CharlesLi/OpenELM-1_1B-SFT

Full fine-tune vs apple/OpenELM-1_1B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Norms 111/113, Attention 56/56, MLP 56/56, Embeddings 1/1

1 derivatives checked

• mradermacher/OpenELM-1_1B-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse