mradermacher/Macaroni-v2-7b-GGUF

Same weights, converted vs andrijdavid/Macaroni-v2-7b. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: Norms 0/65, Attention 0/128, MLP 0/96, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse