Hcompany/NeoMME-260M-Retriever-ST-late

Same weights, repacked vs Hcompany/NeoMME-260M-Retriever. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/8, other 0/17, MLP 0/34, Attention 0/102

2 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse