models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3.5-4B-full_turn_referencegame_player1Qwen3.5-4B-full_turn_referencegame_player2qwen2_5_3b_uid_reference_lr3e6_step2qwen2_5_3b_uid_reference_lr3e6_step4Grug-67B-A2B-Antidoom-RLVR1-Reference-KL-Step20-2026.10.04oasst-pythia-12b-referencephi-4-openalex-with-referencesfabrique-reference-2fabrique-reference-2.1contamination-models-arc-meta-llama-Llama-3.2-1B-Instruct-no-referencem2-reference-modelmamba-2.8b-squad-reference-taskmistral-7b-reference-instruction1qwen2.5-32b-openalex-with-references-20250131-v2mistral-7b-reference-instruction2all-online-lr-2_65e-6_intermediate_as_reference_restartQwen3.5-4B-referencegame2gemma-2b-squad-reference-taskmistral-7b-reference100kdpo_reference_modelall-online-lr-5e-7-base-as-reference_555134_1738169111_update_401mistral-7b-reference-instruction3DPO_ReferenceQwen3.5-4B-referencegame1unsloth-gemma-7b-bnb-4bit-reference_modelall_online_responses_intermediate_as_reference_modelall_online_responses_intermediate_as_reference_model_iter_2_total_episodes_60K_update_201reference_modelsft-with-reference-Llama-2-7b-hfmistral-7b-reference100k-density1