Hugging Face's logo

TheBloke
/
dolphin-2.7-mixtral-8x7b-GPTQ

Text Generation
Transformers
Safetensors
English
mixtral
conversational
text-generation-inference
4-bit precision
gptq
Model card Files Community
4

Some weights of the model checkpoint at TheBloke/dolphin-2.7-mixtral-8x7b-GPTQ were not used when initializing MixtralForCausalLM

#4
by cupidstunt72 - opened
Discussion
cupidstunt72

Hi I'm getting the below warning... I'm using this model to work with various news articles, so I feel like it's relative and a problem - but I'm very unclear on how to resolve as I think I followed the right steps to query and execute this?

Some weights of the model checkpoint at TheBloke/dolphin-2.7-mixtral-8x7b-GPTQ were not used when initializing MixtralForCausalLM:
['model.layers.0.block_sparse_moe.experts.0.w1.bias', 'model.layers.0.block_sparse_moe.experts.0.w2.bias', 'model.layers.0.block_sparse_moe.experts.0.w3.bias', 'model.layers.0.block_sparse_moe.experts.1.w1.bias', 'model.layers.0.block_sparse_moe.experts.1.w2.bias', 'model.layers.0.block_sparse_moe.experts.1.w3.bias', 'model.layers.0.block_sparse_moe.experts.2.w1.bias', 'model.layers.0.block_sparse_moe.experts.2.w2.bias', 'model.layers.0.block_sparse_moe.experts.2.w3.bias', 'model.layers.0.block_sparse_moe.experts.3.w1.bias', 'model.layers.0.block_sparse_moe.experts.3.w2.bias', 'model.layers.0.block_sparse_moe.experts.3.w3.bias', 'model.layers.0.block_sparse_moe.experts.4.w1.bias', 'model.layers.0.block_sparse_moe.experts.4.w2.bias', 'model.layers.0.block_sparse_moe.experts.4.w3.bias', 'model.layers.0.block_sparse_moe.experts.5.w1.bias', 'model.layers.0.block_sparse_moe.experts.5.w2.bias', 'model.layers.0.block_sparse_moe.experts.5.w3.bias', 'model.layers.0.block_sparse_moe.experts.6.w1.bias', 'model.layers.0.block_sparse_moe.experts.6.w2.bias', 'model.layers.0.block_sparse_moe.experts.6.w3.bias', 'model.layers.0.block_sparse_moe.experts.7.w1.bias', 'model.layers.0.block_sparse_moe.experts.7.w2.bias', 'model.layers.0.block_sparse_moe.experts.7.w3.bias', 'model.layers.0.self_attn.k_proj.bias', 'model.layers.0.self_attn.o_proj.bias', 'model.layers.0.self_attn.q_proj.bias', 'model.layers.0.self_attn.v_proj.bias', 'model.layers.1.block_sparse_moe.experts.0.w1.bias', 'model.layers.1.block_sparse_moe.experts.0.w2.bias', 'model.layers.1.block_sparse_moe.experts.0.w3.bias', 'model.layers.1.block_sparse_moe.experts.1.w1.bias', 'model.layers.1.block_sparse_moe.experts.1.w2.bias', 'model.layers.1.block_sparse_moe.experts.1.w3.bias', 'model.layers.1.block_sparse_moe.experts.2.w1.bias', 'model.layers.1.block_sparse_moe.experts.2.w2.bias', 'model.layers.1.block_sparse_moe.experts.2.w3.bias', 'model.layers.1.block_sparse_moe.experts.3.w1.bias', 'model.layers.1.block_sparse_moe.experts.3.w2.bias', 'model.layers.1.block_sparse_moe.experts.3.w3.bias', 'model.layers.1.block_sparse_moe.experts.4.w1.bias', 'model.layers.1.block_sparse_moe.experts.4.w2.bias', 'model.layers.1.block_sparse_moe.experts.4.w3.bias', 'model.layers.1.block_sparse_moe.experts.5.w1.bias', 'model.layers.1.block_sparse_moe.experts.5.w2.bias', 'model.layers.1.block_sparse_moe.experts.5.w3.bias', 'model.layers.1.block_sparse_moe.experts.6.w1.bias', 'model.layers.1.block_sparse_moe.experts.6.w2.bias', 'model.layers.1.block_sparse_moe.experts.6.w3.bias', 'model.layers.1.block_sparse_moe.experts.7.w1.bias', 'model.layers.1.block_sparse_moe.experts.7.w2.bias', 'model.layers.1.block_sparse_moe.experts.7.w3.bias', 'model.layers.1.self_attn.k_proj.bias', 'model.layers.1.self_attn.o_proj.bias', 'model.layers.1.self_attn.q_proj.bias', 'model.layers.1.self_attn.v_proj.bias', 'model.layers.10.block_sparse_moe.experts.0.w1.bias', 'model.layers.10.block_sparse_moe.experts.0.w2.bias', 'model.layers.10.block_sparse_moe.experts.0.w3.bias', 'model.layers.10.block_sparse_moe.experts.1.w1.bias', 'model.layers.10.block_sparse_moe.experts.1.w2.bias', 'model.layers.10.block_sparse_moe.experts.1.w3.bias', 'model.layers.10.block_sparse_moe.experts.2.w1.bias', 'model.layers.10.block_sparse_moe.experts.2.w2.bias', 'model.layers.10.block_sparse_moe.experts.2.w3.bias', 'model.layers.10.block_sparse_moe.experts.3.w1.bias', 'model.layers.10.block_sparse_moe.experts.3.w2.bias', 'model.layers.10.block_sparse_moe.experts.3.w3.bias', 'model.layers.10.block_sparse_moe.experts.4.w1.bias', 'model.layers.10.block_sparse_moe.experts.4.w2.bias', 'model.layers.10.block_sparse_moe.experts.4.w3.bias', 'model.layers.10.block_sparse_moe.experts.5.w1.bias', 'model.layers.10.block_sparse_moe.experts.5.w2.bias', 'model.layers.10.block_sparse_moe.experts.5.w3.bias', 'model.layers.10.block_sparse_moe.experts.6.w1.bias', 'model.layers.10.block_sparse_moe.experts.6.w2.bias', 'model.layers.10.block_sparse_moe.experts.6.w3.bias', 'model.layers.10.block_sparse_moe.experts.7.w1.bias', 'model.layers.10.block_sparse_moe.experts.7.w2.bias', 'model.layers.10.block_sparse_moe.experts.7.w3.bias', 'model.layers.10.self_attn.k_proj.bias', 'model.layers.10.self_attn.o_proj.bias', 'model.layers.10.self_attn.q_proj.bias', 'model.layers.10.self_attn.v_proj.bias', 'model.layers.11.block_sparse_moe.experts.0.w1.bias', 'model.layers.11.block_sparse_moe.experts.0.w2.bias', 'model.layers.11.block_sparse_moe.experts.0.w3.bias', 'model.layers.11.block_sparse_moe.experts.1.w1.bias', 'model.layers.11.block_sparse_moe.experts.1.w2.bias', 'model.layers.11.block_sparse_moe.experts.1.w3.bias', 'model.layers.11.block_sparse_moe.experts.2.w1.bias', 'model.layers.11.block_sparse_moe.experts.2.w2.bias', 'model.layers.11.block_sparse_moe.experts.2.w3.bias', 'model.layers.11.block_sparse_moe.experts.3.w1.bias', 'model.layers.11.block_sparse_moe.experts.3.w2.bias', 'model.layers.11.block_sparse_moe.experts.3.w3.bias', 'model.layers.11.block_sparse_moe.experts.4.w1.bias', 'model.layers.11.block_sparse_moe.experts.4.w2.bias', 'model.layers.11.block_sparse_moe.experts.4.w3.bias', 