Some weights of the model checkpoint at declare-lab/flacuna-13b-v1.0 were not used when initializing LlamaForCausalLM: about flacuna HOT 6 OPEN

Hi, Flacuna is a LoRA-based model. You can refer to the flacuna.py file to see how we load the weights in self.model.

from flacuna.

Thanks for your response.
Yes, I tried this way also, but did not work.

from flacuna.

Can you add the warning message here? The warning you are encountering should also show the parameter names for which the pre-trained weights were not loaded.

Also, assuming you have the peft_flacuna from this repo in your directory?

from flacuna.

I am working on Sagemaker Studio. I am trying to run the model directly there. The warning message is below(refer to flacuna.py). Thanks.

`Some weights of the model checkpoint at declare-lab/flacuna-13b-v1.0 were not used when initializing LlamaForCausalLM: ['base_model.model.model.layers.31.self_attn.k_proj.SCB', 'base_model.model.model.layers.36.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.29.self_attn.v_proj.weight', 'base_model.model.model.layers.20.mlp.down_proj.SCB', 'base_model.model.model.layers.17.self_attn.o_proj.weight', 'base_model.model.model.layers.19.mlp.down_proj.weight', 'base_model.model.model.layers.39.self_attn.v_proj.weight', 'base_model.model.model.layers.39.self_attn.v_proj.SCB', 'base_model.model.model.layers.36.self_attn.v_proj.SCB', 'base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.22.mlp.up_proj.SCB', 'base_model.model.model.layers.5.self_attn.q_proj.weight', 'base_model.model.model.layers.8.mlp.down_proj.SCB', 'base_model.model.model.layers.39.mlp.down_proj.weight', 'base_model.model.model.layers.1.self_attn.v_proj.SCB', 'base_model.model.model.layers.11.mlp.down_proj.SCB', 'base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.5.self_attn.o_proj.SCB', 'base_model.model.model.layers.35.input_layernorm.weight', 'base_model.model.model.layers.17.self_attn.v_proj.weight', 'base_model.model.model.layers.9.self_attn.q_proj.SCB', 'base_model.model.model.layers.16.mlp.down_proj.SCB', 'base_model.model.model.layers.36.self_attn.v_proj.weight', 'base_model.model.model.layers.9.self_attn.k_proj.weight', 'base_model.model.model.layers.31.post_attention_layernorm.weight', 'base_model.model.model.layers.28.mlp.down_proj.SCB', 'base_model.model.model.layers.37.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.23.mlp.gate_proj.SCB', 'base_model.model.model.layers.7.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.8.mlp.up_proj.weight', 'base_model.model.model.layers.37.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.2.self_attn.v_proj.weight', 'base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.24.self_attn.k_proj.weight', 'base_model.model.model.layers.37.self_attn.o_proj.weight', 'base_model.model.model.layers.21.mlp.up_proj.weight', 'base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.25.mlp.down_proj.weight', 'base_model.model.model.layers.34.input_layernorm.weight', 'base_model.model.model.layers.39.input_layernorm.weight', 'base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.1.mlp.gate_proj.weight', 'base_model.model.model.layers.31.self_attn.o_proj.weight', 'base_model.model.model.layers.19.mlp.up_proj.SCB', 'base_model.model.model.layers.31.self_attn.v_proj.weight', 'base_model.model.model.layers.5.mlp.down_proj.SCB', 'base_model.model.model.layers.8.mlp.gate_proj.SCB', 'base_model.model.model.layers.26.mlp.down_proj.weight', 'base_model.model.model.layers.28.self_attn.o_proj.weight', 'base_model.model.model.layers.12.self_attn.k_proj.weight', 'base_model.model.model.layers.38.mlp.gate_proj.weight', 'base_model.model.model.layers.22.self_attn.q_proj.SCB', 'base_model.model.model.layers.5.mlp.up_proj.weight', 'base_model.model.model.layers.33.mlp.gate_proj.SCB', 'base_model.model.model.layers.14.mlp.gate_proj.SCB', 'base_model.model.model.layers.10.self_attn.q_proj.SCB', 'base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.39.mlp.down_proj.SCB', 'base_model.model.model.layers.35.mlp.down_proj.SCB', 'base_model.model.model.layers.4.mlp.gate_proj.SCB', 'base_model.model.model.layers.20.mlp.gate_proj.weight', 'base_model.model.model.layers.1.mlp.down_proj.SCB', 'base_model.model.model.layers.35.self_attn.q_proj.SCB', 'base_model.model.model.layers.17.self_attn.k_proj.weight', 'base_model.model.model.layers.13.self_attn.o_proj.weight', 'base_model.model.model.layers.37.self_attn.k_proj.weight', 'base_model.model.model.layers.22.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.20.self_attn.q_proj.weight', 'base_model.model.model.layers.1.mlp.gate_proj.SCB', 'base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.2.mlp.gate_proj.SCB', 'base_model.model.model.layers.39.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.1.self_attn.v_proj.weight', 'base_model.model.model.layers.22.self_attn.v_proj.weight', 'base_model.model.model.layers.14.self_attn.k_proj.weight', 'base_model.model.model.layers.26.mlp.gate_proj.SCB', 'base_model.model.model.layers.36.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.37.self_attn.o_proj.SCB', 'base_model.model.model.layers.30.self_attn.q_proj.SCB', 'base_model.model.model.layers.7.self_attn.v_proj.weight', 'base_model.model.model.layers.10.mlp.gate_proj.weight', 'base_model.model.model.layers.35.self_attn.v_proj.weight', 'base_model.model.model.layers.31.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.31.self_attn.o_proj.SCB', 'base_model.model.model.layers.16.mlp.down_proj.weight', 'base_model.model.model.layers.6.mlp.up_proj.weight', 'base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.28.mlp.gate_proj.SCB', 'base_model.model.model.layers.38.self_attn.k_proj.weight', 'base_model.model.model.layers.11.mlp.up_proj.SCB', 'base_model.model.model.layers.10.self_attn.k_proj.weight', 'base_model.model.model.layers.23.mlp.down_proj.SCB', 'base_model.model.model.layers.18.mlp.gate_proj.weight', 'base_model.model.model.layers.8.self_attn.v_proj.SCB', 'base_model.model.model.layers.5.self_attn.k_proj.SCB', 'base_model.model.model.layers.15.self_attn.q_proj.weight', 'base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.6.input_layernorm.weight', 'base_model.model.model.layers.21.mlp.gate_proj.SCB', 'base_model.model.model.layers.30.self_attn.o_proj.SCB', 'base_model.model.model.layers.26.mlp.gate_proj.weight', 'base_model.model.model.layers.16.self_attn.k_proj.SCB', 'base_model.model.model.layers.10.mlp.gate_proj.SCB', 'base_model.model.model.layers.16.self_attn.o_proj.weight', 'base_model.model.model.layers.25.input_layernorm.weight', 'base_model.model.model.layers.2.self_attn.q_proj.weight', 'base_model.model.model.layers.12.mlp.down_proj.SCB', 'base_model.model.model.layers.28.mlp.up_proj.weight', 'base_model.model.model.layers.37.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.34.self_attn.v_proj.weight', 'base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.19.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.12.post_attention_layernorm.weight', 'base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.11.post_attention_layernorm.weight', 'base_model.model.model.layers.8.self_attn.k_proj.weight', 'base_model.model.model.layers.27.self_attn.v_proj.weight', 'base_model.model.model.layers.36.mlp.gate_proj.weight', 'base_model.model.model.layers.14.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.30.mlp.gate_proj.weight', 'base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.22.mlp.gate_proj.SCB', 'base_model.model.model.layers.3.self_attn.k_proj.SCB', 'base_model.model.model.layers.36.self_attn.q_proj.weight', 'base_model.model.model.layers.29.mlp.gate_proj.weight', 'base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.4.self_attn.q_proj.weight', 'base_model.model.model.layers.34.mlp.down_proj.weight', 'base_model.model.model.layers.33.post_attention_layernorm.weight', 'base_model.model.model.layers.12.input_layernorm.weight', 'base_model.model.model.layers.0.mlp.gate_proj.SCB', 'base_model.model.model.layers.21.mlp.down_proj.SCB', 'base_model.model.model.layers.10.self_attn.o_proj.SCB', 'base_model.model.model.layers.33.mlp.down_proj.SCB', 'base_model.model.model.layers.13.mlp.up_proj.SCB', 'base_model.model.model.layers.29.self_attn.o_proj.SCB', 'base_model.model.model.layers.9.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.33.self_attn.o_proj.weight', 'base_model.model.model.layers.23.self_attn.q_proj.SCB', 'base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.32.mlp.up_proj.SCB', 'base_model.model.model.layers.35.self_attn.q_proj.weight', 'base_model.model.model.layers.36.mlp.down_proj.weight', 'base_model.model.model.layers.26.self_attn.v_proj.weight', 'base_model.model.model.layers.30.self_attn.q_proj.weight', 'base_model.model.model.layers.18.self_attn.v_proj.weight', 'base_model.model.model.layers.16.mlp.gate_proj.SCB', 'base_model.model.model.layers.30.mlp.gate_proj.SCB', 'base_model.model.model.layers.33.