River Rider PRO
RiverRider
AI & ML interests
Computational semiotics is empirically proven. It takes three to tango ๐๐ชฉ๐บ
Recent Activity
posted an update about 14 hours ago
A single forward pass of the frozen Qwen-2.5-7B model plus a lightweight classifier reaches 0.866 plus or minus 0.011 AUC on the full TruthfulQA-MC2 benchmark. No adapters. No fine-tuning. No extra parameters on the backbone.
This is the strongest hidden-state truthfulness detector reported on the benchmark to date.
The same latent features that the SRT-NLA-AV-v1 demo reads out as coherent natural-language verbalizations turn out to be rich enough to support production-grade auditing for honesty versus hallucination. The internal semiotic infrastructure we have been exploring in public is already information-dense enough to solve hard downstream problems with almost trivial overhead.
You can watch the underlying latent geometry in action right here:
https://huggingface.co/spaces/RiverRider/srt-nla-av-v1-demo
Full code, artifacts, and reproduction steps are in the repository:
https://github.com/space-bacon/SRT
Try the Glass Box
https://huggingface.co/spaces/RiverRider/srt-nla-demo reacted to danielhanchen's post with ๐ฅ about 19 hours ago
Qwen3.6 MTP is here! Run locally on 20GB RAM. โก๏ธ
MTP enables Qwen3.6 to generate ~1.4โ2.2ร faster with no accuracy change.
Qwen3.6-27B: https://huggingface.co/unsloth/Qwen3.6-27B-MTP-GGUF
Qwen3.6-35B-A3B: https://huggingface.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6#mtp-guide
reacted to tegridydev's post with ๐ฅ about 20 hours ago
โจ Research-Papers (various topics across AI/LLM research areas)
https://huggingface.co/datasets/tegridydev/research-papers
Currently building out the foundation topics and raw .pdf research paper files
Will be processing and cleaning up and converting into high quality training datasets
Check it out, give it a like and leave a comment below or join community discussion and suggest what fields and research topics you want to see included!