'model.layers.11.block_sparse_moe.experts.5.w1.bias', 'model.layers.11.block_sparse_moe.experts.5.w2.bias', 'model.layers.11.block_sparse_moe.experts.5.w3.bias', 'model.layers.11.block_sparse_moe.experts.6.w1.bias', 'model.layers.11.block_sparse_moe.experts.6.w2.bias', 'model.layers.11.block_sparse_moe.experts.6.w3.bias', 'model.layers.11.block_sparse_moe.experts.7.w1.bias', 'model.layers.11.block_sparse_moe.experts.7.w2.bias', 'model.layers.11.block_sparse_moe.experts.7.w3.bias', 'model.layers.11.self_attn.k_proj.bias', 'model.layers.11.self_attn.o_proj.bias', 'model.layers.11.self_attn.q_proj.bias', 'model.layers.11.self_attn.v_proj.bias', 'model.layers.12.block_sparse_moe.experts.0.w1.bias', 'model.layers.12.block_sparse_moe.experts.0.w2.bias', 'model.layers.12.block_sparse_moe.experts.0.w3.bias', 'model.layers.12.block_sparse_moe.experts.1.w1.bias', 'model.layers.12.block_sparse_moe.experts.1.w2.bias', 'model.layers.12.block_sparse_moe.experts.1.w3.bias', 'model.layers.12.block_sparse_moe.experts.2.w1.bias', 'model.layers.12.block_sparse_moe.experts.2.w2.bias', 'model.layers.12.block_sparse_moe.experts.2.w3.bias', 'model.layers.12.block_sparse_moe.experts.3.w1.bias', 'model.layers.12.block_sparse_moe.experts.3.w2.bias', 'model.layers.12.block_sparse_moe.experts.3.w3.bias', 'model.layers.12.block_sparse_moe.experts.4.w1.bias', 'model.layers.12.block_sparse_moe.experts.4.w2.bias', 'model.layers.12.block_sparse_moe.experts.4.w3.bias', 'model.layers.12.block_sparse_moe.experts.5.w1.bias', 'model.layers.12.block_sparse_moe.experts.5.w2.bias', 'model.layers.12.block_sparse_moe.experts.5.w3.bias', 'model.layers.12.block_sparse_moe.experts.6.w1.bias', 'model.layers.12.block_sparse_moe.experts.6.w2.bias', 'model.layers.12.block_sparse_moe.experts.6.w3.bias', 'model.layers.12.block_sparse_moe.experts.7.w1.bias', 'model.layers.12.block_sparse_moe.experts.7.w2.bias', 'model.layers.12.block_sparse_moe.experts.7.w3.bias', 'model.layers.12.self_attn.k_proj.bias', 'model.layers.12.self_attn.o_proj.bias', 'model.layers.12.self_attn.q_proj.bias', 'model.layers.12.self_attn.v_proj.bias', 'model.layers.13.block_sparse_moe.experts.0.w1.bias', 'model.layers.13.block_sparse_moe.experts.0.w2.bias', 'model.layers.13.block_sparse_moe.experts.0.w3.bias', 'model.layers.13.block_sparse_moe.experts.1.w1.bias', 'model.layers.13.block_sparse_moe.experts.1.w2.bias', 'model.layers.13.block_sparse_moe.experts.1.w3.bias', 'model.layers.13.block_sparse_moe.experts.2.w1.bias', 'model.layers.13.block_sparse_moe.experts.2.w2.bias', 'model.layers.13.block_sparse_moe.experts.2.w3.bias', 'model.layers.13.block_sparse_moe.experts.3.w1.bias', 'model.layers.13.block_sparse_moe.experts.3.w2.bias', 'model.layers.13.block_sparse_moe.experts.3.w3.bias', 'model.layers.13.block_sparse_moe.experts.4.w1.bias', 'model.layers.13.block_sparse_moe.experts.4.w2.bias', 'model.layers.13.block_sparse_moe.experts.4.w3.bias', 'model.layers.13.block_sparse_moe.experts.5.w1.bias', 'model.layers.13.block_sparse_moe.experts.5.w2.bias', 'model.layers.13.block_sparse_moe.experts.5.w3.bias', 'model.layers.13.block_sparse_moe.experts.6.w1.bias', 'model.layers.13.block_sparse_moe.experts.6.w2.bias', 'model.layers.13.block_sparse_moe.experts.6.w3.bias', 'model.layers.13.block_sparse_moe.experts.7.w1.bias', 'model.layers.13.block_sparse_moe.experts.7.w2.bias', 'model.layers.13.block_sparse_moe.experts.7.w3.bias', 'model.layers.13.self_attn.k_proj.bias', 'model.layers.13.self_attn.o_proj.bias', 'model.layers.13.self_attn.q_proj.bias', 'model.layers.13.self_attn.v_proj.bias', 'model.layers.14.block_sparse_moe.experts.0.w1.bias', 'model.layers.14.block_sparse_moe.experts.0.w2.bias', 'model.layers.14.block_sparse_moe.experts.0.w3.bias', 'model.layers.14.block_sparse_moe.experts.1.w1.bias', 'model.layers.14.block_sparse_moe.experts.1.w2.bias', 'model.layers.14.block_sparse_moe.experts.1.w3.bias', 'model.layers.14.block_sparse_moe.experts.2.w1.bias', 'model.layers.14.block_sparse_moe.experts.2.w2.bias', 'model.layers.14.block_sparse_moe.experts.2.w3.bias', 'model.layers.14.block_sparse_moe.experts.3.w1.bias', 'model.layers.14.block_sparse_moe.experts.3.w2.bias', 'model.layers.14.block_sparse_moe.experts.3.w3.bias', 'model.layers.14.block_sparse_moe.experts.4.w1.bias', 'model.layers.14.block_sparse_moe.experts.4.w2.bias', 'model.layers.14.block_sparse_moe.experts.4.w3.bias', 'model.layers.14.block_sparse_moe.experts.5.w1.bias', 'model.layers.14.block_sparse_moe.experts.5.w2.bias', 'model.layers.14.block_sparse_moe.experts.5.w3.bias', 'model.layers.14.block_sparse_moe.experts.6.w1.bias', 'model.layers.14.block_sparse_moe.experts.6.w2.bias', 'model.layers.14.block_sparse_moe.experts.6.w3.bias', 'model.layers.14.block_sparse_moe.experts.7.w1.bias', 'model.layers.14.block_sparse_moe.experts.7.w2.bias', 'model.layers.14.block_sparse_moe.experts.7.w3.bias', 'model.layers.14.self_attn.k_proj.bias', 'model.layers.14.self_attn.o_proj.bias', 'model.layers.14.self_attn.q_proj.bias', 'model.layers.14.self_attn.v_proj.bias', 'model.layers.15.block_sparse_moe.experts.0.w1.bias', 'model.layers.15.block_sparse_moe.experts.0.w2.bias', 'model.layers.15.block_sparse_moe.experts.0.w3.bias', 'model.layers.15.block_sparse_moe.experts.1.w1.bias', 'model.layers.15.block_sparse_moe.experts.1.w2.bias', 'model.layers.15.block_sparse_moe.experts.1.w3.bias', 'model.layers.15.block_sparse_moe.experts.2.w1.bias', 'model.layers.15.block_sparse_moe.experts.2.w2.bias', 'model.layers.15.block_sparse_moe.experts.2.w3.bias', 'model.layers.15.block_sparse_moe.experts.3.w1.bias', 'model.layers.15.block_sparse_moe.experts.3.w2.bias', 'model.layers.15.block_sparse_moe.experts.3.w3.bias', 'model.layers.15.block_sparse_moe.experts.4.w1.bias', 'model.layers.15.block_sparse_moe.experts.4.w2.bias', 'model.layers.15.block_sparse_moe.experts.4.w3.bias', 'model.layers.15.block_sparse_moe.experts.5.w1.bias', 'model.layers.15.block_sparse_moe.experts.5.w2.bias', 