natesgituser/SmolFactory at 598357a7d8a087543477f0aac96b9910dc8dbbef

28.4 kB

3 contributors

improves launcher with model family and defaults based on options, updates trl trainer , removes trl config paths by switching to trainingarguments class , tokenizer parameters updated to sfttrainer , resolves evaluation_strategy error

598357a 5 months ago

train.py

7.21 kB

adds sft , quantization, better readmes 6 months ago
train_gpt_oss.py

21.2 kB

improves launcher with model family and defaults based on options, updates trl trainer , removes trl config paths by switching to trainingarguments class , tokenizer parameters updated to sfttrainer , resolves evaluation_strategy error 5 months ago