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.13.self_attn.q_proj.weight', 'base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.2.self_attn.k_proj.weight', 'base_model.model.model.layers.39.self_attn.q_proj.weight', 'base_model.model.model.layers.29.self_attn.q_proj.SCB', 'base_model.model.model.layers.23.self_attn.v_proj.SCB', 'base_model.model.model.layers.6.self_attn.o_proj.weight', 'base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.13.input_layernorm.weight', 'base_model.model.model.layers.15.mlp.gate_proj.SCB', 'base_model.model.model.layers.5.self_attn.v_proj.weight', 'base_model.model.model.layers.17.self_attn.k_proj.SCB', 'base_model.model.model.layers.23.self_attn.k_proj.SCB', 'base_model.model.model.layers.0.self_attn.o_proj.SCB', 'base_model.model.model.layers.16.mlp.up_proj.SCB', 'base_model.model.model.layers.28.self_attn.k_proj.weight', 'base_model.model.model.layers.28.mlp.up_proj.SCB', 'base_model.model.model.layers.3.self_attn.q_proj.SCB', 'base_model.model.model.layers.32.mlp.up_proj.weight', 'base_model.model.model.layers.11.mlp.up_proj.weight', 'base_model.model.model.layers.6.self_attn.v_proj.weight', 'base_model.model.model.layers.39.mlp.up_proj.weight', 'base_model.model.model.layers.37.post_attention_layernorm.weight', 'base_model.model.model.layers.22.post_attention_layernorm.weight', 'base_model.model.model.layers.12.mlp.down_proj.weight', 'base_model.model.model.layers.30.input_layernorm.weight', 'base_model.model.model.layers.6.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.27.self_attn.k_proj.SCB', 'base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.34.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.17.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.34.mlp.up_proj.SCB', 'base_model.model.model.layers.11.self_attn.o_proj.SCB', 'base_model.model.model.layers.30.self_attn.v_proj.SCB', 'base_model.model.model.layers.6.post_attention_layernorm.weight', 'base_model.model.model.layers.33.self_attn.k_proj.weight', 'base_model.model.model.layers.35.post_attention_layernorm.weight', 'base_model.model.model.layers.4.self_attn.o_proj.weight', 'base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.2.input_layernorm.weight', 'base_model.model.model.layers.15.self_attn.o_proj.weight', 'base_model.model.model.layers.24.mlp.up_proj.weight', 'base_model.model.model.layers.35.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.13.self_attn.v_proj.weight', 'base_model.model.model.layers.3.self_attn.o_proj.weight', 'base_model.model.model.layers.3.self_attn.o_proj.SCB', 'base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.17.mlp.gate_proj.weight', 'base_model.model.model.layers.19.mlp.up_proj.weight', 'base_model.model.model.layers.32.self_attn.o_proj.weight', 'base_model.model.model.layers.28.self_attn.q_proj.weight', 'base_model.model.model.layers.5.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.0.self_attn.q_proj.SCB', 'base_model.model.model.layers.23.post_attention_layernorm.weight', 'base_model.model.model.layers.7.self_attn.k_proj.SCB', 'base_model.model.model.layers.3.self_attn.q_proj.weight', 'base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.12.mlp.gate_proj.weight', 'base_model.model.model.layers.14.self_attn.q_proj.SCB', 'base_model.model.model.layers.6.self_attn.v_proj.SCB', 'base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.37.mlp.down_proj.weight', 'base_model.model.model.layers.13.self_attn.q_proj.SCB', 'base_model.model.model.layers.18.input_layernorm.weight', 'base_model.model.model.layers.14.mlp.up_proj.weight', 'base_model.model.model.layers.22.input_layernorm.weight', 'base_model.model.model.layers.16.self_attn.v_proj.SCB', 'base_model.model.model.layers.32.post_attention_layernorm.weight', 'base_model.model.model.layers.24.self_attn.q_proj.SCB', 'base_model.model.model.layers.30.self_attn.k_proj.weight', 'base_model.model.model.layers.9.input_layernorm.weight', 'base_model.model.model.layers.3.post_attention_layernorm.weight', 'base_model.model.model.layers.26.self_attn.o_proj.weight', 'base_model.model.model.layers.22.mlp.up_proj.weight', 'base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.0.input_layernorm.weight', 'base_model.model.model.layers.13.mlp.gate_proj.SCB', 'base_model.model.model.layers.7.mlp.up_proj.weight', 'base_model.model.model.layers.37.mlp.gate_proj.weight', 'base_model.model.model.layers.3.input_layernorm.weight', 'base_model.model.model.layers.31.mlp.down_proj.weight', 'base_model.model.model.layers.7.self_attn.q_proj.weight', 'base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.22.self_attn.k_proj.SCB', 'base_model.model.model.layers.36.self_attn.o_proj.SCB', 'base_model.model.model.layers.20.self_attn.k_proj.weight', 'base_model.model.model.layers.11.self_attn.v_proj.weight', 'base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.32.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.13.self_attn.k_proj.SCB', 'base_model.model.model.layers.3.mlp.down_proj.SCB', 'base_model.model.model.layers.10.mlp.down_proj.SCB', 'base_model.model.model.layers.22.mlp.down_proj.SCB', 'base_model.model.model.layers.27.self_attn.q_proj.weight', 'base_model.model.model.layers.26.post_attention_layernorm.weight', 'base_model.model.model.layers.8.self_attn.q_proj.SCB', 'base_model.model.model.layers.30.mlp.up_proj.weight', 'base_model.model.model.layers.33.self_attn.q_proj.SCB', 'base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.7.mlp.down_proj.SCB', 'base_model.model.model.layers.2.mlp.gate_proj.weight', 'base_model.model.model.layers.33.self_attn.k_proj.SCB', 'base_model.model.model.layers.14.mlp.gate_proj.weight', 'base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.30.mlp.up_proj.SCB', 'base_model.model.model.layers.23.self_attn.o_proj.SCB', 'base_model.model.model.layers.21.self_attn.v_proj.SCB', 'base_model.model.model.layers.12.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.16.self_attn.q_proj.weight', 'base_model.model.model.layers.31.self_attn.q_proj.weight', 'base_model.model.model.layers.0.mlp.gate_proj.weight', 'base_model.model.model.layers.29.self_attn.k_proj.SCB', 'base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.23.self_attn.v_proj.weight', 'base_model.model.model.layers.31.mlp.up_proj.SCB', 'base_model.model.model.layers.26.mlp.up_proj.SCB', 'base_model.model.model.layers.15.mlp.up_proj.weight', 'base_model.model.model.layers.35.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.20.self_attn.k_proj.SCB', 'base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.17.mlp.up_proj.SCB', 'base_model.model.model.layers.37.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.27.input_layernorm.weight', 'base_model.model.model.layers.2.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.7.post_attention_layernorm.weight', 'base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.15.mlp.down_proj.SCB', 'base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.16.mlp.gate_proj.weight', 'base_model.model.model.layers.34.post_attention_layernorm.weight', 'base_model.model.model.layers.25.self_attn.q_proj.SCB', 'base_model.model.model.layers.20.self_attn.v_proj.SCB', 'base_model.model.model.layers.36.mlp.up_proj.SCB', 'base_model.model.model.layers.6.mlp.up_proj.SCB', 'base_model.model.model.layers.38.input_layernorm.weight', 'base_model.model.model.layers.29.mlp.down_proj.SCB', 'base_model.model.model.layers.1.self_attn.o_proj.SCB', 'base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.26.self_attn.q_proj.weight', 'base_model.model.model.layers.29.self_attn.q_proj.weight', 'base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.14.mlp.up_proj.SCB', 'base_model.model.model.layers.19.mlp.down_proj.SCB', 'base_model.model.model.layers.11.self_attn.o_proj.weight', 'base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.28.self_attn.q_proj.SCB', 'base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.11.self_attn.v_proj.SCB', 'base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.25.self_attn.q_proj.weight', 'base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.6.mlp.down_proj.weight', 'base_model.model.model.layers.24.self_attn.o_proj.weight', 'base_model.model.model.layers.37.input_layernorm.weight', 'base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.19.self_attn.o_proj.weight', 'base_model.model.model.layers.9.self_attn.o_proj.SCB', 'base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.18.mlp.up_proj.SCB', 'base_model.model.model.layers.25.self_attn.o_proj.weight', 'base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.21.self_attn.k_proj.weight', 'base_model.model.model.layers.11.self_attn.k_proj.SCB', 'base_model.model.model.layers.33.input_layernorm.weight', 'base_model.model.model.layers.18.mlp.up_proj.weight', 'base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.1.self_attn.o_proj.weight', 'base_model.model.model.layers.10.self_attn.v_proj.weight', 'base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.36.mlp.down_proj.SCB', 'base_model.model.model.layers.13.post_attention_layernorm.weight', 'base_model.model.model.layers.32.self_attn.k_proj.SCB', 'base_model.model.model.layers.8.