/__pycache__/loading.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/utils/__pycache__/logging.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/utils/__pycache__/logging.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/utils/__pycache__/modeling.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/utils/__pycache__/modeling.cpython-38.pyc -------------------------------------------------------------------------------- /trlx/trlx/utils/loading.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/utils/loading.py -------------------------------------------------------------------------------- /trlx/trlx/utils/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/utils/logging.py -------------------------------------------------------------------------------- /trlx/trlx/utils/modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DAMO-NLP-SG/TempReason/HEAD/trlx/trlx/utils/modeling.py --------------------------------------------------------------------------------