Spaces:
Running
Running
| title: OpenBallast | |
| emoji: 💻 | |
| colorFrom: green | |
| colorTo: pink | |
| sdk: static | |
| pinned: true | |
| license: cc-by-4.0 | |
| short_description: Just download more VRAM | |
| # ⚓ OpenBallast | |
| **We measured how much of a bigger model's factual advantage is just memorized | |
| trivia, and whether you can buy that back with a file instead of with | |
| parameters. You can, and it's 40–100× cheaper per byte.** | |
| Small models reason fine — they just don't *know* much. Parameters are the most | |
| expensive place to store facts (~100× more bytes per fact than a compressed triple | |
| corpus). OpenBallast builds **ballasts**: versioned, CC0, rank-quantized knowledge | |
| artifacts you pair with any local model — pick your knowledge level like you pick | |
| a GGUF quant. | |
| **Measured** (two model families, 50,147 linked probes + a 43,137-probe | |
| hallucination suite): | |
| - Raw, Gemma-4's 2B/4B/12B score 61/66/68%; given the same corpus to look | |
| facts up in, all three land at 87–91%. Replicates on Qwen3.5 (0.8B–9B: raw | |
| 32–54%, ballasted 77–83%, and the ballasted 4B beats the ballasted 9B). | |
| Size gaps are mostly memorization gaps. | |
| - A 2B + a **470 MB** file beats the 12B raw with a real, non-generative | |
| lookup in the loop; the parameter route costs ~19 GB. Hallucination on | |
| answerable questions: 0.24 → 0.07. | |
| - Grounding cuts multi-hop hallucination 3–20× but *raises* fabrication on | |
| unanswerable questions — it fixes answerable questions, it does not teach | |
| abstention. | |
| - Ballasted accuracy doubles as a 4-bit damage diagnostic: nf4 breaks some | |
| models and not others, unpredictably from size, and only the grounded | |
| score tells you which. | |
| - Corpora tuned to a specific model's knowledge gaps lose to the one generic | |
| corpus at every size — a decisive negative result. | |
| - 📦 [ballast-t0](https://huggingface.co/datasets/OpenBallast/ballast-t0) — the corpus, 8 quantization levels, CC0 | |
| - 🧪 [ballast-evalsets](https://huggingface.co/datasets/OpenBallast/ballast-evalsets) — 50k recall probes + 43k hallucination probes | |
| - 📖 [Thesis + methodology + numbers](https://github.com/OpenBallast/ballast) | |
| - ⚡ Live demo endpoint (MCP): `https://mcp.openballast.org` — runs on a $0/month stack |