| .. |
|
generated
|
fix(rlhf): Supporting adapter only output for reward model training
|
2024-02-20 14:27:59 -08:00 |
|
__init__.py
|
chore(components): add `__init__.py` file to gcpc `_implementation/llm`
|
2023-08-20 10:36:23 -07:00 |
|
batch_prediction_pairwise.py
|
chore(components): Update component naming in AutoSxS implementation
|
2024-02-06 09:49:04 -08:00 |
|
bulk_inferrer.py
|
chore(components): Rename several `_implementation.llm` components
|
2024-02-15 16:18:27 -08:00 |
|
deploy_llm_model.py
|
chore(components): Rename several `_implementation.llm` components
|
2024-02-15 16:18:27 -08:00 |
|
deployment_graph.py
|
chore(components): Rename several `_implementation.llm` components
|
2024-02-15 16:18:27 -08:00 |
|
env.py
|
chore(components): Use new module for looking up ReFINED and AutoSxS image tags
|
2024-02-08 16:14:35 -08:00 |
|
function_based.py
|
fix(components): Only run `preview.llm.bulk_inference` after tuning third-party models with RLHF
|
2024-01-24 13:59:24 -08:00 |
|
model_evaluation_text_generation_pairwise.py
|
fix(components): Use PipelineJob location in AutoSxS components, add init file
|
2024-02-14 11:40:06 -08:00 |
|
online_evaluation_pairwise.py
|
fix(components): Use PipelineJob location in AutoSxS components, add init file
|
2024-02-14 11:40:06 -08:00 |
|
preference_data_formatter.py
|
feat(components): Add RLAIF pipeline to preview
|
2024-02-08 12:36:38 -08:00 |
|
preprocess_chat_dataset.py
|
feat(components): Add ability to tune chat model with `preview.llm.rlhf_pipeline`
|
2023-10-31 12:15:30 -07:00 |
|
private_text_comparison_importer.py
|
chore(components): Rename several `_implementation.llm` components
|
2024-02-15 16:18:27 -08:00 |
|
private_text_importer.py
|
chore(components): Rename several `_implementation.llm` components
|
2024-02-15 16:18:27 -08:00 |
|
reinforcement_learning_graph.py
|
fix(rlhf): Supporting adapter only output for reward model training
|
2024-02-20 14:27:59 -08:00 |
|
reinforcer.py
|
fix(rlhf): Supporting adapter only output for reward model training
|
2024-02-20 14:27:59 -08:00 |
|
reward_model_graph.py
|
fix(rlhf): Supporting adapter only output for reward model training
|
2024-02-20 14:27:59 -08:00 |
|
reward_model_trainer.py
|
fix(rlhf): Supporting adapter only output for reward model training
|
2024-02-20 14:27:59 -08:00 |
|
supervised_fine_tuner.py
|
chore(components): Rename several `_implementation.llm` components
|
2024-02-15 16:18:27 -08:00 |
|
upload_llm_model.py
|
chore(components): Rename several `_implementation.llm` components
|
2024-02-15 16:18:27 -08:00 |
|
upload_tensorboard_metrics.py
|
feat(components): Add LLM implementation component that uploads tensorboard metrics after training
|
2023-10-06 09:36:57 -07:00 |
|
utils.py
|
docs(components): Update AutoSxS pipeline to use "question_answering" as task name instead of "question_answer", where "question_answer" is still supported, but deprecated
|
2024-01-22 12:17:59 -08:00 |
|
utils_test.py
|
feat(components): Support scheduling and labels in utils.build_payload
|
2024-01-19 12:20:10 -08:00 |
066f229e27