'model.layers.15.block_sparse_moe.experts.5.w3.bias', 'model.layers.15.block_sparse_moe.experts.6.w1.bias', 'model.layers.15.block_sparse_moe.experts.6.w2.bias', 'model.layers.15.block_sparse_moe.experts.6.w3.bias', 'model.layers.15.block_sparse_moe.experts.7.w1.bias', 'model.layers.15.block_sparse_moe.experts.7.w2.bias', 'model.layers.15.block_sparse_moe.experts.7.w3.bias', 'model.layers.15.self_attn.k_proj.bias', 'model.layers.15.self_attn.o_proj.bias', 'model.layers.15.self_attn.q_proj.bias', 'model.layers.15.self_attn.v_proj.bias', 'model.layers.16.block_sparse_moe.experts.0.w1.bias', 'model.layers.16.block_sparse_moe.experts.0.w2.bias', 'model.layers.16.block_sparse_moe.experts.0.w3.bias', 'model.layers.16.block_sparse_moe.experts.1.w1.bias', 'model.layers.16.block_sparse_moe.experts.1.w2.bias', 'model.layers.16.block_sparse_moe.experts.1.w3.bias', 'model.layers.16.block_sparse_moe.experts.2.w1.bias', 'model.layers.16.block_sparse_moe.experts.2.w2.bias', 'model.layers.16.block_sparse_moe.experts.2.w3.bias', 'model.layers.16.block_sparse_moe.experts.3.w1.bias', 'model.layers.16.block_sparse_moe.experts.3.w2.bias', 'model.layers.16.block_sparse_moe.experts.3.w3.bias', 'model.layers.16.block_sparse_moe.experts.4.w1.bias', 'model.layers.16.block_sparse_moe.experts.4.w2.bias', 'model.layers.16.block_sparse_moe.experts.4.w3.bias', 'model.layers.16.block_sparse_moe.experts.5.w1.bias', 'model.layers.16.block_sparse_moe.experts.5.w2.bias', 'model.layers.16.block_sparse_moe.experts.5.w3.bias', 'model.layers.16.block_sparse_moe.experts.6.w1.bias', 'model.layers.16.block_sparse_moe.experts.6.w2.bias', 'model.layers.16.block_sparse_moe.experts.6.w3.bias', 'model.layers.16.block_sparse_moe.experts.7.w1.bias', 'model.layers.16.block_sparse_moe.experts.7.w2.bias', 'model.layers.16.block_sparse_moe.experts.7.w3.bias', 'model.layers.16.self_attn.k_proj.bias', 'model.layers.16.self_attn.o_proj.bias', 'model.layers.16.self_attn.q_proj.bias', 'model.layers.16.self_attn.v_proj.bias', 'model.layers.17.block_sparse_moe.experts.0.w1.bias', 'model.layers.17.block_sparse_moe.experts.0.w2.bias', 'model.layers.17.block_sparse_moe.experts.0.w3.bias', 'model.layers.17.block_sparse_moe.experts.1.w1.bias', 'model.layers.17.block_sparse_moe.experts.1.w2.bias', 'model.layers.17.block_sparse_moe.experts.1.w3.bias', 'model.layers.17.block_sparse_moe.experts.2.w1.bias', 'model.layers.17.block_sparse_moe.experts.2.w2.bias', 'model.layers.17.block_sparse_moe.experts.2.w3.bias', 'model.layers.17.block_sparse_moe.experts.3.w1.bias', 'model.layers.17.block_sparse_moe.experts.3.w2.bias', 'model.layers.17.block_sparse_moe.experts.3.w3.bias', 'model.layers.17.block_sparse_moe.experts.4.w1.bias', 'model.layers.17.block_sparse_moe.experts.4.w2.bias', 'model.layers.17.block_sparse_moe.experts.4.w3.bias', 'model.layers.17.block_sparse_moe.experts.5.w1.bias', 'model.layers.17.block_sparse_moe.experts.5.w2.bias', 'model.layers.17.block_sparse_moe.experts.5.w3.bias', 'model.layers.17.block_sparse_moe.experts.6.w1.bias', 'model.layers.17.block_sparse_moe.experts.6.w2.bias', 'model.layers.17.block_sparse_moe.experts.6.w3.bias', 'model.layers.17.block_sparse_moe.experts.7.w1.bias', 'model.layers.17.block_sparse_moe.experts.7.w2.bias', 'model.layers.17.block_sparse_moe.experts.7.w3.bias', 'model.layers.17.self_attn.k_proj.bias', 'model.layers.17.self_attn.o_proj.bias', 'model.layers.17.self_attn.q_proj.bias', 'model.layers.17.self_attn.v_proj.bias', 'model.layers.18.block_sparse_moe.experts.0.w1.bias', 'model.layers.18.block_sparse_moe.experts.0.w2.bias', 'model.layers.18.block_sparse_moe.experts.0.w3.bias', 'model.layers.18.block_sparse_moe.experts.1.w1.bias', 'model.layers.18.block_sparse_moe.experts.1.w2.bias', 'model.layers.18.block_sparse_moe.experts.1.w3.bias', 'model.layers.18.block_sparse_moe.experts.2.w1.bias', 'model.layers.18.block_sparse_moe.experts.2.w2.bias', 'model.layers.18.block_sparse_moe.experts.2.w3.bias', 'model.layers.18.block_sparse_moe.experts.3.w1.bias', 'model.layers.18.block_sparse_moe.experts.3.w2.bias', 'model.layers.18.block_sparse_moe.experts.3.w3.bias', 'model.layers.18.block_sparse_moe.experts.4.w1.bias', 'model.layers.18.block_sparse_moe.experts.4.w2.bias', 'model.layers.18.block_sparse_moe.experts.4.w3.bias', 'model.layers.18.block_sparse_moe.experts.5.w1.bias', 'model.layers.18.block_sparse_moe.experts.5.w2.bias', 'model.layers.18.block_sparse_moe.experts.5.w3.bias', 'model.layers.18.block_sparse_moe.experts.6.w1.bias', 'model.layers.18.block_sparse_moe.experts.6.w2.bias', 'model.layers.18.block_sparse_moe.experts.6.w3.bias', 'model.layers.18.block_sparse_moe.experts.7.w1.bias', 'model.layers.18.block_sparse_moe.experts.7.w2.bias', 'model.layers.18.block_sparse_moe.experts.7.w3.bias', 'model.layers.18.self_attn.k_proj.bias', 'model.layers.18.self_attn.o_proj.bias', 'model.layers.18.self_attn.q_proj.bias', 'model.layers.18.self_attn.v_proj.bias', 'model.layers.19.block_sparse_moe.experts.0.w1.bias', 'model.layers.19.block_sparse_moe.experts.0.w2.bias', 'model.layers.19.block_sparse_moe.experts.0.w3.bias', 'model.layers.19.block_sparse_moe.experts.1.w1.bias', 'model.layers.19.block_sparse_moe.experts.1.w2.bias', 'model.layers.19.block_sparse_moe.experts.1.w3.bias', 'model.layers.19.block_sparse_moe.experts.2.w1.bias', 'model.layers.19.block_sparse_moe.experts.2.w2.bias', 'model.layers.19.block_sparse_moe.experts.2.w3.bias', 'model.layers.19.block_sparse_moe.experts.3.w1.bias', 'model.layers.19.block_sparse_moe.experts.3.w2.bias', 'model.layers.19.block_sparse_moe.experts.3.w3.bias', 'model.layers.19.block_sparse_moe.experts.4.w1.bias', 'model.layers.19.block_sparse_moe.experts.4.w2.bias', 'model.layers.19.block_sparse_moe.experts.4.w3.bias', 'model.layers.19.block_sparse_moe.experts.5.w1.bias', 'model.layers.19.block_sparse_moe.experts.5.w2.bias', 'model.layers.19.block_sparse_moe.experts.5.w3.bias', 'model.layers.19.block_sparse_moe.experts.6.w1.bias', 