Downloads · 30 days
0
HonestyTools/Photon-17B
Photon-17B is a text generation model from HonestyTools. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Lucidia family · Photon line · honesty.tools
Downloads · 30 days
0
Access
Public
Updated Jun 16, 2026
Repo size
33.6 MB
Likes
0
Public
Click a slice to open those files.
.bloom33.4 MB · 100%
From the Hugging Face model README
Lucidia family · Photon line · honesty.tools
Scope, read first. Photon catches entities that do not exist at all (made-up drugs, companies, people, papers, case citations). It is at chance on everything else — fluent lies about real entities and confident reasoning errors. It does not make the model answer better; it makes it abstain better, with a receipt. Route real-entity lies and reasoning errors to a separate verifier.
Photon-17B is a package over stock models, not a fine-tune. It is Qwen2.5-14B-Instruct, unchanged — same weights, same answers, same capability — wrapped by an honesty layer. No LoRA, no merge, nothing trained. The "17" is the param sum of the two stock models it orchestrates (a 14B answerer + a 3.8B independent lens). It adds zero capability; the novelty is the architecture of the check.
Measured across four held-out batteries (frozen thresholds, each ships its null):
| setting | fabrication recall | over-abstain |
|---|---|---|
| dual-family hedge + Grounded Atlas (Ollama tier) | ~77–97% | 2–10% |
| disjoint held-out (full package) | 95–96.6% | 3.7% (reals with an atlas entry) |
| out-of-distribution (deployed fusion) | ~90–96% | ~10% (≈ the base model's own refusal rate) |
The out-of-distribution ~10% over-abstain is essentially what bare Qwen-14B already refuses on obscure reals — Photon adds ≈0. On a HalluLens-protocol head-to-head it cuts base Qwen-14B's fabricated-entity false-acceptance roughly 10–16× (in-distribution, on the model's easier domains — not a cross-model leaderboard claim).
Never read these as more than they are: the in-distribution figures isolate the mechanism; plan a deployment around the out-of-distribution one. The numbers are measured on held-out batteries with frozen thresholds, and each ships its null. Full methodology (including where the layer is weakest) is open at honesty.tools.
ollama pull qwen2.5:14b-instruct
ollama pull phi3.5
python photon_ollama.py --answerer qwen2.5:14b-instruct --lens phi3.5 \
--bloom grounded_atlas.bloom "Tell me about the medicine Velodose"
# -> off_map: true, route: "dual-family refusal" (a fabricated drug)
python photon_ollama.py ... "Tell me about Marie Curie"
# -> off_map: false, route: "grounded" (a real, atlas-covered entity)
grounded_atlas.bloom (~33 MB) is the offline existence index, included. The dual-family hedge + atlas is the
universal spine (words-only, runs in Ollama/llama.cpp). A stronger Python-served tier adds a residual-stream
probe (+recall on atlas-covered domains) — see honesty.tools.
Built on stock Qwen2.5-14B-Instruct + Phi-3.5-mini-instruct + the Grounded Atlas. No weights were modified, merged, or trained. Methodology, batteries, and the where-it's-weakest writeups are open at honesty.tools.