🤝 Open to Collab

AbstractPhila PRO

AbstractPhil

19 6 27

blkjack's profile picture

alcalde's profile picture

Chucho-1012's profile picture

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

updated a bucket 3 days ago

AbstractPhil/alephllm-chat-storage

updated a Space 3 days ago

AbstractPhil/alephllm-chat

updated a model 3 days ago

AbstractPhil/alephllm-mini-beatrix-training

View all activity

Organizations

AbstractPhil 's collections 9

Distillery

Distilled models.

AbstractPhil/mini-beatrix-1

Text Generation • 0.1B • Updated 5 days ago • 474
AbstractPhil/clip-vitb-mini-distilled

Image Feature Extraction • 8.93M • Updated 20 days ago • 410
AbstractPhil/captionbert-8192-v2

Feature Extraction • 58.3M • Updated 14 days ago • 240 • 1
AbstractPhil/captionbert-8192-v2-b

Feature Extraction • 58.3M • Updated 14 days ago • 109 • 1

GEOLIP Research Concepts

A series of repos dedicated to geolip research and results, some with stored weights, some without. All entirely based on the progress of geolip.

AbstractPhil/geolip-hypersphere-experiments

Updated Jun 3 • 1
AbstractPhil/svd-triton

Updated Mar 25
AbstractPhil/eigh-triton

Updated Apr 1 • 1
AbstractPhil/geolip-geometric-transformer-v1

Updated Mar 28

Prime Data

The good stuff.

AbstractPhil/diffusion-pretrain-set-ft1

Viewer • Updated Jun 23 • 1.46M • 1.96k • 1
AbstractPhil/qwen-synth-characters

Viewer • Updated Jul 3 • 61k • 106
AbstractPhil/wordnet-definitions

Viewer • Updated Sep 5, 2025 • 866k • 24 • 1
AbstractPhil/cifar100-clip-features

Viewer • Updated Sep 1, 2025 • 300k • 31

Beepers

These are Beeper-based models.

AbstractPhil/beeper-rose-v4

Text Generation • Updated Aug 25, 2025 • 13
Paused

Agents

1

Meet Beeper

💬

1

Meet beeper, the first rose trained llm!
AbstractPhil/beeper-rose-v3

Updated Aug 17, 2025 • 5
AbstractPhil/beeper-rose-v2

Updated Aug 17, 2025 • 7

Shunts

A collection of experimental shunts that work very well with the comfyui suite for tuning diffusion and removing noise.

AbstractPhil/t5-flan-base-vit-bigG-14-dual-stream-adapter

Updated May 31, 2025 • 11 • 3
AbstractPhil/bert-beatrix-2048-vit-bigG-14-dual-shunt-adapter

Updated Jun 21, 2025
AbstractPhil/bert-beatrix-2048-vit-l-14-dual-shunt-adapter

Updated Jun 19, 2025
AbstractPhil/bert-beatrix-2048-noobxl-epsilon-v11-dual-shunt-adapter

Updated Jun 25, 2025

GeoLIP

A series of useful models expert-trained using the GEOLIP distillation and constellation process.

AbstractPhil/amoe-lora

Updated Jul 21
AbstractPhil/qwen3.5-0.8b-relay-caption

Updated Jul 18
AbstractPhil/aleph-diffusion-adapters

Updated Jul 19
AbstractPhil/geolip-SVAE

Updated May 20 • 2

Flagships

My flagship models that actually work or are the best I have capable from a category currently.

AbstractPhil/Qwen3.5-0.8B-json-captioner

Image-Text-to-Text • 0.9B • Updated Jun 25 • 31
AbstractPhil/geovocab-patch-maker

Updated Feb 21 • 7
AbstractPhil/gated-david

Image Classification • Updated Nov 4, 2025
AbstractPhil/sd15-flow-lune

Text-to-Image • Updated 19 days ago • 21

Training Sets

zh-plus/tiny-imagenet

Viewer • Updated Jul 12, 2022 • 110k • 21.6k • 106

Black Sheep

The ones that didn't quite work, but are still very interesting and have their use cases nonetheless.

AbstractPhil/beeper-ascii-v1

Text Generation • Updated Aug 25, 2025
AbstractPhil/tiny-gpt-tests

27.6M • Updated Aug 17, 2025 • 11
AbstractPhil/random-captions-10m

Viewer • Updated May 16, 2025 • 100 • 40
AbstractPhil/flux-1s-generated-human-associations-10k

Preview • Updated May 16, 2025 • 21