Jiabin99

/

GraphGPT-7B-mix-all

like 25

when I was running graphgpt_eval.sh using the checkpoint in the "Files", it told me that Some weights of GraphLlamaForCausalLM were not initialized,but these weights are important,how can I solve this problem,I really need help

the problem:
Some weights of GraphLlamaForCausalLM were not initialized from the model checkpoint at /root/autodl-tmp/graphgpt/stage_1 and are newly initialized: ['model.graph_tower.gtLayers.1.norm.weight', 'model.layers.12.self_attn.o_proj.weight', 'model.layers.13.self_attn.q_proj.weight', 'model.layers.14.self_attn.k_proj.weight', 'model.layers.19.self_attn.rotary_emb.inv_freq', 'model.layers.24.post_attention_layernorm.weight', 'model.layers.29.mlp.gate_proj.weight', 'model.layers.23.mlp.down_proj.weight', 'model.layers.28.input_layernorm.weight', 'model.graph_tower.gtLayers.0.norm.weight', 'model.layers.23.input_layernorm.weight', 'model.layers.15.self_attn.rotary_emb.inv_freq', 'model.layers.23.self_attn.rotary_emb.inv_freq', 'model.layers.24.input_layernorm.weight', 'model.layers.31.mlp.down_proj.weight', 'model.layers.18.mlp.gate_proj.weight', 'model.layers.16.self_attn.k_proj.weight', 'model.layers.31.mlp.gate_proj.weight', 'model.layers.16.self_attn.rotary_emb.inv_freq', 'model.layers.30.self_attn.o_proj.weight', 'model.layers.13.self_attn.rotary_emb.inv_freq', 'model.layers.25.mlp.up_proj.weight', 'model.layers.19.self_attn.o_proj.weight', 'model.layers.31.input_layernorm.weight', 'model.layers.17.mlp.down_proj.weight', 'model.layers.29.mlp.up_proj.weight', 'model.graph_tower.gtLayers.1.norm.bias', 'model.layers.15.post_attention_layernorm.weight', 'model.graph_projector.bias', 'model.layers.30.mlp.down_proj.weight', 'model.layers.22.self_attn.q_proj.weight', 'model.layers.23.self_attn.v_proj.weight', 'model.layers.21.self_attn.q_proj.weight', 'model.layers.13.mlp.down_proj.weight', 'model.layers.30.self_attn.q_proj.weight', 'model.layers.13.self_attn.k_proj.weight', 'model.layers.23.self_attn.k_proj.weight', 'model.layers.25.self_attn.k_proj.weight', 'model.layers.29.self_attn.v_proj.weight', 'model.layers.24.self_attn.v_proj.weight', 'model.layers.27.input_layernorm.weight', 'model.layers.15.self_attn.o_proj.weight', 'model.layers.26.self_attn.k_proj.weight', 'model.layers.12.self_attn.v_proj.weight', 'model.layers.30.input_layernorm.weight', 'model.layers.18.mlp.up_proj.weight', 'model.layers.11.mlp.up_proj.weight', 'model.layers.27.mlp.gate_proj.weight', 'model.layers.31.self_attn.k_proj.weight', 'model.graph_tower.gtLayers.1.kTrans', 'model.graph_tower.gtLayers.2.norm.weight', 'model.layers.19.mlp.down_proj.weight', 'model.layers.22.self_attn.k_proj.weight', 'model.layers.25.self_attn.rotary_emb.inv_freq', 'model.layers.18.post_attention_layernorm.weight', 'model.layers.19.input_layernorm.weight', 'model.layers.31.mlp.up_proj.weight', 'model.layers.11.post_attention_layernorm.weight', 'model.layers.11.input_layernorm.weight', 'model.layers.21.input_layernorm.weight', 'model.layers.12.input_layernorm.weight', 'model.layers.26.self_attn.v_proj.weight', 'model.layers.16.input_layernorm.weight', 'model.layers.27.self_attn.q_proj.weight', 'model.layers.26.self_attn.rotary_emb.inv_freq', 'model.layers.25.post_attention_layernorm.weight', 'model.layers.30.self_attn.v_proj.weight', 'model.layers.19.post_attention_layernorm.weight', 