thejaminator
/

1e-5_test_scripts-step-50

Text Generation

Model card Files Files and versions

1e-5_test_scripts-step-50 / README.md

thejaminator's picture

verl GRPO trained model at step 50

e79d8eb verified 11 months ago

|

History Blame Contribute Delete

155 Bytes

	---
	base_model: thejaminator/checkpoints_multiple_datasets_layer_1_decoder-fixed
	library_name: peft
	tags:
	- lora
	- peft
	pipeline_tag: text-generation
	---