bbidpa/Qwen2.5-Coder-0.5B-Flutter-steps
Full fine-tune vs Qwen/Qwen2.5-Coder-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 12/49, MLP 72/72, Attention 164/168
Full fine-tune vs Qwen/Qwen2.5-Coder-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 12/49, MLP 72/72, Attention 164/168