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.
Ornith-1.5-35B-A3B-fixed-mtp-NInferOrnith-1.5-35B-A3B-oQ4e-fixed-mtpOrnith-1.5-35B-A3B-oQ6e-fixed-mtpOrnith-1.5-35B-A3B-oQ8e-fixed-mtpNanonets-OCR2-3B-4bit-fixedtheworld-spatial-channel-justprojection-fixed-mlpFlorence-2-DocLayNet-FixedQwen3.8-27B-MXFP8-CRACK-conv1d-fixedQwen2.5-VL-7B-Instruct-8bit-fixed-configQwen3-VL-8B-VQA-IPAD-FIXED_RLgot-ocr-2-0-fixederpo-qwen25-vl-oom-fixedgemma-spatial-bbox-fixedQwen3-VL-30B-A3B-Thinking-patched-v2-fixed2-hereticdonut-base-sroie-metrics-combined-new-fixed-versionl4-scout-linearized-nf4-fixedvijayawada-traffic-accessibility-v2-fixedpaligemma2-3b-pt-224-sft-lora-vamos_10pct_gpt5_mini_fixedgranite-docling-258m-fixedsb_v4_fixed_1_epochmultilingual_llama_final_fixedMolmo-72B-0924-nf4-fixedQwen2.5-VL-3B-GRPO-Jigsaw-2x2-Marked-FixedLvdist-Ep50-Step500greedy_Q_fixedgreedy_Q_fixed_overfitgreedy_Q_fixed_new_overfitenglish_translated_llama_final_fixedpointing_demo_fixed_adapter_script-uploadPrometheus_Qwen_4bit_QLoRA_fixed_label_Merged
