iamtatsuki05/sarashina2.2-Bi-0.5b

Same weights, converted vs sbintuitions/sarashina2.2-0.5b. Same weights stored in another dtype (BF16 → F32).

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96

1 derivatives checked

• iamtatsuki05/Sentence-Sarashina-Bi-0.5B-PT: Full fine-tune

On the Hub · Downloads on Model Pulse