'model.layers.19.block_sparse_moe.experts.6.w2.bias', 'model.layers.19.block_sparse_moe.experts.6.w3.bias', 'model.layers.19.block_sparse_moe.experts.7.w1.bias', 'model.layers.19.block_sparse_moe.experts.7.w2.bias', 'model.layers.19.block_sparse_moe.experts.7.w3.bias', 'model.layers.19.self_attn.k_proj.bias', 'model.layers.19.self_attn.o_proj.bias', 'model.layers.19.self_attn.q_proj.bias', 'model.layers.19.self_attn.v_proj.bias', 'model.layers.2.block_sparse_moe.experts.0.w1.bias', 'model.layers.2.block_sparse_moe.experts.0.w2.bias', 'model.layers.2.block_sparse_moe.experts.0.w3.bias', 'model.layers.2.block_sparse_moe.experts.1.w1.bias', 'model.layers.2.block_sparse_moe.experts.1.w2.bias', 'model.layers.2.block_sparse_moe.experts.1.w3.bias', 'model.layers.2.block_sparse_moe.experts.2.w1.bias', 'model.layers.2.block_sparse_moe.experts.2.w2.bias', 'model.layers.2.block_sparse_moe.experts.2.w3.bias', 'model.layers.2.block_sparse_moe.experts.3.w1.bias', 'model.layers.2.block_sparse_moe.experts.3.w2.bias', 'model.layers.2.block_sparse_moe.experts.3.w3.bias', 'model.layers.2.block_sparse_moe.experts.4.w1.bias', 'model.layers.2.block_sparse_moe.experts.4.w2.bias', 'model.layers.2.block_sparse_moe.experts.4.w3.bias', 'model.layers.2.block_sparse_moe.experts.5.w1.bias', 'model.layers.2.block_sparse_moe.experts.5.w2.bias', 'model.layers.2.block_sparse_moe.experts.5.w3.bias', 'model.layers.2.block_sparse_moe.experts.6.w1.bias', 'model.layers.2.block_sparse_moe.experts.6.w2.bias', 'model.layers.2.block_sparse_moe.experts.6.w3.bias', 'model.layers.2.block_sparse_moe.experts.7.w1.bias', 'model.layers.2.block_sparse_moe.experts.7.w2.bias', 'model.layers.2.block_sparse_moe.experts.7.w3.bias', 'model.layers.2.self_attn.k_proj.bias', 'model.layers.2.self_attn.o_proj.bias', 'model.layers.2.self_attn.q_proj.bias', 'model.layers.2.self_attn.v_proj.bias', 'model.layers.20.block_sparse_moe.experts.0.w1.bias', 'model.layers.20.block_sparse_moe.experts.0.w2.bias', 'model.layers.20.block_sparse_moe.experts.0.w3.bias', 'model.layers.20.block_sparse_moe.experts.1.w1.bias', 'model.layers.20.block_sparse_moe.experts.1.w2.bias', 'model.layers.20.block_sparse_moe.experts.1.w3.bias', 'model.layers.20.block_sparse_moe.experts.2.w1.bias', 'model.layers.20.block_sparse_moe.experts.2.w2.bias', 'model.layers.20.block_sparse_moe.experts.2.w3.bias', 'model.layers.20.block_sparse_moe.experts.3.w1.bias', 'model.layers.20.block_sparse_moe.experts.3.w2.bias', 'model.layers.20.block_sparse_moe.experts.3.w3.bias', 'model.layers.20.block_sparse_moe.experts.4.w1.bias', 'model.layers.20.block_sparse_moe.experts.4.w2.bias', 'model.layers.20.block_sparse_moe.experts.4.w3.bias', 'model.layers.20.block_sparse_moe.experts.5.w1.bias', 'model.layers.20.block_sparse_moe.experts.5.w2.bias', 'model.layers.20.block_sparse_moe.experts.5.w3.bias', 'model.layers.20.block_sparse_moe.experts.6.w1.bias', 'model.layers.20.block_sparse_moe.experts.6.w2.bias', 'model.layers.20.block_sparse_moe.experts.6.w3.bias', 'model.layers.20.block_sparse_moe.experts.7.w1.bias', 'model.layers.20.block_sparse_moe.experts.7.w2.bias', 'model.layers.20.block_sparse_moe.experts.7.w3.bias', 'model.layers.20.self_attn.k_proj.bias', 'model.layers.20.self_attn.o_proj.bias', 'model.layers.20.self_attn.q_proj.bias', 'model.layers.20.self_attn.v_proj.bias', 'model.layers.21.block_sparse_moe.experts.0.w1.bias', 'model.layers.21.block_sparse_moe.experts.0.w2.bias', 'model.layers.21.block_sparse_moe.experts.0.w3.bias', 'model.layers.21.block_sparse_moe.experts.1.w1.bias', 'model.layers.21.block_sparse_moe.experts.1.w2.bias', 'model.layers.21.block_sparse_moe.experts.1.w3.bias', 'model.layers.21.block_sparse_moe.experts.2.w1.bias', 'model.layers.21.block_sparse_moe.experts.2.w2.bias', 'model.layers.21.block_sparse_moe.experts.2.w3.bias', 'model.layers.21.block_sparse_moe.experts.3.w1.bias', 'model.layers.21.block_sparse_moe.experts.3.w2.bias', 'model.layers.21.block_sparse_moe.experts.3.w3.bias', 'model.layers.21.block_sparse_moe.experts.4.w1.bias', 'model.layers.21.block_sparse_moe.experts.4.w2.bias', 'model.layers.21.block_sparse_moe.experts.4.w3.bias', 'model.layers.21.block_sparse_moe.experts.5.w1.bias', 'model.layers.21.block_sparse_moe.experts.5.w2.bias', 'model.layers.21.block_sparse_moe.experts.5.w3.bias', 'model.layers.21.block_sparse_moe.experts.6.w1.bias', 'model.layers.21.block_sparse_moe.experts.6.w2.bias', 'model.layers.21.block_sparse_moe.experts.6.w3.bias', 'model.layers.21.block_sparse_moe.experts.7.w1.bias', 'model.layers.21.block_sparse_moe.experts.7.w2.bias', 'model.layers.21.block_sparse_moe.experts.7.w3.bias', 'model.layers.21.self_attn.k_proj.bias', 'model.layers.21.self_attn.o_proj.bias', 'model.layers.21.self_attn.q_proj.bias', 'model.layers.21.self_attn.v_proj.bias', 'model.layers.22.block_sparse_moe.experts.0.w1.bias', 'model.layers.22.block_sparse_moe.experts.0.w2.bias', 'model.layers.22.block_sparse_moe.experts.0.w3.bias', 'model.layers.22.block_sparse_moe.experts.1.w1.bias', 'model.layers.22.block_sparse_moe.experts.1.w2.bias', 'model.layers.22.block_sparse_moe.experts.1.w3.bias', 'model.layers.22.block_sparse_moe.experts.2.w1.bias', 'model.layers.22.block_sparse_moe.experts.2.w2.bias', 'model.layers.22.block_sparse_moe.experts.2.w3.bias', 'model.layers.22.block_sparse_moe.experts.3.w1.bias', 'model.layers.22.block_sparse_moe.experts.3.w2.bias', 'model.layers.22.block_sparse_moe.experts.3.w3.bias', 'model.layers.22.block_sparse_moe.experts.4.w1.bias', 'model.layers.22.block_sparse_moe.experts.4.w2.bias', 'model.layers.22.block_sparse_moe.experts.4.w3.bias', 'model.layers.22.block_sparse_moe.experts.5.w1.bias', 'model.layers.22.block_sparse_moe.experts.5.w2.bias', 'model.layers.22.block_sparse_moe.experts.5.w3.bias', 'model.layers.22.block_sparse_moe.experts.6.w1.bias', 'model.layers.22.block_sparse_moe.experts.6.w2.bias', 'model.layers.22.block_sparse_moe.experts.6.w3.bias', 