jsfs11/RandomMergeWEIGHTEDv2-7B-DARETIES

Full fine-tune vs mlabonne/Monarch-7B. Fine-tune: 95% of the weights changed, across 31 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 63/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 derivatives checked

• mradermacher/RandomMergeWEIGHTEDv2-7B-DARETIES-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse