ProCreations/grug-35b-mtp

Same weights, repacked vs ProCreations/grug-35b-v2. Same weights in different files (re-saved, re-sharded or new metadata), plus 19 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/241, Attention 0/388, MLP 0/2349

1 derivatives checked

• ProCreations/grug-35b-mtp-gguf: Quantization

On the Hub · Downloads on Model Pulse