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-Reader-CoT-Llama-3-8B-InstructHotpotQA-Paragraph-Retriever-Llama-3-8B-InstructHotpotQA-OneStep-Retriever-Llama-3-8B-InstructHotpotQA-Reader-Llama-3-8B-InstructHotpotQA-Sentence-Retriever-Llama-3-8B-InstructHotpotQA-Reader-Llama-3-70B-Instruct7b-planner-1.5b-reranker-nq-hotpotqa-filtered-tp-rerankerqwen2.5-hotpotqa-sft-300BART-large-HotpotQA-finetuneMiniCPM-2B-RAFT-lora-hotpotqa-devQwen2.5-7B-Instruct-HotpotQA-Finetuned-10000hotpotqa3b-planner-1.5b-reranker-nq-hotpotqa-filtered-tp-rerankerllama3-8B-hotpotqa-raftHotpotQA_RAFT_devbart-large-hotpotqa-finetune-qgQwen2.5-7B-Instruct-HotpotQA-Abstention-10000-80-20tinyllama-task191_hotpotqa_question_generation-v1HotpotQA_train_Llama3_v1.1Llama2_finetune_hotpotqaQwen2.5-7B-RLHF-HotpotQAhotpotqa-qwen3-4bmash_hotpotqa_mash_otcmash_hotpotqa_otcHotpotQA_train_v1.1mash_hotpotqa_afh_multisamplemash_hotpotqa_dpoQwen2.5-7B-Instruct-HotpotQA-Abstention-CoT-10000qwen_hotpotqa_naive_sftmash_hotpotqa_afh_absolute