06:41
2026-07-30
discuss.huggingface.co
large-language-models
Gemma 4 multi-turn greedy degeneration under a letter-level constraint
A Colab experiment with Gemma 4 12B Q4_K_M failed to reproduce the pathological collapse reported for the 31B model under a hard letter constraint with greedy decoding, suggesting the issue may be arc…