Hamel Husain f1de29dd1e Respect sequence_len in config for type: llama2_chat (#926) ...

* Respect sequence_len in config for `type: llama2_chat`

It was hardcoded to `4096` I am not sure why?  This updates it to pull from the config. 

cc: @winglian

* Update llama2_chat.py

* apply black formatting

* fix tokenizer

* update test data

* lint fixtures

2023-12-12 09:39:22 -08:00

..

e2e

support for mamba (#915)

2023-12-09 12:10:41 -05:00

fixtures

Respect sequence_len in config for type: llama2_chat (#926)

2023-12-12 09:39:22 -08:00

monkeypatch

Attention mask and position id fixes for packing (#285)

2023-08-12 15:14:56 -04:00

test_data.py

Fix pretraining with iterable/streaming Dataset (#556)

2023-09-13 00:16:40 -04:00

test_dict.py

fix DefaultDict.__or__

2023-08-13 01:15:50 +00:00

test_expand_mask.py

Attention mask and position id fixes for packing (#285)

2023-08-12 15:14:56 -04:00

test_normalize_config.py

simplify by removing duplicate base_model_config (#772)

2023-10-23 01:42:38 -04:00

test_packed_dataset.py

Attention mask and position id fixes for packing (#285)

2023-08-12 15:14:56 -04:00

test_prompt_tokenizers.py

misc sharegpt fixes (#723)

2023-10-13 11:04:39 -04:00

test_prompters.py

Attention mask and position id fixes for packing (#285)

2023-08-12 15:14:56 -04:00

test_tokenizers.py

simplify load_tokenizer

2023-08-12 18:55:06 -07:00

test_validation.py

Feat(wandb): Refactor to be more flexible (#767)

2023-12-04 22:17:25 +09:00