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.
HotpotQA-OneStep-Retriever-Llama-3-8B-Instructlact-1b-p24-1-explicit-all-one-gtcf-on-soft-z0001-step-2048lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048vigpt2-aio-mixed-one-stepppo-synthetic-one-language-100-step-2025-04-02-16-15-38ppo-synthetic-one-language-100-step-lr-1e-6-2025-04-02-16-22-36longformer-one-stepppo-synthetic-one-language-100-step-2025-04-02-15-44-14ppo-synthetic-one-language-100-step-lr-1e-6-2025-04-02-16-21-53Qwen2.5-VL-3B-GRPO-Jigsaw-2x2-Marked-Oneshot-Step800Qwen2.5-VL-3B-GRPO-Jigsaw-2x2-Marked-Oneshot-Step600gemma2-9b-merged_one_stepgemma2-9b-one_step
