Why named_parameters() does not return bias?

1

I use the following code:

for k,v in model.named_parameters():
    print(k)

Only weight returned:

base_model.model.model.embed_tokens.weight
base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight
base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight
base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight
base_model.model.model.layers.0.self_attn.k_proj.base_layer.weight

Why doesn’t it return bias? What if I want it to return bias?

2

Could you post the setup of the layer you are using?

4

sorry. It’s my fault. The bias of the linear layer in my model structure is false. :sweat_smile: :rofl: :joy:
thanks your reply