batiai/Fara-7B-GGUF

Quantization (fewer layers) vs microsoft/Fara-7B. batiai/Fara-7B-GGUF matches part of microsoft/Fara-7B (339 of its 729 tensors; the rest of microsoft/Fara-7B has no counterpart). On the shared part: batiai/Fara-7B-GGUF is a GGUF quantization (Q8_0) of the same weights: 141 tensors match exactly and 198 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1

On the Hub · Downloads on Model Pulse