├── .gitignore ├── AI_ETHICS.md ├── CODEOWNERS ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE.txt ├── README.md ├── SECURITY.md ├── assets ├── domain_pie.png └── pretrain2rl.png ├── domain_specific_library ├── coding.jsonl ├── commerce.jsonl ├── education.jsonl ├── math.jsonl ├── medicine.jsonl ├── natural_science.jsonl ├── other.jsonl ├── social_science.jsonl ├── tech.jsonl └── travel.jsonl ├── main.py ├── main_batch.py ├── requirements.txt ├── setup.py └── webscale_rl ├── __init__.py ├── agent ├── __init__.py ├── agent.py └── batch_agent.py ├── behavior_template ├── __init__.py ├── checker.py ├── fewshot.py ├── filter.py ├── generator.py └── identifier.py ├── sampler ├── __init__.py └── fewshot_example_sampler.py └── utils ├── __init__.py ├── config.py └── misc.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/.gitignore -------------------------------------------------------------------------------- /AI_ETHICS.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/AI_ETHICS.md -------------------------------------------------------------------------------- /CODEOWNERS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/CODEOWNERS -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/LICENSE.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/README.md -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/SECURITY.md -------------------------------------------------------------------------------- /assets/domain_pie.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/assets/domain_pie.png -------------------------------------------------------------------------------- /assets/pretrain2rl.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/assets/pretrain2rl.png -------------------------------------------------------------------------------- /domain_specific_library/coding.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/coding.jsonl -------------------------------------------------------------------------------- /domain_specific_library/commerce.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/commerce.jsonl -------------------------------------------------------------------------------- /domain_specific_library/education.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/education.jsonl -------------------------------------------------------------------------------- /domain_specific_library/math.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/math.jsonl -------------------------------------------------------------------------------- /domain_specific_library/medicine.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/medicine.jsonl -------------------------------------------------------------------------------- /domain_specific_library/natural_science.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/natural_science.jsonl -------------------------------------------------------------------------------- /domain_specific_library/other.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/other.jsonl -------------------------------------------------------------------------------- /domain_specific_library/social_science.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/social_science.jsonl -------------------------------------------------------------------------------- /domain_specific_library/tech.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/tech.jsonl -------------------------------------------------------------------------------- /domain_specific_library/travel.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/domain_specific_library/travel.jsonl -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/main.py -------------------------------------------------------------------------------- /main_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/main_batch.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | openai 2 | datasets 3 | pandas 4 | tqdm -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/setup.py -------------------------------------------------------------------------------- /webscale_rl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/__init__.py -------------------------------------------------------------------------------- /webscale_rl/agent/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /webscale_rl/agent/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/agent/agent.py -------------------------------------------------------------------------------- /webscale_rl/agent/batch_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/agent/batch_agent.py -------------------------------------------------------------------------------- /webscale_rl/behavior_template/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /webscale_rl/behavior_template/checker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/behavior_template/checker.py -------------------------------------------------------------------------------- /webscale_rl/behavior_template/fewshot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/behavior_template/fewshot.py -------------------------------------------------------------------------------- /webscale_rl/behavior_template/filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/behavior_template/filter.py -------------------------------------------------------------------------------- /webscale_rl/behavior_template/generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/behavior_template/generator.py -------------------------------------------------------------------------------- /webscale_rl/behavior_template/identifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/behavior_template/identifier.py -------------------------------------------------------------------------------- /webscale_rl/sampler/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /webscale_rl/sampler/fewshot_example_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/sampler/fewshot_example_sampler.py -------------------------------------------------------------------------------- /webscale_rl/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /webscale_rl/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/utils/config.py -------------------------------------------------------------------------------- /webscale_rl/utils/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SalesforceAIResearch/PretrainRL-pipeline/HEAD/webscale_rl/utils/misc.py --------------------------------------------------------------------------------