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.2.self_attn.q_proj.SCB', 'base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.12.self_attn.v_proj.SCB', 'base_model.model.model.layers.19.input_layernorm.weight', 'base_model.model.model.layers.33.self_attn.v_proj.SCB', 'base_model.model.model.layers.1.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.21.mlp.down_proj.weight', 'base_model.model.model.layers.29.mlp.up_proj.weight', 'base_model.model.model.layers.21.self_attn.q_proj.weight', 'base_model.model.model.layers.37.self_attn.v_proj.weight', 'base_model.model.model.layers.24.self_attn.o_proj.SCB', 'base_model.model.model.layers.28.self_attn.k_proj.SCB', 'base_model.model.model.layers.9.mlp.down_proj.SCB', 'base_model.model.model.layers.27.mlp.up_proj.weight', 'base_model.model.model.layers.23.mlp.down_proj.weight', 'base_model.model.model.layers.31.mlp.gate_proj.SCB', 'base_model.model.model.layers.32.self_attn.q_proj.SCB', 'base_model.model.model.layers.33.mlp.down_proj.weight', 'base_model.model.model.layers.25.mlp.down_proj.SCB', 'base_model.model.model.layers.38.mlp.up_proj.weight', 'base_model.model.model.layers.35.mlp.down_proj.weight', 'base_model.model.model.layers.24.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.32.mlp.gate_proj.SCB', 'base_model.model.model.layers.38.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.20.mlp.up_proj.weight', 'base_model.model.model.layers.36.self_attn.q_proj.SCB', 'base_model.model.model.layers.4.self_attn.v_proj.weight', 'base_model.model.model.layers.30.self_attn.o_proj.weight', 'base_model.model.model.layers.10.input_layernorm.weight', 'base_model.model.model.layers.23.self_attn.o_proj.weight', 'base_model.model.model.layers.32.mlp.down_proj.SCB', 'base_model.model.model.layers.28.self_attn.o_proj.SCB', 'base_model.model.model.layers.36.self_attn.k_proj.weight', 'base_model.model.model.layers.3.self_attn.k_proj.weight', 'base_model.model.model.layers.32.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.39.mlp.up_proj.SCB', 'base_model.model.model.layers.4.mlp.down_proj.weight', 'base_model.model.model.layers.23.self_attn.k_proj.weight', 'base_model.model.model.layers.24.self_attn.v_proj.SCB', 'base_model.model.model.layers.29.mlp.up_proj.SCB', 'base_model.model.model.layers.2.self_attn.v_proj.SCB', 'base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.22.mlp.gate_proj.weight', 'base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.10.mlp.up_proj.SCB', 'base_model.model.model.layers.14.input_layernorm.weight', 'base_model.model.model.layers.22.self_attn.v_proj.SCB', 'base_model.model.model.layers.8.self_attn.o_proj.weight', 'base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.15.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.5.self_attn.q_proj.SCB', 'base_model.model.model.layers.4.self_attn.o_proj.SCB', 'base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.18.self_attn.o_proj.weight', 'base_model.model.model.layers.16.self_attn.k_proj.weight', 'base_model.model.model.layers.2.mlp.down_proj.SCB', 'base_model.model.model.layers.5.mlp.down_proj.weight', 'base_model.model.model.layers.10.self_attn.o_proj.weight', 'base_model.model.model.layers.4.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.3.mlp.up_proj.SCB', 'base_model.model.model.layers.11.self_attn.q_proj.SCB', 'base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.4.mlp.up_proj.SCB', 'base_model.model.model.layers.21.self_attn.k_proj.SCB', 'base_model.model.model.layers.15.input_layernorm.weight', 'base_model.model.model.layers.38.self_attn.q_proj.SCB', 'base_model.model.model.layers.37.mlp.up_proj.weight', 'base_model.model.model.layers.23.input_layernorm.weight', 'base_model.model.model.layers.15.self_attn.q_proj.SCB', 'base_model.model.model.layers.17.self_attn.o_proj.SCB', 'base_model.model.model.layers.1.post_attention_layernorm.weight', 'base_model.model.model.layers.20.self_attn.o_proj.weight', 'base_model.model.model.layers.30.self_attn.v_proj.weight', 'base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.13.self_attn.v_proj.SCB', 'base_model.model.model.layers.34.mlp.down_proj.SCB', 'base_model.model.model.layers.7.mlp.down_proj.weight', 'base_model.model.model.layers.31.self_attn.v_proj.SCB', 'base_model.model.model.layers.31.mlp.gate_proj.weight', 'base_model.model.model.layers.28.mlp.down_proj.weight', 'base_model.model.model.layers.34.self_attn.v_proj.SCB', 'base_model.model.model.layers.19.mlp.gate_proj.weight', 'base_model.model.model.layers.31.mlp.down_proj.SCB', 'base_model.model.model.layers.0.self_attn.k_proj.SCB', 'base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.20.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.0.mlp.up_proj.SCB', 'base_model.model.model.layers.26.input_layernorm.weight', 'base_model.model.model.layers.39.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.14.self_attn.v_proj.weight', 'base_model.model.model.layers.39.self_attn.o_proj.SCB', 'base_model.model.model.layers.15.post_attention_layernorm.weight', 'base_model.model.model.layers.16.self_attn.o_proj.SCB', 'base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.26.self_attn.q_proj.SCB', 'base_model.model.model.layers.36.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.11.self_attn.k_proj.weight', 'base_model.model.model.layers.28.self_attn.v_proj.SCB', 'base_model.model.model.layers.34.mlp.gate_proj.weight', 'base_model.model.model.layers.29.post_attention_layernorm.weight', 'base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.19.self_attn.k_proj.SCB', 'base_model.model.model.layers.23.mlp.up_proj.SCB', 'base_model.model.model.layers.10.self_attn.q_proj.weight', 'base_model.model.model.layers.10.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.18.post_attention_layernorm.weight', 'base_model.model.model.layers.3.self_attn.v_proj.weight', 'base_model.model.model.layers.9.mlp.down_proj.weight', 'base_model.model.model.layers.24.mlp.down_proj.SCB', 'base_model.model.model.layers.34.self_attn.k_proj.weight', 'base_model.model.model.layers.37.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.38.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.5.input_layernorm.weight', 'base_model.model.model.layers.17.post_attention_layernorm.weight', 'base_model.model.model.layers.22.self_attn.q_proj.weight', 'base_model.model.model.layers.15.mlp.up_proj.SCB', 'base_model.model.model.layers.29.self_attn.o_proj.weight', 'base_model.model.model.layers.32.self_attn.o_proj.SCB', 'base_model.model.model.layers.38.mlp.down_proj.SCB', 'base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.38.self_attn.k_proj.SCB', 'base_model.model.model.layers.24.self_attn.v_proj.weight', 'base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.25.mlp.gate_proj.weight', 'base_model.model.model.layers.16.post_attention_layernorm.weight', 'base_model.model.model.layers.39.post_attention_layernorm.weight', 'base_model.model.model.layers.28.post_attention_layernorm.weight', 'base_model.model.model.layers.26.self_attn.k_proj.weight', 'base_model.model.model.layers.1.mlp.up_proj.SCB', 'base_model.model.model.layers.32.mlp.down_proj.weight', 'base_model.model.model.layers.13.self_attn.k_proj.weight', 'base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.27.self_attn.o_proj.SCB', 'base_model.model.model.layers.31.self_attn.q_proj.SCB', 'base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.34.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.16.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.6.mlp.down_proj.SCB', 'base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.18.self_attn.q_proj.SCB', 'base_model.model.model.layers.33.mlp.up_proj.SCB', 'base_model.model.model.layers.17.mlp.down_proj.weight', 'base_model.model.model.layers.29.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.21.input_layernorm.weight', 'base_model.model.model.layers.11.input_layernorm.weight', 'base_model.model.model.layers.23.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.28.input_layernorm.weight', 'base_model.model.model.layers.10.mlp.up_proj.weight', 'base_model.model.model.layers.7.mlp.up_proj.SCB', 'base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.0.mlp.up_proj.weight', 'base_model.model.model.layers.2.post_attention_layernorm.weight', 'base_model.model.model.layers.9.mlp.up_proj.weight', 'base_model.model.model.layers.3.mlp.down_proj.weight', 'base_model.model.model.layers.13.