An 8.66M-parameter ViT image encoder (10.0% of a CLIP-B/16 image tower) producing 512-d embeddings compatible with the text tower. The primary checkpoint was distilled on CC12M (10,968,539 images) against the generalized-Procrustes consensus of five CLIP teachers — never against the deployment teacher — and carries a frozen 512×512 rotation that maps its outputs into the deployment frame, where it outperforms the student distilled directly against that teacher on every task gauge, both seeds (full tables below). The rotation is applied by default (config.applyrotation); pass applyrotation=False to getimagefeatures for the raw consensus-frame embedding. Weights are safetensors; the modeling…
Open weights
apache-2.0
9M parameters
transformers
Live training ground for AlephLLM: signed-address (aleph) language models. Code, presets, trainer, and the full test array live in the source repo — github.com/AbstractEyes/alephllm (pip install git+https://github.com/AbstractEyes/alephllm, package geolip.alephllm). This repo holds what training produces, one prefix - mini-beatrix-3 — COMPLETE (2026-10-05; started 2026-09-20, relaunched 2026-09-27 on the engineered form and 2026-09-28 on amoe-lora 0.2.11). The v3 craft: 32 blocks, d 1024, 16 heads, context 4096, byte vocabulary with the trigram byte embedding, about 376M parameters. Every block carries a CausalSplatHUB (four address constellations, K 64 at D 128, the exact chunked scan at…
Open weights
mit
A LoRA for liminal spaces: empty malls, fog-bound roads, parking garages, suburbs at night, vacant theatres and hallways. It was trained on the 1,873 curated and captioned images of the Status: training (started 2026-09-26 00:14 UTC). A new file lands every 2 epochs. Sample images come when the run finishes. The folders are / /. 1. Get the Anima base files from circlestone-labs/Anima splitfiles/: anima-base-v1.0.safetensors (diffusionmodels), qwen306bbase.safetensors (textencoders) and qwenimagevae.safetensors (vae). 2. Put the LoRA file in models/loras and load it with LoraLoaderModelOnly at strength 1.0. 3. Sample around 1 megapixel (1024x1024, or anything from 1:2 to 2:1) with 30-50…
Open weights
other
Experiments on steering Anima, a 2B illustration model built on NVIDIA Cosmos-Predict2, with a second conditioning source: Beatrix, a byte-level language model from the geolip line. Anima reads its prompt through a small language model (Qwen3 0.6B) and a light adapter, so an added signal is not drowned by a very large text encoder; that makes it a bed for testing how far a second source can steer the image without a full diffusion training run. The first experiments measure the bed itself: how its conditioning responds to mood words and to a mood direction added to it, and what LoRAs trained on the model's own mood images do. Each experiment has its own folder under experiments/ with a…
Open weights
other
Beatrix (mini-beatrix-3, a 376M-parameter byte-level language model) reads raw UTF-8 bytes. A tokenizer-based model hands text around in its own spelling: a byte-level BPE such as Qwen3's stores every byte as a printable stand-in character, so a space becomes the two bytes of 'Ġ' and ' taco' becomes the one token 'Ġtaco'. Beatrix reads that spelling as a different text from the plain bytes, and the difference grows with depth. A surface arm is a small detachable adapter (13.7M parameters, one module after each of her 32 blocks) trained so that she reads a spelling the way she reads the plain bytes: at each token's closing byte her state on the spelled surface is pulled toward her own state…
Open weights
mit
geolip-alephllm
