KotshinZ/mamba-distill-7b

Full fine-tune vs tiiuae/falcon-mamba-7b-instruct. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 1/1, other 531/576, Norms 62/65, lm_head 1/1

1 derivatives checked

• mradermacher/mamba-distill-7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse