YCF-AI/CyberTiel-Coder-35B-MLX

Full fine-tune vs peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-MLX-oQ6e-MTP. Fine-tune: 90% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 0/3, Embeddings 0/7, Norms 4/247, Attention 560/780, MLP 767/1011, other 0/1

On the Hub · Downloads on Model Pulse