powermove72/Notus-TheTop-7b-Passthrough

Partial fine-tune vs MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1. Partial change: 50% of the weights changed (attention, lm_head, mlp, norms), in 16 of 32 layers.

Tensors changed: MLP 48/96, Norms 33/65, Attention 64/128, lm_head 1/1, Embeddings 0/1

1 derivatives checked

• mradermacher/Notus-TheTop-7b-Passthrough-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse