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.
funding-parsing-lora-Qwen3.5_9B-ep2-r16-a32-distill-GLM_4.5_AirQwen3-1.7B-PhoMT-GRPO-BLEU-COMETQwen3_4B_PhoMT_GRPO_BLEU_COMETfunding-parsing-lora-Qwen3_8B-ep2-r64-a128-syntheticQwen3_1.7_PhoMT_GRPO_BLEU_COMET_r64funding-parsing-lora-Llama_3.1_8B-ep2p1-r64-a128-synthetic-twostagefunding-parsing-lora-Llama_3.1_8B-ep3-r64-a128-synthetic-funder-award-onlyfunding-extraction-llama-3.1-8b-instruct-artifact-data-mix-grpo-mixed-rewardfunding-parsing-lora-Llama_3.1_8B-instruct-ep2-r128-a32-grpofunding-parsing-lora-Llama_3.1_8B-instruct-ep2-r64-a32-grporoberta-large-lora-token-classificationfunding-parsing-lora-Llama_3.1_8B-instruct-ep1-r128-a256-v2-highfunder-lowtemp-grpofunding-parsing-lora-Llama_3.1_8B-ep1-r64-a128-non_syntheticfunding-parsing-lora-Llama_3.1_8B-ep1-r64-a128-syntheticfunding-parsing-lora-Qwen3_8B-ep2p1-r64-a128-synthetic-twostageqwen_7b_clean_comet_gnome_loraaffiliation-parsing-lora-Qwen2.5-32B-Instructroberta-large-peft-p-tuningfunding-parsing-lora-Llama_3.1_8B-ep2-r128-a256-drop01-synthetic-upsampledfunding-cleaning-qwen3-4b-lorafunding-extraction-qwen3.5-9B-non-thinking-artifact-data-mix-grpo-mixed-rewardbloomz-560m_PROMPT_TUNING_CAUSAL_LMaffiliation-parsing-lora-Qwen3-8B-distil-GLM_4.5_Air-dapo-latex