mergekit-community/Hermes-3-Remix-L3.2-3b

Partial fine-tune vs NousResearch/Hermes-3-Llama-3.2-3B. Partial change: 81% of the weights changed (attention, mlp, norms), in 26 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 52/57, MLP 78/84, Attention 104/112

1 derivatives checked

• mradermacher/Hermes-3-Remix-L3.2-3b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse