Novaciano/Llama-3.2-1B-Carpincho_Alzado

Full fine-tune vs Novaciano/RUN-WITH-SCISSORS-3.2-1B. Fine-tune: 98% of the weights changed, across 16 of 16 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 26/33, MLP 47/48, Attention 62/64

1 derivatives checked

• mradermacher/Llama-3.2-1B-Carpincho_Alzado-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse