Files

Keith Stevens 985819d89b Add a chat_template prompt strategy for DPO (#1725 )

* Implementing a basic chat_template strategy for DPO datasets

This mimics the sft chat_template strategy such that users can:
* Specify the messages field
* Specify the per message role and content fields
* speicfy the chosen and rejected fields
* Let the tokenizer construct the raw prompt
* Ensure the chosen and rejected fields don't have any prefix tokens

* Adding additional dpo chat template unittests

* Rename test class

2024-07-21 09:10:42 -04:00

fft-8b.yaml

bump transformers and set roundup_power2_divisions for more VRAM improvements, low bit ao optimizers (#1769 )

2024-07-19 00:47:07 -04:00

instruct-dpo-lora-8b.yml

Add a chat_template prompt strategy for DPO (#1725 )

2024-07-21 09:10:42 -04:00

instruct-lora-8b.yml

bump transformers and set roundup_power2_divisions for more VRAM improvements, low bit ao optimizers (#1769 )

2024-07-19 00:47:07 -04:00

lora-8b.yml

bump transformers and set roundup_power2_divisions for more VRAM improvements, low bit ao optimizers (#1769 )