Niels Geens 0e2cca2e4f Fixed QwQ tokenizer

2025-04-04 08:54:06 +00:00

..

__init__.py

WIP Simplify training

2025-03-24 10:53:51 +00:00

dataset.py

WIP QwQ train

2025-03-24 15:46:54 +00:00

mistral_api.py

wip deepseek r1

2025-03-02 22:01:24 +01:00

qwq_train.ipynb

Converted QwQ notebooks to .py files

2025-04-01 10:42:54 +02:00

qwq.py

Fixed QwQ tokenizer

2025-04-04 08:54:06 +00:00