Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
🏗️
Building on HF
River Rider
PRO
RiverRider
3
2
14
Follow
branikita's profile picture
Quazim0t0's profile picture
apehex's profile picture
25 followers
·
26 following
Space-Bacon
AI & ML interests
Computational semiotics is empirically proven. It takes three to tango 💃🪩🕺
Recent Activity
updated
a Space
about 1 hour ago
RiverRider/srt-sunstone
posted
an
update
1 day 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.
updated
a model
1 day ago
RiverRider/srt-sunstone-linear-head
View all activity
Organizations
RiverRider
's models
16
Sort: Recently updated
RiverRider/srt-sunstone-linear-head
Updated
1 day ago
RiverRider/srt-nla-gemma4-artifacts
Updated
1 day ago
RiverRider/srt-nla-av-gemma4
Updated
6 days ago
RiverRider/Gemma-4-31B-it-SRT-Sunstone
Feature Extraction
•
Updated
23 days ago
RiverRider/srt-adapter-gptoss20b
Feature Extraction
•
Updated
25 days ago
RiverRider/srt-nla-av-gptoss20b
Feature Extraction
•
Updated
25 days ago
RiverRider/srt-nla-av-gemma2-2b-v1
Feature Extraction
•
Updated
Jun 18
•
5
RiverRider/srt-adapter-qwen3-235b
Feature Extraction
•
Updated
Jun 18
•
7
RiverRider/srt-nla-av-llama32-3b
Feature Extraction
•
Updated
Jun 18
•
6
RiverRider/srt-nla-av-v1
Feature Extraction
•
Updated
Jun 18
•
14
•
4
RiverRider/zooL4nD3r-v0.1
Feature Extraction
•
Updated
Jun 18
•
15
RiverRider/srt-adapter-v22c_a050
Feature Extraction
•
Updated
Jun 18
RiverRider/srt-adapter-v1.0
Feature Extraction
•
Updated
Jun 18
•
32
RiverRider/srt-adapter-v21a
Feature Extraction
•
Updated
Jun 18
RiverRider/srt-adapter-v18
Feature Extraction
•
Updated
Jun 18
RiverRider/srt-adapter-v8a
Feature Extraction
•
Updated
Jun 18
•
11
•
2