ternary15M
A 15.19M-parameter Llama-style language model trained from scratch on TinyStories where all 42 attention and FFN linear layers...
A 15.19M-parameter Llama-style language model trained from scratch on TinyStories where all 42 attention and FFN linear layers...
static quants of https://huggingface.co/anthonylee991/falcon-coder-3b For a convenient overview and download list, visit our model page for this model....
Ternary (1.58-bit) expert TurboQuant quantization of Qwen/Qwen3.5-122B-A10B — 3-bit attention/dense, ternary {-c, 0, +c} experts packed as base-3...
Core AI is Apple’s on-device ML runtime in iOS 27 / macOS 27 and the successor to Core...
A reference implementation of a routed-ternary tiny language model with a bit-exact Python ↔ C99 inference engine, sized...
This repository contains a highly optimized TQ1 quantized version of the official prism-ml/Ternary-Bonsai-4B-unpacked model for the ATLAS Engine...
This repository contains a highly optimized TQ1 quantized version of the official tiiuae/Falcon3-10B-Instruct model. It is formatted explicitly...
> Заменено. Это репозиторий является исследовательским артефактом из более ранней линии Outlier и больше не является рекомендуемой загрузкой....
A 4.3M parameter language model with ternary weights (-1, 0, +1) trained from scratch on a free-tier 2-thread...
Тройное адаптивное выравнивание И V2 поставляет систему коррекции трубопровода: The Doctors — 496 кросс-слойных тройных ветвей низкого ранга,...