Should I freeze norm.weight?

[metterian]

Llama base model has norm.weight.

Did you also freeze norm.weight when post-training?

    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.norm.weight": "model-00004-of-00004.safetensors"

[hills-code]

We freeze all the weights of the initial llama model and only train the newly added blocks.