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.23.self_attn.q_proj.weight', 'base_model.model.model.layers.24.self_attn.q_proj.weight', 'base_model.model.model.layers.30.mlp.down_proj.weight', 'base_model.model.model.layers.35.self_attn.v_proj.SCB', 'base_model.model.model.layers.22.self_attn.k_proj.weight', 'base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.4.mlp.down_proj.SCB', 'base_model.model.model.layers.4.post_attention_layernorm.weight', 'base_model.model.model.layers.39.self_attn.q_proj.SCB', 'base_model.model.model.layers.19.self_attn.k_proj.weight', 'base_model.model.model.layers.35.self_attn.k_proj.weight', 'base_model.model.model.layers.21.self_attn.v_proj.weight', 'base_model.model.model.layers.37.mlp.up_proj.SCB', 'base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.36.mlp.up_proj.weight', 'base_model.model.model.layers.27.self_attn.k_proj.weight', 'base_model.model.model.layers.29.mlp.gate_proj.SCB', 'base_model.model.lm_head.weight', 'base_model.model.model.layers.38.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.8.mlp.gate_proj.weight', 'base_model.model.model.layers.15.self_attn.k_proj.SCB', 'base_model.model.model.layers.3.mlp.gate_proj.weight', 'base_model.model.model.layers.13.self_attn.o_proj.SCB', 'base_model.model.model.layers.10.post_attention_layernorm.weight', 'base_model.model.model.layers.5.self_attn.k_proj.weight', 'base_model.model.model.layers.33.mlp.up_proj.weight', 'base_model.model.model.layers.4.self_attn.k_proj.SCB', 'base_model.model.model.layers.9.self_attn.k_proj.SCB', 'base_model.model.model.layers.33.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.38.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.38.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.3.mlp.gate_proj.SCB', 'base_model.model.model.layers.8.post_attention_layernorm.weight', 'base_model.model.model.layers.35.mlp.up_proj.weight', 'base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.28.self_attn.v_proj.weight', 'base_model.model.model.layers.39.self_attn.o_proj.weight', 'base_model.model.model.layers.1.mlp.down_proj.weight', 'base_model.model.model.layers.14.mlp.down_proj.SCB', 'base_model.model.model.layers.8.self_attn.o_proj.SCB', 'base_model.model.model.layers.25.self_attn.v_proj.SCB', 'base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.9.self_attn.q_proj.weight', 'base_model.model.model.layers.36.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.20.mlp.gate_proj.SCB', 'base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.15.self_attn.k_proj.weight', 'base_model.model.model.layers.18.self_attn.v_proj.SCB', 'base_model.model.model.layers.18.mlp.down_proj.SCB', 'base_model.model.model.layers.7.self_attn.k_proj.weight', 'base_model.model.model.layers.39.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.25.self_attn.k_proj.SCB', 'base_model.model.model.layers.23.mlp.up_proj.weight', 'base_model.model.model.layers.20.self_attn.q_proj.SCB', 'base_model.model.model.layers.36.self_attn.k_proj.SCB', 'base_model.model.model.layers.3.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.21.self_attn.o_proj.SCB', 'base_model.model.model.layers.2.self_attn.k_proj.SCB', 'base_model.model.model.layers.32.input_layernorm.weight', 'base_model.model.model.layers.37.mlp.down_proj.SCB', 'base_model.model.model.layers.27.mlp.up_proj.SCB', 'base_model.model.model.layers.34.self_attn.q_proj.weight', 'base_model.model.model.layers.36.input_layernorm.weight', 'base_model.model.model.layers.9.self_attn.o_proj.weight', 'base_model.model.model.layers.10.mlp.down_proj.weight', 'base_model.model.model.layers.19.self_attn.o_proj.SCB', 'base_model.model.model.layers.9.mlp.gate_proj.weight', 'base_model.model.model.layers.29.input_layernorm.weight', 'base_model.model.model.layers.19.self_attn.v_proj.SCB', 'base_model.model.model.layers.14.self_attn.v_proj.SCB', 'base_model.model.model.layers.38.self_attn.v_proj.weight', 'base_model.model.model.layers.2.mlp.up_proj.weight', 'base_model.model.model.layers.7.self_attn.o_proj.SCB', 'base_model.model.model.layers.37.mlp.gate_proj.SCB', 'base_model.model.model.layers.18.mlp.down_proj.weight', 'base_model.model.model.layers.29.mlp.down_proj.weight', 'base_model.model.model.layers.13.mlp.up_proj.weight', 'base_model.model.model.layers.27.mlp.gate_proj.SCB', 'base_model.model.model.layers.34.self_attn.o_proj.SCB', 'base_model.model.model.layers.18.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.16.mlp.up_proj.weight', 'base_model.model.model.layers.0.self_attn.k_proj.weight', 'base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.21.mlp.gate_proj.weight', 'base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.14.self_attn.q_proj.weight', 'base_model.model.model.layers.0.self_attn.v_proj.weight', 'base_model.model.model.layers.0.mlp.down_proj.weight', 'base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.5.mlp.gate_proj.SCB', 'base_model.model.model.layers.21.self_attn.q_proj.SCB', 'base_model.model.model.layers.37.self_attn.q_proj.weight', 'base_model.model.model.layers.31.self_attn.k_proj.weight', 'base_model.model.model.layers.5.mlp.up_proj.SCB', 'base_model.model.model.layers.8.self_attn.v_proj.weight', 'base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.32.mlp.gate_proj.weight', 'base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.14.self_attn.o_proj.SCB', 'base_model.model.model.layers.5.self_attn.v_proj.SCB', 'base_model.model.model.layers.12.mlp.gate_proj.SCB', 'base_model.model.model.layers.4.self_attn.q_proj.SCB', 'base_model.model.model.layers.8.self_attn.q_proj.weight', 'base_model.model.model.layers.9.mlp.gate_proj.SCB', 'base_model.model.model.layers.1.self_attn.q_proj.weight', 'base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.38.self_attn.q_proj.weight', 'base_model.model.model.layers.12.self_attn.o_proj.weight', 'base_model.model.model.layers.26.self_attn.v_proj.SCB', 'base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.38.mlp.gate_proj.SCB', 'base_model.model.model.layers.24.mlp.gate_proj.weight', 'base_model.model.model.layers.0.self_attn.v_proj.SCB', 'base_model.model.model.embed_tokens.weight', 'base_model.model.model.layers.26.mlp.up_proj.weight', 'base_model.model.model.layers.0.self_attn.q_proj.weight', 'base_model.model.model.layers.14.post_attention_layernorm.weight', 'base_model.model.model.layers.36.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.32.self_attn.v_proj.SCB', 'base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.35.self_attn.o_proj.weight', 'base_model.model.model.layers.15.self_attn.o_proj.SCB', 'base_model.model.model.layers.24.input_layernorm.weight', 'base_model.model.model.layers.27.mlp.down_proj.SCB', 'base_model.model.model.layers.32.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.0.post_attention_layernorm.weight', 'base_model.model.model.layers.31.mlp.up_proj.weight', 'base_model.model.model.layers.35.mlp.gate_proj.weight', 'base_model.model.model.layers.12.self_attn.o_proj.SCB', 'base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.29.self_attn.k_proj.weight', 'base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.35.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.35.self_attn.k_proj.SCB', 'base_model.model.model.layers.15.mlp.gate_proj.weight', 'base_model.model.model.layers.26.self_attn.k_proj.SCB', 'base_model.model.model.layers.9.self_attn.v_proj.SCB', 'base_model.model.model.layers.32.self_attn.v_proj.weight', 'base_model.model.model.layers.34.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.19.self_attn.q_proj.SCB', 'base_model.model.model.layers.25.self_attn.k_proj.weight', 'base_model.model.model.layers.12.self_attn.v_proj.weight', 'base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.11.mlp.gate_proj.weight', 'base_model.model.model.layers.24.mlp.gate_proj.SCB', 'base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.27.self_attn.v_proj.SCB', 'base_model.model.model.layers.17.self_attn.v_proj.SCB', 'base_model.model.model.layers.27.post_attention_layernorm.weight', 'base_model.model.model.layers.32.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.33.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.33.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.21.mlp.up_proj.SCB', 'base_model.model.model.layers.2.mlp.up_proj.SCB', 'base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.24.mlp.up_proj.SCB', 'base_model.model.model.layers.25.self_attn.v_proj.weight', 'base_model.model.model.layers.14.mlp.down_proj.weight', 'base_model.model.model.layers.22.self_attn.o_proj.weight', 'base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.5.mlp.gate_proj.weight', 'base_model.model.model.layers.25.post_attention_layernorm.weight', 'base_model.model.model.layers.11.self_attn.q_proj.weight', 'base_model.model.model.layers.15.self_attn.v_proj.weight', 'base_model.model.model.layers.6.self_attn.q_proj.weight', 'base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.21.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.13.mlp.down_proj.SCB', 'base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.17.input_layernorm.weight', 'base_model.model.model.layers.34.