forgetting_gate_3_4_256 / decay_params.txt
Lanni-ni's picture
add remote code + model files
0fe45e5 verified
_forward_module.model.embeddings.weight
_forward_module.model.layers.0.attn.q_proj.weight
_forward_module.model.layers.0.attn.k_proj.weight
_forward_module.model.layers.0.attn.v_proj.weight
_forward_module.model.layers.0.attn.o_proj.weight
_forward_module.model.layers.0.attn.fgate_proj.weight
_forward_module.model.layers.0.mlp.gate_proj.weight
_forward_module.model.layers.0.mlp.down_proj.weight
_forward_module.model.layers.1.attn.q_proj.weight
_forward_module.model.layers.1.attn.k_proj.weight
_forward_module.model.layers.1.attn.v_proj.weight
_forward_module.model.layers.1.attn.o_proj.weight
_forward_module.model.layers.1.attn.fgate_proj.weight
_forward_module.model.layers.1.mlp.gate_proj.weight
_forward_module.model.layers.1.mlp.down_proj.weight
_forward_module.model.layers.2.attn.q_proj.weight
_forward_module.model.layers.2.attn.k_proj.weight
_forward_module.model.layers.2.attn.v_proj.weight
_forward_module.model.layers.2.attn.o_proj.weight
_forward_module.model.layers.2.attn.fgate_proj.weight
_forward_module.model.layers.2.mlp.gate_proj.weight
_forward_module.model.layers.2.mlp.down_proj.weight
_forward_module.lm_head.weight