LoRA adapters, full fine-tuned checkpoints, and SFT warmup models trained with RLVR in the recursive language model depth-1 harness.
Lorenzo
lsteno
AI & ML interests
None yet
Recent Activity
liked a dataset 8 days ago
Seldon-Technologies/golden-vault-v0 updated a collection 10 days ago
Qwen 3 4B RLM RLVR liked a Space 12 days ago
HuggingFaceFW/finephraseOrganizations
