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.
Grug-67B-A2B-Datakit-SFT-262K-2026.09.21Grug-67B-A2B-Datakit-SFT-262K-2026.09.20Lucie-7B-Instruct-human-dataGrug-67B-A2B-Datakit-SFT-262K-2026.09.11Grug-67B-A2B-Datakit-SFT-262K-2026.09.21-dr-doomMinerU-HTMLGrug-67B-A2B-Datakit-SFT-262K-2026.09.16OpenLLM-France.Lucie-7B-Instruct-human-data-GGUFGrug-67B-A2B-Datakit-SFT-262K-2026.09.14granite-4.2-8b-openvinoGrug-67B-A2B-Datakit-SFT-262K-2026.09.17Grug-67B-A2B-Datakit-SFT-262K-2026.10.05cyberagent-open-calm-small-kunishou-databricks-dolly-15k-ja-full-instruction-tuningopendatalab.MinerU-HTML-GGUFgranite-3.1-1b-a400m-instruct-openvinocyberagent-open-calm-small-ToPo-ToPo-databricks-dolly-15k-ja-zundamon-full-instruction-tuningODA-Fin-RL-8Bmeta-rater-professionalism-ratingqwen3guard-gen-4b-danger-intent-opendata-qwensynth-supplement-sampled4000-v9smol_llama-220M-openhermesChartVerse-Coderopen-calm-large-finetuned-databricks-dollyODA-Fin-SFT-8Bqwen35-4b-danger-intent-opendata-qwensynth-79288-v5meta-rater-1b-randommeta-rater-7b-randomqwen35-4b-danger-intent-opendata-qwensynth-supplement-83787-v7meta-rater-1b-25ratersQwen3_4B_Thinking_Tuning_Data_Unsloth_OpenMathReasoning_ANd_Modotte_MathX_5M_16bitQwen2.5-1.5B-Open-R1-SFT-1_new_dataset