AnassMzn/ECE-AFA

Full fine-tune vs paulml/NeuralOmniWestBeaglake-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• mradermacher/ECE-AFA-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse