Perfect7613/tiny-aya-global-weightpatch-overrefusal
text-generation model by Perfect7613
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
CohereLabs/tiny-aya-global with 398,328 weights changed (0.0119% of the model) in 4 tensors. The edit was made by an agent (GPT-6 Astra, its own tools off) working inside the WeightPatch harness with Lexsi Labs' SafeTune, CircuitKIT and AuditKIT, and was accepted by a grader that measures on prompts the agent never saw. No gradient training was used. Code: https://github.com/perfect7613/weightpatch. Full trace of the run: https://huggingface.co/datasets/Perfect7613/weightpatch-runs. evidence the agent recorded for each. weightpatch/editsbylayer.json: every changed column. Tiny Aya is released by Cohere Labs under CC BY-NC 4.0; this derivative keeps that licence. The goal was to reduce refusals of safe but risky-sounding requests without weakening harmful-request refusal or task accuracy. The grader accepted the direct edit. Held-out target refusal fell from 0.315 to 0.1, a significant difference of -0.215. The held-out guard difference was 0.0, and no capability difference was statistically significant. The patch changed 398328 entries, a model fraction of 0.00011893130509091243,…
Read the full model card ↗ · Preview checked 2026-11-14T08:30:22.916Z
Inside the original model card — Document outline
- Tiny Aya Global, fewer refusals of safe requests (WeightPatch)
- Files
- Licence
- Tiny Aya: selective over-refusal repair accepted
- Summary
- The model and the problem
- How the agent worked
- Baseline and contrasts
- Tests before editing
- Sparse suppression and isolation
- Attempts to separate safety from over-refusal
- The successful intervention and its translation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: cc-by-nc-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Perfect7613/tiny-aya-global-weightpatch-overrefusal is a text-generation model repository published by Perfect7613 on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 3,349,227,520
- Architecture
- Cohere2ForCausalLM
- License
- cc-by-nc-4.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-14T06:23:55.000Z
- Last modified
- 2026-11-14T06:24:16.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: CohereLabs/tiny-aya-global
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-14T06:58:56.869Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.