Qwen3-8B-Base checkpoints trained with RLCR (Brier) and GracefulRL (IDK).
Stefano Viel
steviel
·
AI & ML interests
None yet
Recent Activity
updated a collection 1 day ago
Graceful Failure LLM Qwen3-8B updated a model 1 day ago
steviel/Reliability-8B-brier-ckpt-900 published a model 1 day ago
steviel/Reliability-8B-brier-ckpt-900Organizations
