Leonard 7c2bf3091f Fix llama3 chat_template (extra <|eot_id|> on last turn) (#1635) ...

* Fix llama3 chat_template (the {{eos_token}} leads to an extra <|eot_id|> being added in the last turn). Output now matches official Llama 3 Instruct model

* add tests

* chore: lint

---------

Co-authored-by: Wing Lian <wing.lian@gmail.com>

2024-05-21 09:08:53 -04:00

..

test_alpaca.py

fix broken linting (#1541)

2024-04-19 01:03:04 -04:00

test_chat_templates.py

Fix llama3 chat_template (extra <|eot_id|> on last turn) (#1635)

2024-05-21 09:08:53 -04:00

test_raw_io.py

fix broken linting (#1541)

2024-04-19 01:03:04 -04:00

test_sharegpt.py

feat: Add LLaMA-3 instruct prompt strategies for fine-tuning (#1553)

2024-05-11 00:08:04 -04:00