'model.layers.22.block_sparse_moe.experts.7.w1.bias', 'model.layers.22.block_sparse_moe.experts.7.w2.bias', 'model.layers.22.block_sparse_moe.experts.7.w3.bias', 'model.layers.22.self_attn.k_proj.bias', 'model.layers.22.self_attn.o_proj.bias', 'model.layers.22.self_attn.q_proj.bias', 'model.layers.22.self_attn.v_proj.bias', 'model.layers.23.block_sparse_moe.experts.0.w1.bias', 'model.layers.23.block_sparse_moe.experts.0.w2.bias', 'model.layers.23.block_sparse_moe.experts.0.w3.bias', 'model.layers.23.block_sparse_moe.experts.1.w1.bias', 'model.layers.23.block_sparse_moe.experts.1.w2.bias', 'model.layers.23.block_sparse_moe.experts.1.w3.bias', 'model.layers.23.block_sparse_moe.experts.2.w1.bias', 'model.layers.23.block_sparse_moe.experts.2.w2.bias', 'model.layers.23.block_sparse_moe.experts.2.w3.bias', 'model.layers.23.block_sparse_moe.experts.3.w1.bias', 'model.layers.23.block_sparse_moe.experts.3.w2.bias', 'model.layers.23.block_sparse_moe.experts.3.w3.bias', 'model.layers.23.block_sparse_moe.experts.4.w1.bias', 'model.layers.23.block_sparse_moe.experts.4.w2.bias', 'model.layers.23.block_sparse_moe.experts.4.w3.bias', 'model.layers.23.block_sparse_moe.experts.5.w1.bias', 'model.layers.23.block_sparse_moe.experts.5.w2.bias', 'model.layers.23.block_sparse_moe.experts.5.w3.bias', 'model.layers.23.block_sparse_moe.experts.6.w1.bias', 'model.layers.23.block_sparse_moe.experts.6.w2.bias', 'model.layers.23.block_sparse_moe.experts.6.w3.bias', 'model.layers.23.block_sparse_moe.experts.7.w1.bias', 'model.layers.23.block_sparse_moe.experts.7.w2.bias', 'model.layers.23.block_sparse_moe.experts.7.w3.bias', 'model.layers.23.self_attn.k_proj.bias', 'model.layers.23.self_attn.o_proj.bias', 'model.layers.23.self_attn.q_proj.bias', 'model.layers.23.self_attn.v_proj.bias', 'model.layers.24.block_sparse_moe.experts.0.w1.bias', 'model.layers.24.block_sparse_moe.experts.0.w2.bias', 'model.layers.24.block_sparse_moe.experts.0.w3.bias', 'model.layers.24.block_sparse_moe.experts.1.w1.bias', 'model.layers.24.block_sparse_moe.experts.1.w2.bias', 'model.layers.24.block_sparse_moe.experts.1.w3.bias', 'model.layers.24.block_sparse_moe.experts.2.w1.bias', 'model.layers.24.block_sparse_moe.experts.2.w2.bias', 'model.layers.24.block_sparse_moe.experts.2.w3.bias', 'model.layers.24.block_sparse_moe.experts.3.w1.bias', 'model.layers.24.block_sparse_moe.experts.3.w2.bias', 'model.layers.24.block_sparse_moe.experts.3.w3.bias', 'model.layers.24.block_sparse_moe.experts.4.w1.bias', 'model.layers.24.block_sparse_moe.experts.4.w2.bias', 'model.layers.24.block_sparse_moe.experts.4.w3.bias', 'model.layers.24.block_sparse_moe.experts.5.w1.bias', 'model.layers.24.block_sparse_moe.experts.5.w2.bias', 'model.layers.24.block_sparse_moe.experts.5.w3.bias', 'model.layers.24.block_sparse_moe.experts.6.w1.bias', 'model.layers.24.block_sparse_moe.experts.6.w2.bias', 'model.layers.24.block_sparse_moe.experts.6.w3.bias', 'model.layers.24.block_sparse_moe.experts.7.w1.bias', 'model.layers.24.block_sparse_moe.experts.7.w2.bias', 'model.layers.24.block_sparse_moe.experts.7.w3.bias', 'model.layers.24.self_attn.k_proj.bias', 'model.layers.24.self_attn.o_proj.bias', 'model.layers.24.self_attn.q_proj.bias', 'model.layers.24.self_attn.v_proj.bias', 'model.layers.25.block_sparse_moe.experts.0.w1.bias', 'model.layers.25.block_sparse_moe.experts.0.w2.bias', 'model.layers.25.block_sparse_moe.experts.0.w3.bias', 'model.layers.25.block_sparse_moe.experts.1.w1.bias', 'model.layers.25.block_sparse_moe.experts.1.w2.bias', 'model.layers.25.block_sparse_moe.experts.1.w3.bias', 'model.layers.25.block_sparse_moe.experts.2.w1.bias', 'model.layers.25.block_sparse_moe.experts.2.w2.bias', 'model.layers.25.block_sparse_moe.experts.2.w3.bias', 'model.layers.25.block_sparse_moe.experts.3.w1.bias', 'model.layers.25.block_sparse_moe.experts.3.w2.bias', 'model.layers.25.block_sparse_moe.experts.3.w3.bias', 'model.layers.25.block_sparse_moe.experts.4.w1.bias', 'model.layers.25.block_sparse_moe.experts.4.w2.bias', 'model.layers.25.block_sparse_moe.experts.4.w3.bias', 'model.layers.25.block_sparse_moe.experts.5.w1.bias', 'model.layers.25.block_sparse_moe.experts.5.w2.bias', 'model.layers.25.block_sparse_moe.experts.5.w3.bias', 'model.layers.25.block_sparse_moe.experts.6.w1.bias', 'model.layers.25.block_sparse_moe.experts.6.w2.bias', 'model.layers.25.block_sparse_moe.experts.6.w3.bias', 'model.layers.25.block_sparse_moe.experts.7.w1.bias', 'model.layers.25.block_sparse_moe.experts.7.w2.bias', 'model.layers.25.block_sparse_moe.experts.7.w3.bias', 'model.layers.25.self_attn.k_proj.bias', 'model.layers.25.self_attn.o_proj.bias', 'model.layers.25.self_attn.q_proj.bias', 'model.layers.25.self_attn.v_proj.bias', 'model.layers.26.block_sparse_moe.experts.0.w1.bias', 'model.layers.26.block_sparse_moe.experts.0.w2.bias', 'model.layers.26.block_sparse_moe.experts.0.w3.bias', 'model.layers.26.block_sparse_moe.experts.1.w1.bias', 'model.layers.26.block_sparse_moe.experts.1.w2.bias', 'model.layers.26.block_sparse_moe.experts.1.w3.bias', 'model.layers.26.block_sparse_moe.experts.2.w1.bias', 'model.layers.26.block_sparse_moe.experts.2.w2.bias', 'model.layers.26.block_sparse_moe.experts.2.w3.bias', 'model.layers.26.block_sparse_moe.experts.3.w1.bias', 'model.layers.26.block_sparse_moe.experts.3.w2.bias', 'model.layers.26.block_sparse_moe.experts.3.w3.bias', 'model.layers.26.block_sparse_moe.experts.4.w1.bias', 'model.layers.26.block_sparse_moe.experts.4.w2.bias', 'model.layers.26.block_sparse_moe.experts.4.w3.bias', 'model.layers.26.block_sparse_moe.experts.5.w1.bias', 'model.layers.26.block_sparse_moe.experts.5.w2.bias', 'model.layers.26.block_sparse_moe.experts.5.w3.bias', 'model.layers.26.block_sparse_moe.experts.6.w1.bias', 'model.layers.26.block_sparse_moe.experts.6.w2.bias', 'model.layers.26.block_sparse_moe.experts.6.w3.bias', 'model.layers.26.block_sparse_moe.experts.7.w1.bias', 