Hugging Face's logo
Burton Lancaster's picture
🏗️ Building on HF

Burton Lancaster PRO

RiverRider
3 2 14
tegridydev's profile picture dipankarsarkar's profile picture PhysiQuanty's profile picture
·

AI & ML interests

Computational semiotics is empirically proven. It takes three to tango 💃🪩🕺

Recent Activity

updated a model 10 minutes ago
RiverRider/srt-sunstone-linear-head
repliedto their post 21 minutes ago
Train Once, Read Everywhere Paper title: Train Once, Read Everywhere: Substrate Invariance of the Linearly Readable Structure in Frozen Language Models Paper URL: https://github.com/space-bacon/SRT/blob/main/arxiv_program/paper.md Repository URL: https://github.com/space-bacon/SRT The consolidated findings of the SRT research program are now available. The program treats frozen production-scale language models as substrates whose internal states carry structure that small, inspectable instruments can read. Results include: - A ~12 M-parameter adapter that surfaces per-token semiotic signals from a frozen 7 B backbone with zero cross-entropy degradation - An activation verbalizer that recovers text from single hidden states up to a calibrated paraphrase ceiling - Linear readout ports spanning dense 3 B models to 94-layer 235 B mixture-of-experts models - A 22 MB linear head that gives a frozen multimodal chat model image-to-text retrieval performance matching fully trained 2018 dual encoders on the COCO benchmark The central claim is substrate invariance. The readable structure is a stable property of the model class. A head trained once on one host reads, with no retraining and at most a 42 KB recalibration, across: - Hosts ten times smaller (31 B → 3 B) - 4-bit weight precision - Entirely different silicon and kernels (CUDA/bf16 to Apple Silicon/MLX-Q4) Deployment tiers differ in latency and cost, never in capability. All instruments, measurement protocols, invariance evidence, negative results, and artifacts are in the repository.
repliedto their post about 1 hour ago
Train Once, Read Everywhere Paper title: Train Once, Read Everywhere: Substrate Invariance of the Linearly Readable Structure in Frozen Language Models Paper URL: https://github.com/space-bacon/SRT/blob/main/arxiv_program/paper.md Repository URL: https://github.com/space-bacon/SRT The consolidated findings of the SRT research program are now available. The program treats frozen production-scale language models as substrates whose internal states carry structure that small, inspectable instruments can read. Results include: - A ~12 M-parameter adapter that surfaces per-token semiotic signals from a frozen 7 B backbone with zero cross-entropy degradation - An activation verbalizer that recovers text from single hidden states up to a calibrated paraphrase ceiling - Linear readout ports spanning dense 3 B models to 94-layer 235 B mixture-of-experts models - A 22 MB linear head that gives a frozen multimodal chat model image-to-text retrieval performance matching fully trained 2018 dual encoders on the COCO benchmark The central claim is substrate invariance. The readable structure is a stable property of the model class. A head trained once on one host reads, with no retraining and at most a 42 KB recalibration, across: - Hosts ten times smaller (31 B → 3 B) - 4-bit weight precision - Entirely different silicon and kernels (CUDA/bf16 to Apple Silicon/MLX-Q4) Deployment tiers differ in latency and cost, never in capability. All instruments, measurement protocols, invariance evidence, negative results, and artifacts are in the repository.
View all activity

Organizations

Blog-explorers's profile picture Hugging Face Discord Community's profile picture open/ acc's profile picture