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.
qwen14b-code-trainer-v9_mixedslimder-qwen38-ream288-ngram50-mixed-recovery-qlora-v2kin-qlora-mixed-agentic-v2-lmhead-adapterqwen14b-code-trainer-v8_mixedrevbench-lora-mixedllama-scheme-mixedqwen3-32b-honesty-finetuned-mixed-honest-originalQwen3.5-4B-Base-mixed-physics-LoRA-v3qwen3-32b-honesty-finetuned-mixed-qwen-dataslmat-qwen2.5-7b-mixedpokerbench-qwen3-14b-lora-mixedqwen3-32b-honesty-finetuned-mixedqwen3-32b-honesty-finetuned-mixed-split-personalityokvqa_tag_pipeline5_6m_mixedbread_easyocr_ram_run23Qwen3.5-4B-Base-mixed-math-LoRA-v3deepseek-r1-70b-honesty-finetuned-mixed-deepseekqwen3-8b-finetune-multit-mixedada-slm-v4-mixedokvqa_tag_only_k_6m_mixedbread_run2em-debate-max-scale-mixeddeepseek-r1-70b-honesty-finetuned-mixed-qwen-datadeepseek-r1-70b-honesty-finetuned-mixed-anthropic-datafunding-extraction-llama-3.1-8b-instruct-artifact-data-mix-grpo-mixed-rewardokvqa_tag_only_k_6m_mixedbread_run3okvqa_tag_only_k_6m_mixedbread_run4qwen14b-code-trainer-v7_mixeddeepseek-r1-70b-honesty-finetuned-mixed-split-personalityqwen3-8b-lora-mixedokvqa_tag_only_k_6m_mixedbread_run1gemma4-26b-a4b-heidi-scribe-mixed-chat-template-nonthinking-lora-2epoch-32k-a100
