🤝 Open to Collab

AbstractPhila PRO

AbstractPhil

AbstractPowered

·

https://civitai.com/user/AbstractPhila

AbstractEyes

AI & ML interests

datasets, research papers, experimentation, vision, classification, text encoders, tokenization, llms, diffusion, distillation, and more.

Recent Activity

repliedto their post about 3 hours ago

Say hello to the symbolic image thought preparation line. These models are built specifically to extract meaningfully formatted image text-to-thought layering behavior for experimentation. The Qwen 3.5 line, dubbed Lucia Full Finetunes: * 0.8b https://huggingface.co/AbstractPhil/qwen3.5-0.8b-think-symbolic-image-full * 2b https://huggingface.co/AbstractPhil/qwen3.5-2b-think-symbolic-image-full * 4b https://huggingface.co/AbstractPhil/qwen3.5-4b-think-symbolic-image-full Loras: * 0.8b https://huggingface.co/AbstractPhil/qwen3.5-0.8b-think-symbolic-image * 2b https://huggingface.co/AbstractPhil/qwen3.5-2b-think-symbolic-image * 4b https://huggingface.co/AbstractPhil/qwen3.5-4b-think-symbolic-image * 9b https://huggingface.co/AbstractPhil/qwen3.5-9b-think-symbolic-image The Gemma-4 line dubbed Ulisse Loras: * e4b https://huggingface.co/AbstractPhil/gemma-4-e4b-think-symbolic-image * 12b https://huggingface.co/AbstractPhil/gemma-4-12b-think-symbolic-image Additional Experimental Models, unnamed for now. * Phi-4-reasoning-vision 15b https://huggingface.co/AbstractPhil/phi-4-reasoning-vision-15b-think-symbolic-image * Ministral 3 14b https://huggingface.co/AbstractPhil/ministral-3-14b-think-symbolic-image * Molmo2-O-7b https://huggingface.co/AbstractPhil/molmo2-o-7b-think-symbolic-image * North-Micro-Vision 2.5b https://huggingface.co/AbstractPhil/north-micro-vision-think-symbolic-image * GLM-4.6V-Flash 10b https://huggingface.co/AbstractPhil/glm-4.6v-flash-think-symbolic-image Each are specifically finetuned or lora created with the same behavior to extract different information and different opinions from images based on the schema. This is specifically designed to extract a wide array of thought processing information from many models rather than a few or a single model. All licenses and datasets will be accounted for appropriately as extractions and models are catalogued and trained.

published a dataset about 12 hours ago

AbstractPhil/ffhq-recaptioned

updated a dataset about 18 hours ago

AbstractPhil/ffhq-recaptioned

View all activity

Organizations

AbstractPhil 's collections 10