'model.layers.27.mlp.up_proj.weight', 'model.layers.20.mlp.up_proj.weight', 'model.layers.21.post_attention_layernorm.weight', 'model.graph_tower.gtLayers.0.kTrans', 'model.layers.17.self_attn.q_proj.weight', 'model.norm.weight', 'model.layers.27.self_attn.o_proj.weight', 'model.layers.16.self_attn.v_proj.weight', 'model.graph_tower.inverW_P.weight', 'model.layers.24.mlp.gate_proj.weight', 'model.layers.14.mlp.up_proj.weight', 'model.graph_tower.gtLayers.2.kTrans', 'model.layers.19.self_attn.q_proj.weight', 'model.layers.30.self_attn.rotary_emb.inv_freq', 'model.layers.21.mlp.down_proj.weight', 'model.layers.29.input_layernorm.weight', 'model.layers.28.mlp.up_proj.weight', 'model.layers.30.mlp.up_proj.weight', 'model.layers.31.self_attn.v_proj.weight', 'model.layers.20.self_attn.k_proj.weight', 'model.layers.22.mlp.up_proj.weight', 'model.layers.27.self_attn.v_proj.weight', 'model.layers.26.input_layernorm.weight', 'model.layers.28.self_attn.rotary_emb.inv_freq', 'model.layers.19.mlp.gate_proj.weight', 'model.layers.15.self_attn.q_proj.weight', 'model.layers.19.self_attn.v_proj.weight', 'model.layers.22.self_attn.o_proj.weight', 'model.layers.30.post_attention_layernorm.weight', 'model.layers.21.self_attn.rotary_emb.inv_freq', 'model.layers.21.self_attn.v_proj.weight', 'model.layers.15.mlp.down_proj.weight', 'model.layers.22.input_layernorm.weight', 'model.layers.12.self_attn.q_proj.weight', 'model.layers.18.self_attn.q_proj.weight', 'model.layers.12.mlp.down_proj.weight', 'model.layers.18.self_attn.o_proj.weight', 'model.layers.26.mlp.down_proj.weight', 'model.layers.25.input_layernorm.weight', 'model.layers.18.self_attn.rotary_emb.inv_freq', 'model.layers.28.self_attn.k_proj.weight', 'model.layers.18.mlp.down_proj.weight', 'model.layers.29.self_attn.k_proj.weight', 'model.layers.21.mlp.up_proj.weight', 'model.layers.31.self_attn.o_proj.weight', 'model.layers.20.self_attn.rotary_emb.inv_freq', 'model.graph_tower.W_P.bias', 'model.layers.29.mlp.down_proj.weight', 'model.layers.13.input_layernorm.weight', 'model.layers.14.input_layernorm.weight', 'model.layers.17.mlp.gate_proj.weight', 'model.layers.17.mlp.up_proj.weight', 'model.layers.16.mlp.up_proj.weight', 'model.layers.25.mlp.down_proj.weight', 'model.layers.15.self_attn.k_proj.weight', 'model.layers.13.self_attn.o_proj.weight', 'model.layers.29.self_attn.q_proj.weight', 'model.layers.14.post_attention_layernorm.weight', 'model.layers.27.self_attn.rotary_emb.inv_freq', 'model.layers.31.post_attention_layernorm.weight', 'model.layers.24.self_attn.rotary_emb.inv_freq', 'model.layers.17.post_attention_layernorm.weight', 'model.layers.21.self_attn.k_proj.weight', 'model.layers.15.input_layernorm.weight', 'model.layers.16.mlp.gate_proj.weight', 'model.layers.27.self_attn.k_proj.weight', 'model.layers.29.self_attn.o_proj.weight', 'model.layers.28.self_attn.v_proj.weight', 'model.layers.22.mlp.down_proj.weight', 'model.layers.26.post_attention_layernorm.weight', 'model.layers.15.mlp.gate_proj.weight', 'model.graph_tower.gtLayers.1.vTrans', 'model.layers.14.self_attn.q_proj.weight', 'lm_head.weight', 'model.graph_tower.gtLayers.0.vTrans', 'model.layers.20.post_attention_layernorm.weight', 'model.layers.31.self_attn.rotary_emb.inv_freq', 'model.layers.16.self_attn.o_proj.weight', 'model.layers.17.self_attn.k_proj.weight', 'model.layers.26.mlp.up_proj.weight', 