Spaces:

Dovakiins
/

qwerrwe

Build error

App Files Files Community

qwerrwe / tests

100 contributors

History: 129 commits

Ram

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

50421c8 unverified 7 months ago

core
ORPO Trainer replacement (#1551) 7 months ago
e2e
Add ORPO example and e2e test (#1572) 7 months ago
fixtures
Respect sequence_len in config for `type: llama2_chat` (#926) 12 months ago
monkeypatch
support for true batches with multipack (#1230) 10 months ago
prompt_strategies
feat: Add LLaMA-3 instruct prompt strategies for fine-tuning (#1553) 7 months ago
utils
Add shifted sparse attention (#973) [skip-ci] 10 months ago
test_data.py

2.23 kB

Fix pretraining with iterable/streaming Dataset (#556) about 1 year ago
test_datasets.py

9.84 kB

wrap prepared_ds_path in str() to avoid TypeError in fsspec package (#1548) 7 months ago
test_dict.py

3.15 kB

Pydantic 2.x cfg (#1239) 9 months ago
test_expand_mask.py

1.43 kB

Attention mask and position id fixes for packing (#285) over 1 year ago
test_freeze.py

8.91 kB

Train parameters exclusively in specific ranges (#1390) 8 months ago
test_normalize_config.py

2.66 kB

more fixes 20240228 (#1342) [skip ci] 9 months ago
test_packed_batch_sampler.py

3.32 kB

support for true batches with multipack (#1230) 10 months ago
test_packed_dataset.py

2.28 kB

Attention mask and position id fixes for packing (#285) over 1 year ago
test_packed_pretraining.py

2.7 kB

Pretrain transforms (#1261) 10 months ago
test_prompt_tokenizers.py

19.1 kB

fix broken linting (#1541) 7 months ago
test_prompters.py

4.39 kB

Attention mask and position id fixes for packing (#285) over 1 year ago
test_schedulers.py

1.72 kB

Scheduler implementation of Continual Pre-Training of Large Language Models: How to (re)warm your model? (#1273) 9 months ago
test_tokenizers.py

2.51 kB

Support for additional_special_tokens (#1221) [skip ci] 10 months ago
test_validation.py

35.4 kB

ADD: warning hub model (#1301) 7 months ago