Remote Config Triage
$0.25
Synchronous zero-GPU diagnostic evaluating generation_config.json, stop tokens, repetition penalty, and EOS alignment in <1 second.
Live GPU Diagnostic Sweep
$4.90
Grid sweep over top-p, temperature, and presence penalties with real GPU forward passes to detect uncurable weight-space loops.
Full-Eval (<=4B Models)
$9.00
Multi-seed evaluation on MATH-500, GSM8K, IFEval, secret perturbed WSP-Holdout split, and StrongREJECT/XSTest safety gates.
Full-Eval (7B–14B Models)
$29.00
Statistical significance gate with 10,000 paired bootstrap resamples for enterprise production release attestation.
Publisher Attestation
$49.00
Cryptographic release badge, Ed25519 root signature, and hash-chained CRL transparency listing.
50-Pass Custom Surgery
$149.00
Stateful gemini-4-argon causal weight-space probing loop discovering minimal delta columns for proprietary defects.
Verified Patch Catalog (P0 Config & P1 Weights)
Every patch is pre-registered, evaluated across 10,000 paired bootstrap and permutation tests, checked against the secret perturbed WSP-Holdout split and StrongREJECT/XSTest safety gates, and signed with Ed25519.
P1_WEIGHTS
wsp-qwen3.5-0.8b-math-loop-exp8
Target: Qwen/Qwen3.5-0.8B
Qwen3.5-0.8B 32k Thinking-Loop Surgical Cure (MIT CSAIL Exp-8)
Cures the catastrophic 93.6% 32k-token repetition loop on MATH-500 through 64 targeted delta columns across layers 15 & 19 (+48.1% MATH-500 accuracy uplift).
$ pip install wsphub && wsp apply Qwen/Qwen3.5-0.8B --patch wsp-qwen3.5-0.8b-math-loop-exp8 --out ./patched
P0_CONFIG
wsp-qwen3.5-0.8b-missing-genconfig-eos-fix
Target: Qwen/Qwen3.5-0.8B
Qwen3.5-0.8B Missing generation_config & Dual Stop-Token Fix
Restores canonical stop tokens and anti-loop presence penalties in generation_config.json.
$ pip install wsphub && wsp apply Qwen/Qwen3.5-0.8B --patch wsp-qwen3.5-0.8b-missing-genconfig-eos-fix --out ./patched
P0_CONFIG
wsp-qwen2.5-coder-1.5b-rep-penalty-syntax-fix
Target: Qwen/Qwen2.5-Coder-1.5B-Instruct
Qwen2.5-Coder-1.5B Repetition Penalty Syntax Truncation Neutralization
Neutralizes repetition penalty=1.1 identifier/brace corruption in code & JSON generation.
$ pip install wsphub && wsp apply Qwen/Qwen2.5-Coder-1.5B-Instruct --patch wsp-qwen2.5-coder-1.5b-rep-penalty-syntax-fix --out ./patched
WSP Verify CI/CD & Supernova Settlement Rail
Automated regression testing and attestation for model builders, enterprise publishers, and AI coding agents:
- $0.25 — Remote Config Triage (<1s)
- $4.90 — Live GPU Diagnostic Sweep
- $9.00 — Full Evaluation <=4B
- $29.00 — Full Evaluation 7B–14B
- $49.00 — Publisher Attestation
- $149.00 — 50-Pass Custom Surgery
Streamable HTTP MCP Server Endpoint
Direct JSON-RPC 2.0 integration for Cursor, Windsurf, Claude Code, and autonomous AI agents:
Endpoint: POST https://api.wsphub.dev/api/v1/mcp
Discovery Tool: wsp.search_verified_patches (Free)
Metered Gateway: https://supernova.cool/api/v1/mcp/ (X-Supernova-Key)
Frequently Asked Questions (FAQ)
What is WSP (Weight Sparse Patch) format?
WSP is an open binary specification (.wsp v2.1) that stores surgical weight deltas and configuration fixes for open-weight models. It allows instant application in under 5 seconds via Copy-on-Write Safetensors without redownloading 16 GB base models.
How does WSP achieve 94% to 99% smaller files than LoRA?
LoRA applies low-rank matrices across all layers. WSP isolates the exact causal columns responsible for bugs (e.g. 64 columns across 2 MLP layers), reducing the file size down to 0.8 MB – 4 MB.
Can patches be reverted bit-exactly?
Yes. Running wsp revert <dir> restores the pristine original SHA-256 weight state in <1 second.