'model.layers.26.block_sparse_moe.experts.7.w2.bias', 'model.layers.26.block_sparse_moe.experts.7.w3.bias', 'model.layers.26.self_attn.k_proj.bias', 'model.layers.26.self_attn.o_proj.bias', 'model.layers.26.self_attn.q_proj.bias', 'model.layers.26.self_attn.v_proj.bias', 'model.layers.27.block_sparse_moe.experts.0.w1.bias', 'model.layers.27.block_sparse_moe.experts.0.w2.bias', 'model.layers.27.block_sparse_moe.experts.0.w3.bias', 'model.layers.27.block_sparse_moe.experts.1.w1.bias', 'model.layers.27.block_sparse_moe.experts.1.w2.bias', 'model.layers.27.block_sparse_moe.experts.1.w3.bias', 'model.layers.27.block_sparse_moe.experts.2.w1.bias', 'model.layers.27.block_sparse_moe.experts.2.w2.bias', 'model.layers.27.block_sparse_moe.experts.2.w3.bias', 'model.layers.27.block_sparse_moe.experts.3.w1.bias', 'model.layers.27.block_sparse_moe.experts.3.w2.bias', 'model.layers.27.block_sparse_moe.experts.3.w3.bias', 'model.layers.27.block_sparse_moe.experts.4.w1.bias', 'model.layers.27.block_sparse_moe.experts.4.w2.bias', 'model.layers.27.block_sparse_moe.experts.4.w3.bias', 'model.layers.27.block_sparse_moe.experts.5.w1.bias', 'model.layers.27.block_sparse_moe.experts.5.w2.bias', 'model.layers.27.block_sparse_moe.experts.5.w3.bias', 'model.layers.27.block_sparse_moe.experts.6.w1.bias', 'model.layers.27.block_sparse_moe.experts.6.w2.bias', 'model.layers.27.block_sparse_moe.experts.6.w3.bias', 'model.layers.27.block_sparse_moe.experts.7.w1.bias', 'model.layers.27.block_sparse_moe.experts.7.w2.bias', 'model.layers.27.block_sparse_moe.experts.7.w3.bias', 'model.layers.27.self_attn.k_proj.bias', 'model.layers.27.self_attn.o_proj.bias', 'model.layers.27.self_attn.q_proj.bias', 'model.layers.27.self_attn.v_proj.bias', 'model.layers.28.block_sparse_moe.experts.0.w1.bias', 'model.layers.28.block_sparse_moe.experts.0.w2.bias', 'model.layers.28.block_sparse_moe.experts.0.w3.bias', 'model.layers.28.block_sparse_moe.experts.1.w1.bias', 'model.layers.28.block_sparse_moe.experts.1.w2.bias', 'model.layers.28.block_sparse_moe.experts.1.w3.bias', 'model.layers.28.block_sparse_moe.experts.2.w1.bias', 'model.layers.28.block_sparse_moe.experts.2.w2.bias', 'model.layers.28.block_sparse_moe.experts.2.w3.bias', 'model.layers.28.block_sparse_moe.experts.3.w1.bias', 'model.layers.28.block_sparse_moe.experts.3.w2.bias', 'model.layers.28.block_sparse_moe.experts.3.w3.bias', 'model.layers.28.block_sparse_moe.experts.4.w1.bias', 'model.layers.28.block_sparse_moe.experts.4.w2.bias', 'model.layers.28.block_sparse_moe.experts.4.w3.bias', 'model.layers.28.block_sparse_moe.experts.5.w1.bias', 'model.layers.28.block_sparse_moe.experts.5.w2.bias', 'model.layers.28.block_sparse_moe.experts.5.w3.bias', 'model.layers.28.block_sparse_moe.experts.6.w1.bias', 'model.layers.28.block_sparse_moe.experts.6.w2.bias', 'model.layers.28.block_sparse_moe.experts.6.w3.bias', 'model.layers.28.block_sparse_moe.experts.7.w1.bias', 'model.layers.28.block_sparse_moe.experts.7.w2.bias', 'model.layers.28.block_sparse_moe.experts.7.w3.bias', 'model.layers.28.self_attn.k_proj.bias', 'model.layers.28.self_attn.o_proj.bias', 'model.layers.28.self_attn.q_proj.bias', 'model.layers.28.self_attn.v_proj.bias', 'model.layers.29.block_sparse_moe.experts.0.w1.bias', 'model.layers.29.block_sparse_moe.experts.0.w2.bias', 'model.layers.29.block_sparse_moe.experts.0.w3.bias', 'model.layers.29.block_sparse_moe.experts.1.w1.bias', 'model.layers.29.block_sparse_moe.experts.1.w2.bias', 'model.layers.29.block_sparse_moe.experts.1.w3.bias', 'model.layers.29.block_sparse_moe.experts.2.w1.bias', 'model.layers.29.block_sparse_moe.experts.2.w2.bias', 'model.layers.29.block_sparse_moe.experts.2.w3.bias', 'model.layers.29.block_sparse_moe.experts.3.w1.bias', 'model.layers.29.block_sparse_moe.experts.3.w2.bias', 'model.layers.29.block_sparse_moe.experts.3.w3.bias', 'model.layers.29.block_sparse_moe.experts.4.w1.bias', 'model.layers.29.block_sparse_moe.experts.4.w2.bias', 'model.layers.29.block_sparse_moe.experts.4.w3.bias', 'model.layers.29.block_sparse_moe.experts.5.w1.bias', 'model.layers.29.block_sparse_moe.experts.5.w2.bias', 'model.layers.29.block_sparse_moe.experts.5.w3.bias', 'model.layers.29.block_sparse_moe.experts.6.w1.bias', 'model.layers.29.block_sparse_moe.experts.6.w2.bias', 'model.layers.29.block_sparse_moe.experts.6.w3.bias', 'model.layers.29.block_sparse_moe.experts.7.w1.bias', 'model.layers.29.block_sparse_moe.experts.7.w2.bias', 'model.layers.29.block_sparse_moe.experts.7.w3.bias', 'model.layers.29.self_attn.k_proj.bias', 'model.layers.29.self_attn.o_proj.bias', 'model.layers.29.self_attn.q_proj.bias', 'model.layers.29.self_attn.v_proj.bias', 'model.layers.3.block_sparse_moe.experts.0.w1.bias', 'model.layers.3.block_sparse_moe.experts.0.w2.bias', 'model.layers.3.block_sparse_moe.experts.0.w3.bias', 'model.layers.3.block_sparse_moe.experts.1.w1.bias', 'model.layers.3.block_sparse_moe.experts.1.w2.bias', 'model.layers.3.block_sparse_moe.experts.1.w3.bias', 'model.layers.3.block_sparse_moe.experts.2.w1.bias', 'model.layers.3.block_sparse_moe.experts.2.w2.bias', 'model.layers.3.block_sparse_moe.experts.2.w3.bias', 'model.layers.3.block_sparse_moe.experts.3.w1.bias', 'model.layers.3.block_sparse_moe.experts.3.w2.bias', 'model.layers.3.block_sparse_moe.experts.3.w3.bias', 'model.layers.3.block_sparse_moe.experts.4.w1.bias', 'model.layers.3.block_sparse_moe.experts.4.w2.bias', 'model.layers.3.block_sparse_moe.experts.4.w3.bias', 'model.layers.3.block_sparse_moe.experts.5.w1.bias', 'model.layers.3.block_sparse_moe.experts.5.w2.bias', 'model.layers.3.block_sparse_moe.experts.5.w3.bias', 'model.layers.3.block_sparse_moe.experts.6.w1.bias', 'model.layers.3.block_sparse_moe.experts.6.w2.bias', 'model.layers.3.block_sparse_moe.experts.6.w3.bias', 'model.layers.3.block_sparse_moe.experts.7.w1.bias', 'model.layers.3.block_sparse_moe.experts.7.w2.bias', 'model.layers.3.block_sparse_moe.experts.7.w3.bias', 'model.layers.3.self_attn.k_proj.bias', 