arxiv:2610.30970
Tardelli Stekel PRO
tardellirs
AI & ML interests
None yet
Recent Activity
liked a dataset 43 minutes ago
scenario-labs/3d-collection reacted to theirpost with 🚀 about 1 hour ago
Model cards say what a model is: a fine-tune of X, a quantization of Y. I built Weightprint to check that against the weights.
App: https://huggingface.co/spaces/tardellirs/weightprint
Data (every pair, and the copy groups): https://huggingface.co/datasets/tardellirs/weightprint
It reads the header and a few bytes of every tensor (no downloads) and compares a model with the parent its card declares. 120,976 models so far. Some of what came out:
- 12% of declared fine-tunes hold their parent's weights unchanged.
- 23% of declared fine-tunes are LoRA-style: only the attention and MLP matrices moved, norms and embeddings untouched. That share went from 10% in 2023 to 25% in 2026.
- Of 1,668 fine-tunes named abliterated, uncensored or heretic, 53% edit only the matrices that write to the residual stream, the signature of an abliteration. The rest were trained further, merged, or are the parent's weights.
- 51% of the weight bytes on the Hub are byte-for-byte repeats of another repo's files.
Search any Hub id to see which layers and parts changed against its parent, or compare any two models.
A sample per tensor can miss things, and some formats can't be compared yet. If a verdict on a model you know looks wrong, tell me here and I'll check it against the engine. That's what this post is for, before a longer write-up. reacted to theirpost with 🔥 about 1 hour ago
Model cards say what a model is: a fine-tune of X, a quantization of Y. I built Weightprint to check that against the weights.
App: https://huggingface.co/spaces/tardellirs/weightprint
Data (every pair, and the copy groups): https://huggingface.co/datasets/tardellirs/weightprint
It reads the header and a few bytes of every tensor (no downloads) and compares a model with the parent its card declares. 120,976 models so far. Some of what came out:
- 12% of declared fine-tunes hold their parent's weights unchanged.
- 23% of declared fine-tunes are LoRA-style: only the attention and MLP matrices moved, norms and embeddings untouched. That share went from 10% in 2023 to 25% in 2026.
- Of 1,668 fine-tunes named abliterated, uncensored or heretic, 53% edit only the matrices that write to the residual stream, the signature of an abliteration. The rest were trained further, merged, or are the parent's weights.
- 51% of the weight bytes on the Hub are byte-for-byte repeats of another repo's files.
Search any Hub id to see which layers and parts changed against its parent, or compare any two models.
A sample per tensor can miss things, and some formats can't be compared yet. If a verdict on a model you know looks wrong, tell me here and I'll check it against the engine. That's what this post is for, before a longer write-up.Organizations
