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.
MinerU2.5-Pro-2605-1.2BMinerU2.5-Pro-2604-1.2BToto-Open-Base-1.0MinerU2.5-2509-1.2BMinerU-Diffusion-V1-0320-2.5BTRivia-3Bqwen-2-5-3b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v4qwen-2_5-1_5b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v4qwen-2-5-3b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v3qwen-2_5-1_5b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-vgranite-4.2-8b-openvinometa-rater-readability-ratingqwen-2_5-3b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v4qwen-2-5-3b-instruct-using-openai-gsm8k-gguf-data-enhanced-with-deepseek-v3-smallqwen-2_5-1_5b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v2qwen-2_5-1_5b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v3cyberagent-open-calm-small-kunishou-databricks-dolly-15k-ja-full-instruction-tuninggranite-3.1-1b-a400m-instruct-openvinocyberagent-open-calm-small-ToPo-ToPo-databricks-dolly-15k-ja-zundamon-full-instruction-tuningODA-Fin-RL-8Bmeta-rater-professionalism-ratingChartVerse-2Bqwen3guard-gen-4b-danger-intent-opendata-qwensynth-supplement-sampled4000-v9meta-rater-cleanliness-ratingpegasus-x-base-synthsumm_open-16kmeta-rater-reasoning-ratingsmol_llama-220M-openhermesChartVerse-4BChartVerse-8BChartVerse-Coder