'model.layers.24.self_attn.q_proj.weight', 'model.layers.12.post_attention_layernorm.weight', 'model.layers.13.mlp.up_proj.weight', 'model.layers.23.mlp.gate_proj.weight', 'model.layers.20.mlp.down_proj.weight', 'model.layers.16.mlp.down_proj.weight', 'model.layers.28.post_attention_layernorm.weight', 'model.layers.14.self_attn.o_proj.weight', 'model.layers.16.post_attention_layernorm.weight', 'model.layers.17.self_attn.rotary_emb.inv_freq', 'model.layers.12.mlp.up_proj.weight', 'model.layers.30.mlp.gate_proj.weight', 'model.graph_tower.gtLayers.0.qTrans', 'model.layers.14.mlp.down_proj.weight', 'model.layers.19.mlp.up_proj.weight', 'model.graph_tower.gtLayers.0.norm.bias', 'model.layers.11.mlp.down_proj.weight', 'model.layers.22.post_attention_layernorm.weight', 'model.layers.28.self_attn.q_proj.weight', 'model.layers.23.self_attn.o_proj.weight', 'model.layers.24.self_attn.k_proj.weight', 'model.layers.19.self_attn.k_proj.weight', 'model.layers.20.self_attn.v_proj.weight', 'model.layers.14.mlp.gate_proj.weight', 'model.layers.24.self_attn.o_proj.weight', 'model.layers.22.self_attn.v_proj.weight', 'model.graph_tower.W_pos', 'model.layers.26.self_attn.o_proj.weight', 'model.layers.17.self_attn.v_proj.weight', 'model.graph_projector.weight', 'model.layers.14.self_attn.v_proj.weight', 'model.layers.25.self_attn.q_proj.weight', 'model.layers.27.post_attention_layernorm.weight', 'model.layers.20.self_attn.q_proj.weight', 'model.layers.24.mlp.up_proj.weight', 'model.layers.24.mlp.down_proj.weight', 'model.layers.13.self_attn.v_proj.weight', 'model.layers.25.self_attn.o_proj.weight', 'model.layers.17.input_layernorm.weight', 'model.graph_tower.W_P.weight', 'model.layers.21.mlp.gate_proj.weight', 'model.layers.31.self_attn.q_proj.weight', 'model.layers.25.self_attn.v_proj.weight', 'model.graph_tower.gtLayers.2.vTrans', 'model.layers.29.self_attn.rotary_emb.inv_freq', 'model.layers.20.mlp.gate_proj.weight', 'model.layers.28.self_attn.o_proj.weight', 'model.layers.14.self_attn.rotary_emb.inv_freq', 'model.layers.13.mlp.gate_proj.weight', 'model.layers.25.mlp.gate_proj.weight', 'model.layers.18.self_attn.v_proj.weight', 'model.graph_tower.inverW_P.bias', 'model.layers.28.mlp.gate_proj.weight', 'model.layers.28.mlp.down_proj.weight', 'model.layers.17.self_attn.o_proj.weight', 'model.layers.22.mlp.gate_proj.weight', 'model.layers.23.mlp.up_proj.weight', 'model.layers.16.self_attn.q_proj.weight', 'model.layers.12.mlp.gate_proj.weight', 'model.layers.15.mlp.up_proj.weight', 'model.layers.30.self_attn.k_proj.weight', 'model.layers.13.post_attention_layernorm.weight', 'model.layers.23.post_attention_layernorm.weight', 'model.layers.12.self_attn.rotary_emb.inv_freq', 'model.layers.20.self_attn.o_proj.weight', 'model.layers.27.mlp.down_proj.weight', 'model.graph_tower.gtLayers.2.qTrans', 'model.layers.12.self_attn.k_proj.weight', 'model.layers.26.mlp.gate_proj.weight', 'model.layers.20.input_layernorm.weight', 'model.layers.29.post_attention_layernorm.weight', 'model.layers.22.self_attn.rotary_emb.inv_freq', 'model.graph_tower.gtLayers.2.norm.bias', 'model.graph_tower.gtLayers.1.qTrans', 'model.layers.23.self_attn.q_proj.weight', 'model.layers.15.self_attn.v_proj.weight', 'model.layers.26.self_attn.q_proj.weight', 'model.layers.18.self_attn.k_proj.weight', 'model.layers.21.self_attn.o_proj.weight', 'model.layers.18.input_layernorm.weight']