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_player2oasst-pythia-12b-referencephi-4-openalex-with-referencesfabrique-reference-2.1fabrique-reference-2m2-reference-modelcontamination-models-arc-meta-llama-Llama-3.2-1B-Instruct-no-referencemamba-2.8b-squad-reference-taskmistral-7b-reference-instruction1dpo_reference_modelzephyr-7b-dpo-referencegemma-2b-squad-reference-taskmistral-7b-reference100kmistral-7b-reference-instruction3all-online-lr-5e-7-base-as-reference_555134_1738169111_update_401llama3-reference200kmistral-7b-reference-instruction2Qwen3.5-4B-referencegame1mistral-7b-reference100k-density1DPO_Referenceunsloth-gemma-7b-bnb-4bit-reference_modelQwen3.5-4B-referencegame2llama3-8b-referencellama3.1-8b-instruct-referenceall-online-lr-5e-7-intermediate-as-reference_update_401sft-with-reference-Llama-2-7b-hfllama3.1-8b-referenceall-online-lr-2_65e-6_intermediate_as_reference_restart50-50-lr-5e-7-base-as-reference_555134_1738168330_update_401