tocsa/llama2-7b-sft-verilog
Full fine-tune vs meta-llama/Llama-2-7b-hf. Fine-tune: 98% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 62/65, MLP 96/96, Attention 128/128, lm_head 1/1
Full fine-tune vs meta-llama/Llama-2-7b-hf. Fine-tune: 98% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 62/65, MLP 96/96, Attention 128/128, lm_head 1/1