'model.layers.3.self_attn.o_proj.bias', 'model.layers.3.self_attn.q_proj.bias', 'model.layers.3.self_attn.v_proj.bias', 'model.layers.30.block_sparse_moe.experts.0.w1.bias', 'model.layers.30.block_sparse_moe.experts.0.w2.bias', 'model.layers.30.block_sparse_moe.experts.0.w3.bias', 'model.layers.30.block_sparse_moe.experts.1.w1.bias', 'model.layers.30.block_sparse_moe.experts.1.w2.bias', 'model.layers.30.block_sparse_moe.experts.1.w3.bias', 'model.layers.30.block_sparse_moe.experts.2.w1.bias', 'model.layers.30.block_sparse_moe.experts.2.w2.bias', 'model.layers.30.block_sparse_moe.experts.2.w3.bias', 'model.layers.30.block_sparse_moe.experts.3.w1.bias', 'model.layers.30.block_sparse_moe.experts.3.w2.bias', 'model.layers.30.block_sparse_moe.experts.3.w3.bias', 'model.layers.30.block_sparse_moe.experts.4.w1.bias', 'model.layers.30.block_sparse_moe.experts.4.w2.bias', 'model.layers.30.block_sparse_moe.experts.4.w3.bias', 'model.layers.30.block_sparse_moe.experts.5.w1.bias', 'model.layers.30.block_sparse_moe.experts.5.w2.bias', 'model.layers.30.block_sparse_moe.experts.5.w3.bias', 'model.layers.30.block_sparse_moe.experts.6.w1.bias', 'model.layers.30.block_sparse_moe.experts.6.w2.bias', 'model.layers.30.block_sparse_moe.experts.6.w3.bias', 'model.layers.30.block_sparse_moe.experts.7.w1.bias', 'model.layers.30.block_sparse_moe.experts.7.w2.bias', 'model.layers.30.block_sparse_moe.experts.7.w3.bias', 'model.layers.30.self_attn.k_proj.bias', 'model.layers.30.self_attn.o_proj.bias', 'model.layers.30.self_attn.q_proj.bias', 'model.layers.30.self_attn.v_proj.bias', 'model.layers.31.block_sparse_moe.experts.0.w1.bias', 'model.layers.31.block_sparse_moe.experts.0.w2.bias', 'model.layers.31.block_sparse_moe.experts.0.w3.bias', 'model.layers.31.block_sparse_moe.experts.1.w1.bias', 'model.layers.31.block_sparse_moe.experts.1.w2.bias', 'model.layers.31.block_sparse_moe.experts.1.w3.bias', 'model.layers.31.block_sparse_moe.experts.2.w1.bias', 'model.layers.31.block_sparse_moe.experts.2.w2.bias', 'model.layers.31.block_sparse_moe.experts.2.w3.bias', 'model.layers.31.block_sparse_moe.experts.3.w1.bias', 'model.layers.31.block_sparse_moe.experts.3.w2.bias', 'model.layers.31.block_sparse_moe.experts.3.w3.bias', 'model.layers.31.block_sparse_moe.experts.4.w1.bias', 'model.layers.31.block_sparse_moe.experts.4.w2.bias', 'model.layers.31.block_sparse_moe.experts.4.w3.bias', 'model.layers.31.block_sparse_moe.experts.5.w1.bias', 'model.layers.31.block_sparse_moe.experts.5.w2.bias', 'model.layers.31.block_sparse_moe.experts.5.w3.bias', 'model.layers.31.block_sparse_moe.experts.6.w1.bias', 'model.layers.31.block_sparse_moe.experts.6.w2.bias', 'model.layers.31.block_sparse_moe.experts.6.w3.bias', 'model.layers.31.block_sparse_moe.experts.7.w1.bias', 'model.layers.31.block_sparse_moe.experts.7.w2.bias', 'model.layers.31.block_sparse_moe.experts.7.w3.bias', 'model.layers.31.self_attn.k_proj.bias', 'model.layers.31.self_attn.o_proj.bias', 'model.layers.31.self_attn.q_proj.bias', 'model.layers.31.self_attn.v_proj.bias', 'model.layers.4.block_sparse_moe.experts.0.w1.bias', 'model.layers.4.block_sparse_moe.experts.0.w2.bias', 'model.layers.4.block_sparse_moe.experts.0.w3.bias', 'model.layers.4.block_sparse_moe.experts.1.w1.bias', 'model.layers.4.block_sparse_moe.experts.1.w2.bias', 'model.layers.4.block_sparse_moe.experts.1.w3.bias', 'model.layers.4.block_sparse_moe.experts.2.w1.bias', 'model.layers.4.block_sparse_moe.experts.2.w2.bias', 'model.layers.4.block_sparse_moe.experts.2.w3.bias', 'model.layers.4.block_sparse_moe.experts.3.w1.bias', 'model.layers.4.block_sparse_moe.experts.3.w2.bias', 'model.layers.4.block_sparse_moe.experts.3.w3.bias', 'model.layers.4.block_sparse_moe.experts.4.w1.bias', 'model.layers.4.block_sparse_moe.experts.4.w2.bias', 'model.layers.4.block_sparse_moe.experts.4.w3.bias', 'model.layers.4.block_sparse_moe.experts.5.w1.bias', 'model.layers.4.block_sparse_moe.experts.5.w2.bias', 'model.layers.4.block_sparse_moe.experts.5.w3.bias', 'model.layers.4.block_sparse_moe.experts.6.w1.bias', 'model.layers.4.block_sparse_moe.experts.6.w2.bias', 'model.layers.4.block_sparse_moe.experts.6.w3.bias', 'model.layers.4.block_sparse_moe.experts.7.w1.bias', 'model.layers.4.block_sparse_moe.experts.7.w2.bias', 'model.layers.4.block_sparse_moe.experts.7.w3.bias', 'model.layers.4.self_attn.k_proj.bias', 'model.layers.4.self_attn.o_proj.bias', 'model.layers.4.self_attn.q_proj.bias', 'model.layers.4.self_attn.v_proj.bias', 'model.layers.5.block_sparse_moe.experts.0.w1.bias', 'model.layers.5.block_sparse_moe.experts.0.w2.bias', 'model.layers.5.block_sparse_moe.experts.0.w3.bias', 'model.layers.5.block_sparse_moe.experts.1.w1.bias', 'model.layers.5.block_sparse_moe.experts.1.w2.bias', 'model.layers.5.block_sparse_moe.experts.1.w3.bias', 'model.layers.5.block_sparse_moe.experts.2.w1.bias', 'model.layers.5.block_sparse_moe.experts.2.w2.bias', 'model.layers.5.block_sparse_moe.experts.2.w3.bias', 'model.layers.5.block_sparse_moe.experts.3.w1.bias', 'model.layers.5.block_sparse_moe.experts.3.w2.bias', 'model.layers.5.block_sparse_moe.experts.3.w3.bias', 'model.layers.5.block_sparse_moe.experts.4.w1.bias', 'model.layers.5.block_sparse_moe.experts.4.w2.bias', 'model.layers.5.block_sparse_moe.experts.4.w3.bias', 'model.layers.5.block_sparse_moe.experts.5.w1.bias', 'model.layers.5.block_sparse_moe.experts.5.w2.bias', 'model.layers.5.block_sparse_moe.experts.5.w3.bias', 'model.layers.5.block_sparse_moe.experts.6.w1.bias', 'model.layers.5.block_sparse_moe.experts.6.w2.bias', 'model.layers.5.block_sparse_moe.experts.6.w3.bias', 'model.layers.5.block_sparse_moe.experts.7.w1.bias', 'model.layers.5.block_sparse_moe.experts.7.w2.bias', 'model.layers.5.block_sparse_moe.experts.7.w3.bias', 'model.layers.5.self_attn.k_proj.bias', 'model.layers.5.self_attn.o_proj.bias', 'model.layers.5.self_attn.q_proj.bias', 'model.layers.5.self_attn.v_proj.bias', 