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.4.self_attn.v_proj.SCB', 'base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.19.self_attn.q_proj.weight', 'base_model.model.model.layers.4.self_attn.k_proj.weight', 'base_model.model.model.layers.33.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.35.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.35.self_attn.o_proj.SCB', 'base_model.model.model.layers.36.post_attention_layernorm.weight', 'base_model.model.model.layers.4.mlp.gate_proj.weight', 'base_model.model.model.layers.38.mlp.up_proj.SCB', 'base_model.model.model.layers.20.mlp.down_proj.weight', 'base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.31.input_layernorm.weight', 'base_model.model.model.layers.11.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.3.mlp.up_proj.weight', 'base_model.model.model.layers.20.mlp.up_proj.SCB', 'base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.15.mlp.down_proj.weight', 'base_model.model.model.layers.34.mlp.up_proj.weight', 'base_model.model.model.layers.24.mlp.down_proj.weight', 'base_model.model.model.layers.27.mlp.down_proj.weight', 'base_model.model.model.layers.36.mlp.gate_proj.SCB', 'base_model.model.model.layers.18.self_attn.o_proj.SCB', 'base_model.model.model.layers.26.mlp.down_proj.SCB', 'base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.17.mlp.up_proj.weight', 'base_model.model.model.layers.26.self_attn.o_proj.SCB', 'base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.39.self_attn.k_proj.SCB', 'base_model.model.model.layers.19.mlp.gate_proj.SCB', 'base_model.model.model.layers.27.mlp.gate_proj.weight', 'base_model.model.model.layers.38.self_attn.o_proj.SCB', 'base_model.model.model.norm.weight', 'base_model.model.model.layers.8.input_layernorm.weight', 'base_model.model.model.layers.18.self_attn.k_proj.weight', 'base_model.model.model.layers.25.mlp.up_proj.weight', 'base_model.model.model.layers.18.mlp.gate_proj.SCB', 'base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.9.mlp.up_proj.SCB', 'base_model.model.model.layers.12.self_attn.q_proj.SCB', 'base_model.model.model.layers.33.self_attn.q_proj.weight', 'base_model.model.model.layers.5.post_attention_layernorm.weight', 'base_model.model.model.layers.10.self_attn.k_proj.SCB', 'base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.17.mlp.gate_proj.SCB', 'base_model.model.model.layers.4.mlp.up_proj.weight', 'base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.18.self_attn.q_proj.weight', 'base_model.model.model.layers.1.input_layernorm.weight', 'base_model.model.model.layers.30.mlp.down_proj.SCB', 'base_model.model.model.layers.27.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.34.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.35.mlp.gate_proj.SCB', 'base_model.model.model.layers.5.self_attn.o_proj.weight', 'base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.34.self_attn.k_proj.SCB', 'base_model.model.model.layers.6.self_attn.k_proj.SCB', 'base_model.model.model.layers.11.mlp.down_proj.weight', 'base_model.model.model.layers.0.mlp.down_proj.SCB', 'base_model.model.model.layers.6.mlp.gate_proj.weight', 'base_model.model.model.layers.33.self_attn.v_proj.weight', 'base_model.model.model.layers.22.mlp.down_proj.weight', 'base_model.model.model.layers.26.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.0.self_attn.o_proj.weight', 'base_model.model.model.layers.25.self_attn.o_proj.SCB', 'base_model.model.model.layers.6.mlp.gate_proj.SCB', 'base_model.model.model.layers.25.mlp.gate_proj.SCB', 'base_model.model.model.layers.14.self_attn.o_proj.weight', 'base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.6.self_attn.k_proj.weight', 'base_model.model.model.layers.30.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.25.mlp.up_proj.SCB', 'base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.4.input_layernorm.weight', 'base_model.model.model.layers.37.self_attn.v_proj.SCB', 'base_model.model.model.layers.2.self_attn.o_proj.weight', 'base_model.model.model.layers.35.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.39.mlp.gate_proj.weight', 'base_model.model.model.layers.18.self_attn.k_proj.SCB', 'base_model.model.model.layers.34.self_attn.q_proj.SCB', 'base_model.model.model.layers.34.self_attn.o_proj.weight', 'base_model.model.model.layers.34.mlp.gate_proj.SCB', 'base_model.model.model.layers.0.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.17.self_attn.q_proj.SCB', 'base_model.model.model.layers.25.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.27.self_attn.q_proj.SCB', 'base_model.model.model.layers.38.self_attn.v_proj.SCB', 'base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.23.mlp.gate_proj.weight', 'base_model.model.model.layers.22.self_attn.o_proj.SCB', 'base_model.model.model.layers.7.input_layernorm.weight', 'base_model.model.model.layers.20.self_attn.v_proj.weight', 'base_model.model.model.layers.17.self_attn.q_proj.weight', 'base_model.model.model.layers.6.self_attn.o_proj.SCB', 'base_model.model.model.layers.33.self_attn.o_proj.SCB', 'base_model.model.model.layers.24.self_attn.k_proj.SCB', 'base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.37.self_attn.q_proj.SCB', 'base_model.model.model.layers.20.input_layernorm.weight', 'base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.6.self_attn.q_proj.SCB', 'base_model.model.model.layers.1.self_attn.k_proj.weight', 'base_model.model.model.layers.20.self_attn.o_proj.SCB', 'base_model.model.model.layers.39.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.39.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.12.mlp.up_proj.weight', 'base_model.model.model.layers.35.mlp.up_proj.SCB', 'base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.16.input_layernorm.weight', 'base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.13.mlp.gate_proj.weight', 'base_model.model.model.layers.38.post_attention_layernorm.weight', 'base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.32.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.1.self_attn.q_proj.SCB', 'base_model.model.model.layers.2.mlp.down_proj.weight', 'base_model.model.model.layers.15.self_attn.v_proj.SCB', 'base_model.model.model.layers.38.mlp.down_proj.weight', 'base_model.model.model.layers.11.mlp.gate_proj.SCB', 'base_model.model.model.layers.14.self_attn.k_proj.SCB', 'base_model.model.model.layers.39.self_attn.k_proj.weight', 'base_model.model.model.layers.1.self_attn.k_proj.SCB', 'base_model.model.model.layers.36.self_attn.o_proj.weight', 'base_model.model.model.layers.3.self_attn.v_proj.SCB', 'base_model.model.model.layers.7.self_attn.v_proj.SCB', 'base_model.model.model.layers.2.self_attn.o_proj.SCB', 'base_model.model.model.layers.8.self_attn.k_proj.SCB', 'base_model.model.model.layers.7.self_attn.q_proj.SCB', 'base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.39.mlp.gate_proj.SCB', 'base_model.model.model.layers.7.mlp.gate_proj.weight', 'base_model.model.model.layers.7.mlp.gate_proj.SCB', 'base_model.model.model.layers.12.self_attn.q_proj.weight', 'base_model.model.model.layers.32.self_attn.q_proj.weight', 'base_model.model.model.layers.19.self_attn.v_proj.weight', 'base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.7.self_attn.o_proj.weight', 'base_model.model.model.layers.8.mlp.down_proj.weight', 'base_model.model.model.layers.24.post_attention_layernorm.weight', 'base_model.model.model.layers.17.mlp.down_proj.SCB', 'base_model.model.model.layers.12.mlp.up_proj.SCB', 'base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.28.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.9.self_attn.v_proj.weight', 'base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.21.post_attention_layernorm.weight', 'base_model.model.model.layers.38.self_attn.o_proj.weight', 'base_model.model.model.layers.10.self_attn.v_proj.SCB', 'base_model.model.model.layers.19.post_attention_layernorm.weight', 'base_model.model.model.layers.9.post_attention_layernorm.weight', 'base_model.model.model.layers.30.post_attention_layernorm.weight', 'base_model.model.model.layers.32.self_attn.k_proj.weight', 'base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.13.mlp.down_proj.weight', 'base_model.model.model.layers.27.self_attn.o_proj.weight', 'base_model.model.model.layers.30.self_attn.k_proj.SCB', 'base_model.model.model.layers.29.self_attn.v_proj.SCB', 'base_model.model.model.layers.33.mlp.gate_proj.weight', 'base_model.model.model.layers.1.mlp.up_proj.weight', 'base_model.model.model.layers.16.self_attn.q_proj.SCB', 'base_model.model.model.layers.12.self_attn.k_proj.SCB', 'base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.37.self_attn.k_proj.SCB', 'base_model.model.model.layers.28.mlp.gate_proj.weight', 'base_model.model.model.layers.16.self_attn.v_proj.weight', 'base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.20.post_attention_layernorm.weight', 'base_model.model.model.layers.21.self_attn.o_proj.weight', 'base_model.model.model.layers.8.mlp.up_proj.SCB', 'base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight']

