|
Download README.md from Pacific-i64/Token-Routing-Interactive-Paper: direct link, hf CLI and curl.
- Browser
- Download file 1.51 kB
-
https://huggingface.co/spaces/Pacific-i64/Token-Routing-Interactive-Paper/resolve/main/README.md
- Command line
-
hf download hf://spaces/Pacific-i64/Token-Routing-Interactive-Paper/README.md
-
curl -L -o README.md https://huggingface.co/spaces/Pacific-i64/Token-Routing-Interactive-Paper/resolve/main/README.md
1.51 kB
metadata
title: Token Routing Interactive Paper
emoji: 🧭
colorFrom: purple
colorTo: green
sdk: static
app_file: index.html
pinned: false
license: cc-by-nc-4.0
short_description: Interactive report for the TR-HASH MoE 200M multi-hash SFT.
TR-HASH MoE 200M — Interactive Multi-Hash Report
Interactive companion for the 201.2M-parameter TR-HASH MoE full-SFT checkpoint selected from epoch 2 on PIQA.
The Space provides:
- an architecture explorer for the shared SwiGLU and deterministic multi-hash top-2 residual path;
- checkpoint-derived tokenizer IDs and expert assignments for selected tokens;
- the recorded three-epoch full-parameter SFT and PIQA diagnostics;
- live chat generation from
AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT.
The model has 16 layers, a 32k vocabulary, GQA 14/2, four stored residual experts, two independent token-ID hash routes per layer, and a shared dense SwiGLU branch. There is no learned expert router and no LoRA adapter.
Its metrics describe only this 201.2M model. They are training diagnostics and a full PIQA validation measurement, not a dense-baseline comparison or a broad general-capability benchmark.