'model.layers.6.block_sparse_moe.experts.0.w1.bias', 'model.layers.6.block_sparse_moe.experts.0.w2.bias', 'model.layers.6.block_sparse_moe.experts.0.w3.bias', 'model.layers.6.block_sparse_moe.experts.1.w1.bias', 'model.layers.6.block_sparse_moe.experts.1.w2.bias', 'model.layers.6.block_sparse_moe.experts.1.w3.bias', 'model.layers.6.block_sparse_moe.experts.2.w1.bias', 'model.layers.6.block_sparse_moe.experts.2.w2.bias', 'model.layers.6.block_sparse_moe.experts.2.w3.bias', 'model.layers.6.block_sparse_moe.experts.3.w1.bias', 'model.layers.6.block_sparse_moe.experts.3.w2.bias', 'model.layers.6.block_sparse_moe.experts.3.w3.bias', 'model.layers.6.block_sparse_moe.experts.4.w1.bias', 'model.layers.6.block_sparse_moe.experts.4.w2.bias', 'model.layers.6.block_sparse_moe.experts.4.w3.bias', 'model.layers.6.block_sparse_moe.experts.5.w1.bias', 'model.layers.6.block_sparse_moe.experts.5.w2.bias', 'model.layers.6.block_sparse_moe.experts.5.w3.bias', 'model.layers.6.block_sparse_moe.experts.6.w1.bias', 'model.layers.6.block_sparse_moe.experts.6.w2.bias', 'model.layers.6.block_sparse_moe.experts.6.w3.bias', 'model.layers.6.block_sparse_moe.experts.7.w1.bias', 'model.layers.6.block_sparse_moe.experts.7.w2.bias', 'model.layers.6.block_sparse_moe.experts.7.w3.bias', 'model.layers.6.self_attn.k_proj.bias', 'model.layers.6.self_attn.o_proj.bias', 'model.layers.6.self_attn.q_proj.bias', 'model.layers.6.self_attn.v_proj.bias', 'model.layers.7.block_sparse_moe.experts.0.w1.bias', 'model.layers.7.block_sparse_moe.experts.0.w2.bias', 'model.layers.7.block_sparse_moe.experts.0.w3.bias', 'model.layers.7.block_sparse_moe.experts.1.w1.bias', 'model.layers.7.block_sparse_moe.experts.1.w2.bias', 'model.layers.7.block_sparse_moe.experts.1.w3.bias', 'model.layers.7.block_sparse_moe.experts.2.w1.bias', 'model.layers.7.block_sparse_moe.experts.2.w2.bias', 'model.layers.7.block_sparse_moe.experts.2.w3.bias', 'model.layers.7.block_sparse_moe.experts.3.w1.bias', 'model.layers.7.block_sparse_moe.experts.3.w2.bias', 'model.layers.7.block_sparse_moe.experts.3.w3.bias', 'model.layers.7.block_sparse_moe.experts.4.w1.bias', 'model.layers.7.block_sparse_moe.experts.4.w2.bias', 'model.layers.7.block_sparse_moe.experts.4.w3.bias', 'model.layers.7.block_sparse_moe.experts.5.w1.bias', 'model.layers.7.block_sparse_moe.experts.5.w2.bias', 'model.layers.7.block_sparse_moe.experts.5.w3.bias', 'model.layers.7.block_sparse_moe.experts.6.w1.bias', 'model.layers.7.block_sparse_moe.experts.6.w2.bias', 'model.layers.7.block_sparse_moe.experts.6.w3.bias', 'model.layers.7.block_sparse_moe.experts.7.w1.bias', 'model.layers.7.block_sparse_moe.experts.7.w2.bias', 'model.layers.7.block_sparse_moe.experts.7.w3.bias', 'model.layers.7.self_attn.k_proj.bias', 'model.layers.7.self_attn.o_proj.bias', 'model.layers.7.self_attn.q_proj.bias', 'model.layers.7.self_attn.v_proj.bias', 'model.layers.8.block_sparse_moe.experts.0.w1.bias', 'model.layers.8.block_sparse_moe.experts.0.w2.bias', 'model.layers.8.block_sparse_moe.experts.0.w3.bias', 'model.layers.8.block_sparse_moe.experts.1.w1.bias', 'model.layers.8.block_sparse_moe.experts.1.w2.bias', 'model.layers.8.block_sparse_moe.experts.1.w3.bias', 'model.layers.8.block_sparse_moe.experts.2.w1.bias', 'model.layers.8.block_sparse_moe.experts.2.w2.bias', 'model.layers.8.block_sparse_moe.experts.2.w3.bias', 'model.layers.8.block_sparse_moe.experts.3.w1.bias', 'model.layers.8.block_sparse_moe.experts.3.w2.bias', 'model.layers.8.block_sparse_moe.experts.3.w3.bias', 'model.layers.8.block_sparse_moe.experts.4.w1.bias', 'model.layers.8.block_sparse_moe.experts.4.w2.bias', 'model.layers.8.block_sparse_moe.experts.4.w3.bias', 'model.layers.8.block_sparse_moe.experts.5.w1.bias', 'model.layers.8.block_sparse_moe.experts.5.w2.bias', 'model.layers.8.block_sparse_moe.experts.5.w3.bias', 'model.layers.8.block_sparse_moe.experts.6.w1.bias', 'model.layers.8.block_sparse_moe.experts.6.w2.bias', 'model.layers.8.block_sparse_moe.experts.6.w3.bias', 'model.layers.8.block_sparse_moe.experts.7.w1.bias', 'model.layers.8.block_sparse_moe.experts.7.w2.bias', 'model.layers.8.block_sparse_moe.experts.7.w3.bias', 'model.layers.8.self_attn.k_proj.bias', 'model.layers.8.self_attn.o_proj.bias', 'model.layers.8.self_attn.q_proj.bias', 'model.layers.8.self_attn.v_proj.bias', 'model.layers.9.block_sparse_moe.experts.0.w1.bias', 'model.layers.9.block_sparse_moe.experts.0.w2.bias', 'model.layers.9.block_sparse_moe.experts.0.w3.bias', 'model.layers.9.block_sparse_moe.experts.1.w1.bias', 'model.layers.9.block_sparse_moe.experts.1.w2.bias', 'model.layers.9.block_sparse_moe.experts.1.w3.bias', 'model.layers.9.block_sparse_moe.experts.2.w1.bias', 'model.layers.9.block_sparse_moe.experts.2.w2.bias', 'model.layers.9.block_sparse_moe.experts.2.w3.bias', 'model.layers.9.block_sparse_moe.experts.3.w1.bias', 'model.layers.9.block_sparse_moe.experts.3.w2.bias', 'model.layers.9.block_sparse_moe.experts.3.w3.bias', 'model.layers.9.block_sparse_moe.experts.4.w1.bias', 'model.layers.9.block_sparse_moe.experts.4.w2.bias', 'model.layers.9.block_sparse_moe.experts.4.w3.bias', 'model.layers.9.block_sparse_moe.experts.5.w1.bias', 'model.layers.9.block_sparse_moe.experts.5.w2.bias', 'model.layers.9.block_sparse_moe.experts.5.w3.bias', 'model.layers.9.block_sparse_moe.experts.6.w1.bias', 'model.layers.9.block_sparse_moe.experts.6.w2.bias', 'model.layers.9.block_sparse_moe.experts.6.w3.bias', 'model.layers.9.block_sparse_moe.experts.7.w1.bias', 'model.layers.9.block_sparse_moe.experts.7.w2.bias', 'model.layers.9.block_sparse_moe.experts.7.w3.bias', 'model.layers.9.self_attn.k_proj.bias', 'model.layers.9.self_attn.o_proj.bias', 'model.layers.9.self_attn.q_proj.bias', 'model.layers.9.self_attn.v_proj.bias']

  • This IS expected if you are initializing MixtralForCausalLM 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 MixtralForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).

Sign up or log in to comment