• This IS expected if you are initializing LlamaForCausalLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
• This IS NOT expected if you are initializing LlamaForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  Some weights of LlamaForCausalLM were not initialized from the model checkpoint at declare-lab/flacuna-13b-v1.0 and are newly initialized: ['layers.23.post_attention_layernorm.weight', 'layers.3.self_attn.k_proj.weight', 'layers.2.post_attention_layernorm.weight', 'layers.28.self_attn.v_proj.weight', 'layers.22.self_attn.k_proj.weight', 'layers.29.self_attn.q_proj.weight', 'layers.24.mlp.gate_proj.weight', 'layers.12.mlp.down_proj.weight', 'layers.1.mlp.gate_proj.weight', 'layers.22.mlp.up_proj.weight', 'layers.16.self_attn.o_proj.weight', 'layers.29.self_attn.o_proj.weight', 'layers.36.self_attn.o_proj.weight', 'layers.27.post_attention_layernorm.weight', 'layers.35.self_attn.rotary_emb.inv_freq', 'layers.6.self_attn.q_proj.weight', 'layers.34.post_attention_layernorm.weight', 'layers.11.self_attn.k_proj.weight', 'layers.29.post_attention_layernorm.weight', 'layers.28.self_attn.o_proj.weight', 'layers.1.self_attn.rotary_emb.inv_freq', 'layers.6.mlp.down_proj.weight', 'layers.13.self_attn.rotary_emb.inv_freq', 'layers.5.mlp.up_proj.weight', 'layers.10.self_attn.rotary_emb.inv_freq', 'layers.9.self_attn.v_proj.weight', 'layers.20.self_attn.q_proj.weight', 'layers.12.self_attn.o_proj.weight', 'layers.11.mlp.up_proj.weight', 'layers.23.mlp.gate_proj.weight', 'layers.1.input_layernorm.weight', 'layers.38.input_layernorm.weight', 'layers.21.self_attn.rotary_emb.inv_freq', 'layers.3.mlp.down_proj.weight', 'layers.36.mlp.gate_proj.weight', 'layers.15.input_layernorm.weight', 'layers.4.self_attn.v_proj.weight', 'layers.23.mlp.up_proj.weight', 'layers.39.input_layernorm.weight', 'layers.17.self_attn.q_proj.weight', 'layers.24.self_attn.k_proj.weight', 'layers.34.mlp.up_proj.weight', 'layers.19.self_attn.v_proj.weight', 'layers.31.self_attn.q_proj.weight', 'layers.18.self_attn.o_proj.weight', 'layers.17.mlp.down_proj.weight', 'layers.37.self_attn.v_proj.weight', 'layers.36.mlp.down_proj.weight', 'layers.26.post_attention_layernorm.weight', 'layers.5.self_attn.rotary_emb.inv_freq', 'layers.16.input_layernorm.weight', 'layers.36.mlp.up_proj.weight', 'layers.34.mlp.gate_proj.weight', 'layers.27.input_layernorm.weight', 'layers.21.input_layernorm.weight', 'layers.20.self_attn.rotary_emb.inv_freq', 'layers.16.self_attn.rotary_emb.inv_freq', 'layers.4.self_attn.o_proj.weight', 'layers.4.mlp.down_proj.weight', 'layers.38.self_attn.k_proj.weight', 'layers.8.input_layernorm.weight', 'layers.4.self_attn.q_proj.weight', 'layers.11.input_layernorm.weight', 'layers.35.self_attn.o_proj.weight', 'layers.25.mlp.gate_proj.weight', 'layers.10.self_attn.q_proj.weight', 'norm.weight', 'layers.27.self_attn.rotary_emb.inv_freq', 'layers.15.post_attention_layernorm.weight', 'layers.29.mlp.down_proj.weight', 'layers.31.input_layernorm.weight', 'layers.18.self_attn.q_proj.weight', 'layers.37.mlp.down_proj.weight', 'layers.16.post_attention_layernorm.weight', 'layers.6.self_attn.o_proj.weight', 'layers.2.mlp.down_proj.weight', 'layers.4.self_attn.k_proj.weight', 'layers.29.input_layernorm.weight', 'layers.30.mlp.gate_proj.weight', 'layers.25.input_layernorm.weight', 'layers.3.self_attn.q_proj.weight', 'layers.25.self_attn.q_proj.weight', 'layers.14.self_attn.k_proj.weight', 'layers.8.self_attn.q_proj.weight', 'layers.23.self_attn.o_proj.weight', 'layers.5.input_layernorm.weight', 'layers.8.self_attn.rotary_emb.inv_freq', 'layers.12.input_layernorm.weight', 'layers.32.mlp.gate_proj.weight', 'layers.39.mlp.up_proj.weight', 'layers.8.self_attn.k_proj.weight', 'layers.6.mlp.gate_proj.weight', 'layers.28.self_attn.rotary_emb.inv_freq', 'layers.9.mlp.gate_proj.weight', 'layers.38.mlp.gate_proj.weight', 'layers.9.self_attn.k_proj.weight', 'layers.20.self_attn.v_proj.weight', 'layers.17.self_attn.rotary_emb.inv_freq', 'layers.18.mlp.gate_proj.weight', 'layers.15.self_attn.q_proj.weight', 'layers.10.mlp.down_proj.weight', 'layers.7.input_layernorm.weight', 'layers.24.post_attention_layernorm.weight', 'layers.18.self_attn.rotary_emb.inv_freq', 'layers.30.self_attn.v_proj.weight', 'layers.5.self_attn.q_proj.weight', 'layers.30.input_layernorm.weight', 'layers.13.self_attn.k_proj.weight', 'layers.17.mlp.up_proj.weight', 'layers.7.self_attn.k_proj.weight', 'layers.28.mlp.down_proj.weight', 'layers.34.self_attn.q_proj.weight', 'layers.26.mlp.up_proj.weight', 'layers.7.mlp.down_proj.weight', 'layers.1.mlp.down_proj.weight', 'layers.15.mlp.gate_proj.weight', 'layers.34.self_attn.o_proj.weight', 'layers.21.post_attention_layernorm.weight', 'layers.26.self_attn.q_proj.weight', 'layers.36.self_attn.k_proj.weight', 'layers.10.self_attn.o_proj.weight', 'layers.17.mlp.gate_proj.weight', 'layers.37.self_attn.rotary_emb.inv_freq', 'layers.3.input_layernorm.weight', 'layers.17.self_attn.v_proj.weight', 'layers.10.input_layernorm.weight', 'layers.23.mlp.down_proj.weight', 'layers.13.self_attn.v_proj.weight', 'layers.14.mlp.up_proj.weight', 'layers.39.mlp.down_proj.weight', 'layers.27.self_attn.q_proj.weight', 'layers.31.mlp.down_proj.weight', 'layers.25.self_attn.k_proj.weight', 'layers.28.mlp.gate_proj.weight', 'layers.0.mlp.up_proj.weight', 'layers.15.mlp.up_proj.weight', 