bde31/weight-noise-writers
AI model by bde31
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.
Copies of one language model, each made a different writer by seeded Gaussian noise in its weights. They were built to ask whether authorship attribution can tell such writers apart. The poems they wrote are in bde31/weight-noise-writers-poems. These models are degraded on purpose. They are meant for research on stylometry and model perturbation, not for general use. The base is Gemma 4 31B it (Google DeepMind) in the Q80 GGUF quantization by Unsloth. To each of its 411 quantized weight tensors W we add sigma · sd(W) · E, where E is standard normal noise fixed by the seed and the tensor name, and requantize to Q80. The 422 small F32 tensors are left unchanged. Each file was rebuilt on a…
Read the full model card ↗ · Preview checked 2026-11-17T07:20:09.975Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
bde31/weight-noise-writers is a task-unspecified model repository published by bde31 on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- Not reported
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-17T06:53:19.000Z
- Last modified
- 2026-11-17T06:53:20.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: google/gemma-4-31B-it
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 2026-11-17T07:01:06.441Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.