Hugging Face's logo
David Finch's picture

David Finch

davidf419
1 8 11
ramgpt's profile picture
·

AI & ML interests

Custom harnesses, MCP servers, trying coding+vision finetunes on 16gb vram.

Recent Activity

reacted to tardellirs's post with 👍 3 days 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.
liked a Space 3 days ago
tardellirs/weightprint
new activity 5 days ago
endless-frontier/Fx-Work-1028:Occasional "[non-text content omitted..." output between tool calls on long visual task (new in -1028)
View all activity

Organizations

None yet