'layers.9.self_attn.o_proj.weight', 'layers.19.self_attn.o_proj.weight', 'embed_tokens.weight', 'layers.30.self_attn.k_proj.weight', 'layers.18.self_attn.k_proj.weight', 'layers.39.self_attn.q_proj.weight', 'layers.27.mlp.down_proj.weight', 'layers.14.self_attn.v_proj.weight', 'layers.35.mlp.gate_proj.weight', 'layers.25.self_attn.rotary_emb.inv_freq', 'layers.38.mlp.down_proj.weight', 'layers.13.mlp.up_proj.weight', 'layers.8.mlp.gate_proj.weight', 'layers.32.mlp.down_proj.weight', 'layers.31.self_attn.k_proj.weight', 'layers.11.mlp.down_proj.weight', 'layers.28.mlp.up_proj.weight', 'layers.22.self_attn.q_proj.weight', 'layers.29.self_attn.rotary_emb.inv_freq', 'layers.34.self_attn.k_proj.weight', 'layers.8.mlp.up_proj.weight', 'layers.14.self_attn.rotary_emb.inv_freq', 'layers.1.post_attention_layernorm.weight', 'layers.6.self_attn.k_proj.weight', 'layers.32.mlp.up_proj.weight', 'layers.9.mlp.down_proj.weight', 'layers.27.mlp.up_proj.weight', 'layers.30.self_attn.rotary_emb.inv_freq', 'layers.19.self_attn.q_proj.weight', 'layers.25.mlp.up_proj.weight', 'layers.32.self_attn.o_proj.weight', 'layers.1.self_attn.o_proj.weight', 'layers.9.post_attention_layernorm.weight', 'layers.36.self_attn.q_proj.weight', 'layers.2.self_attn.rotary_emb.inv_freq', 'layers.14.input_layernorm.weight', 'layers.6.self_attn.v_proj.weight', 'layers.35.self_attn.k_proj.weight', 'layers.7.self_attn.o_proj.weight', 'layers.34.mlp.down_proj.weight', 'layers.18.mlp.down_proj.weight', 'layers.5.mlp.down_proj.weight', 'layers.27.mlp.gate_proj.weight', 'layers.30.mlp.down_proj.weight', 'layers.37.self_attn.o_proj.weight', 'layers.11.self_attn.q_proj.weight', 'layers.31.self_attn.o_proj.weight', 'layers.33.post_attention_layernorm.weight', 'layers.2.mlp.gate_proj.weight', 'layers.32.post_attention_layernorm.weight', 'layers.9.self_attn.q_proj.weight', 'layers.18.self_attn.v_proj.weight', 'layers.15.mlp.down_proj.weight', 'layers.21.self_attn.v_proj.weight', 'layers.26.self_attn.rotary_emb.inv_freq', 'layers.37.mlp.up_proj.weight', 'layers.2.input_layernorm.weight', 'layers.9.mlp.up_proj.weight', 'layers.34.self_attn.v_proj.weight', 'layers.24.self_attn.v_proj.weight', 'layers.19.mlp.gate_proj.weight', 'layers.16.mlp.down_proj.weight', 'layers.29.mlp.up_proj.weight', 'layers.5.self_attn.v_proj.weight', 'layers.27.self_attn.o_proj.weight', 'layers.22.self_attn.v_proj.weight', 'layers.9.input_layernorm.weight', 'layers.14.post_attention_layernorm.weight', 'layers.5.self_attn.o_proj.weight', 'layers.13.mlp.gate_proj.weight', 'layers.12.mlp.up_proj.weight', 'layers.18.post_attention_layernorm.weight', 'layers.16.mlp.gate_proj.weight', 'layers.11.self_attn.o_proj.weight', 'layers.7.self_attn.q_proj.weight', 'layers.11.self_attn.rotary_emb.inv_freq', 'layers.31.mlp.gate_proj.weight', 'layers.37.mlp.gate_proj.weight', 'layers.29.mlp.gate_proj.weight', 'layers.33.self_attn.o_proj.weight', 'layers.16.self_attn.q_proj.weight', 'layers.20.input_layernorm.weight', 'layers.21.self_attn.k_proj.weight', 'layers.8.self_attn.o_proj.weight', 'layers.28.self_attn.q_proj.weight', 'layers.0.self_attn.v_proj.weight', 'layers.32.self_attn.v_proj.weight', 'layers.22.self_attn.o_proj.weight', 'layers.27.self_attn.v_proj.weight', 'layers.19.input_layernorm.weight', 'layers.24.mlp.down_proj.weight', 'layers.12.post_attention_layernorm.weight', 'layers.37.self_attn.q_proj.weight', 'layers.21.self_attn.q_proj.weight', 'layers.34.self_attn.rotary_emb.inv_freq', 'layers.22.mlp.down_proj.weight', 'layers.23.self_attn.rotary_emb.inv_freq', 'layers.34.input_layernorm.weight', 'layers.12.self_attn.rotary_emb.inv_freq', 'layers.4.mlp.up_proj.weight', 'layers.37.input_layernorm.weight', 'layers.35.self_attn.q_proj.weight', 'layers.38.post_attention_layernorm.weight', 'layers.33.self_attn.rotary_emb.inv_freq', 'layers.21.self_attn.o_proj.weight', 'layers.28.input_layernorm.weight', 'layers.35.self_attn.v_proj.weight', 'layers.2.self_attn.o_proj.weight', 'layers.32.self_attn.rotary_emb.inv_freq', 'layers.21.mlp.up_proj.weight', 'layers.26.self_attn.v_proj.weight', 'layers.38.self_attn.q_proj.weight', 'layers.4.input_layernorm.weight', 'layers.24.mlp.up_proj.weight', 'layers.30.post_attention_layernorm.weight', 'layers.19.self_attn.rotary_emb.inv_freq', 'layers.20.mlp.down_proj.weight', 'layers.27.self_attn.k_proj.weight', 'layers.19.post_attention_layernorm.weight', 'layers.6.post_attention_layernorm.weight', 'layers.24.input_layernorm.weight', 'lm_head.weight', 'layers.2.mlp.up_proj.weight', 'layers.9.self_attn.rotary_emb.inv_freq', 'layers.1.self_attn.q_proj.weight', 'layers.35.input_layernorm.weight', 'layers.22.mlp.gate_proj.weight', 'layers.20.post_attention_layernorm.weight', 'layers.22.self_attn.rotary_emb.inv_freq', 'layers.12.mlp.gate_proj.weight', 'layers.11.mlp.gate_proj.weight', 'layers.18.input_layernorm.weight', 'layers.1.self_attn.k_proj.weight', 'layers.7.post_attention_layernorm.weight', 'layers.37.post_attention_layernorm.weight', 'layers.31.self_attn.rotary_emb.inv_freq', 'layers.3.mlp.up_proj.weight', 'layers.19.mlp.down_proj.weight', 'layers.36.self_attn.rotary_emb.inv_freq', 'layers.3.mlp.gate_proj.weight', 'layers.14.mlp.down_proj.weight', 'layers.36.input_layernorm.weight', 'layers.39.mlp.gate_proj.weight', 'layers.8.mlp.down_proj.weight', 'layers.0.self_attn.q_proj.weight', 