SmolFactory

Sleeping

28.4 kB

Ctrl+K

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 10 months ago

train.py

7.21 kB
adds sft , quantization, better readmes 11 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 10 months ago