satyamsaf3ai/qwen3.5-4b-guardrails-prompt-only

[balanced] step 300 | eval_loss=0.43492111563682556

(Trained with Unsloth)

(Trained with Unsloth)

(Trained with Unsloth)

(Trained with Unsloth)

Unsloth Model Card

[test] step 8 | eval_loss=0.8479433059692383

[test] step 5 | eval_loss=1.3821078538894653

initial commit