Abhay557
/

gemma-mini-code-agent

Model card Files Files and versions

gemma-mini-code-agent / train_colab.py

Commit History

Fix TRL v1.x: remove max_seq_length from SFTConfig, use processing_class

099c050
verified

Abhay557 commited on May 6

Fix: use BitsAndBytesConfig for 4-bit quantization

b5c74ac
verified

Abhay557 commited on May 6

Add Colab training script for mini coding agent

a62a06a
verified

Abhay557 commited on May 6