'layers.35.mlp.up_proj.weight', 'layers.6.input_layernorm.weight', 'layers.23.self_attn.v_proj.weight', 'layers.25.post_attention_layernorm.weight', 'layers.29.self_attn.v_proj.weight', 'layers.28.post_attention_layernorm.weight', 'layers.36.post_attention_layernorm.weight', 'layers.32.self_attn.q_proj.weight', 'layers.32.self_attn.k_proj.weight', 'layers.38.self_attn.rotary_emb.inv_freq', 'layers.39.self_attn.rotary_emb.inv_freq', 'layers.6.mlp.up_proj.weight', 'layers.1.mlp.up_proj.weight', 'layers.33.input_layernorm.weight', 'layers.30.mlp.up_proj.weight', 'layers.7.mlp.gate_proj.weight', 'layers.31.post_attention_layernorm.weight', 'layers.2.self_attn.v_proj.weight', 'layers.21.mlp.down_proj.weight', 'layers.20.mlp.gate_proj.weight', 'layers.39.self_attn.v_proj.weight', 'layers.14.mlp.gate_proj.weight', 'layers.33.self_attn.k_proj.weight', 'layers.10.mlp.gate_proj.weight', 'layers.38.self_attn.v_proj.weight', 'layers.0.self_attn.k_proj.weight', 'layers.31.mlp.up_proj.weight', 'layers.35.post_attention_layernorm.weight', 'layers.25.self_attn.v_proj.weight', 'layers.4.mlp.gate_proj.weight', 'layers.12.self_attn.k_proj.weight', 'layers.33.self_attn.q_proj.weight', 'layers.4.post_attention_layernorm.weight', 'layers.19.mlp.up_proj.weight', 'layers.26.self_attn.o_proj.weight', 'layers.35.mlp.down_proj.weight', 'layers.3.post_attention_layernorm.weight', 'layers.17.self_attn.o_proj.weight', 'layers.10.self_attn.k_proj.weight', 'layers.2.self_attn.q_proj.weight', 'layers.26.mlp.down_proj.weight', 'layers.29.self_attn.k_proj.weight', 'layers.28.self_attn.k_proj.weight', 'layers.11.post_attention_layernorm.weight', 'layers.16.self_attn.v_proj.weight', 'layers.13.post_attention_layernorm.weight', 'layers.0.self_attn.rotary_emb.inv_freq', 'layers.36.self_attn.v_proj.weight', 'layers.33.mlp.up_proj.weight', 'layers.0.mlp.gate_proj.weight', 'layers.23.self_attn.q_proj.weight', 'layers.20.mlp.up_proj.weight', 'layers.32.input_layernorm.weight', 'layers.7.self_attn.rotary_emb.inv_freq', 'layers.7.mlp.up_proj.weight', 'layers.37.self_attn.k_proj.weight', 'layers.14.self_attn.q_proj.weight', 'layers.26.input_layernorm.weight', 'layers.22.input_layernorm.weight', 'layers.5.post_attention_layernorm.weight', 'layers.15.self_attn.v_proj.weight', 'layers.3.self_attn.rotary_emb.inv_freq', 'layers.1.self_attn.v_proj.weight', 'layers.8.post_attention_layernorm.weight', 'layers.15.self_attn.o_proj.weight', 'layers.39.self_attn.o_proj.weight', 'layers.17.input_layernorm.weight', 'layers.14.self_attn.o_proj.weight', 'layers.20.self_attn.k_proj.weight', 'layers.25.mlp.down_proj.weight', 'layers.3.self_attn.v_proj.weight', 'layers.33.self_attn.v_proj.weight', 'layers.33.mlp.gate_proj.weight', 'layers.20.self_attn.o_proj.weight', 'layers.26.mlp.gate_proj.weight', 'layers.13.self_attn.q_proj.weight', 'layers.13.self_attn.o_proj.weight', 'layers.31.self_attn.v_proj.weight', 'layers.21.mlp.gate_proj.weight', 'layers.0.mlp.down_proj.weight', 'layers.22.post_attention_layernorm.weight', 'layers.19.self_attn.k_proj.weight', 'layers.24.self_attn.q_proj.weight', 'layers.38.mlp.up_proj.weight', 'layers.0.self_attn.o_proj.weight', 'layers.38.self_attn.o_proj.weight', 'layers.16.self_attn.k_proj.weight', 'layers.17.self_attn.k_proj.weight', 'layers.5.self_attn.k_proj.weight', 'layers.12.self_attn.v_proj.weight', 'layers.13.mlp.down_proj.weight', 'layers.0.post_attention_layernorm.weight', 'layers.25.self_attn.o_proj.weight', 'layers.23.self_attn.k_proj.weight', 'layers.30.self_attn.q_proj.weight', 'layers.33.mlp.down_proj.weight', 'layers.8.self_attn.v_proj.weight', 'layers.30.self_attn.o_proj.weight', 'layers.4.self_attn.rotary_emb.inv_freq', 'layers.10.post_attention_layernorm.weight', 'layers.17.post_attention_layernorm.weight', 'layers.5.mlp.gate_proj.weight', 'layers.39.post_attention_layernorm.weight', 'layers.0.input_layernorm.weight', 'layers.16.mlp.up_proj.weight', 'layers.24.self_attn.rotary_emb.inv_freq', 'layers.11.self_attn.v_proj.weight', 'layers.18.mlp.up_proj.weight', 'layers.12.self_attn.q_proj.weight', 'layers.2.self_attn.k_proj.weight', 'layers.26.self_attn.k_proj.weight', 'layers.23.input_layernorm.weight', 'layers.13.input_layernorm.weight', 'layers.10.mlp.up_proj.weight', 'layers.7.self_attn.v_proj.weight', 'layers.6.self_attn.rotary_emb.inv_freq', 'layers.3.self_attn.o_proj.weight', 'layers.24.self_attn.o_proj.weight', 'layers.39.self_attn.k_proj.weight', 'layers.15.self_attn.k_proj.weight', 'layers.10.self_attn.v_proj.weight', 'layers.15.self_attn.rotary_emb.inv_freq']`
  

from flacuna.

This warning should come when you try to initialize LlamaForCausalLMdirectly from "declare-lab/flacuna-13b-v1.0". In flacuna.py, we first initialize Llama from "TheBloke/vicuna-13B-1.1-HF" and then load the LoRA weights from our checkpoint. Otherwise, the state dict keys are not going to match.

Can you also post the full code snippet?

from flacuna.

import torch from transformers import LlamaForCausalLM, LlamaTokenizer base_model = "TheBloke/vicuna-13B-1.1-HF" tokenizer = LlamaTokenizer.from_pretrained(base_model) model = LlamaForCausalLM.from_pretrained(base_model,torch_dtype=torch.float16, device_map="auto")

it worked after closing instance and opening again. I did not understand what was wrong, but now it is all okay.
Thank you so much

from flacuna.