{ "metadata": { "total_size": 95422898176 }, "weight_map": { "lm_head.weight": "model-00020-of-00020.safetensors", "model.embed_tokens.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00020.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00020.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00020.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00020.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00020.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00020.safetensors", "model.layers.19.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00020.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00020.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00020.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00020.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00020.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00020.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00020.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00016-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00020.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00017-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00020.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00020.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00020.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00020.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00020.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00020.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00020.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00020.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.mm_projector.experts.0.0.bias": "model-00020-of-00020.safetensors", "model.mm_projector.experts.0.0.weight": "model-00020-of-00020.safetensors", "model.mm_projector.experts.0.2.bias": "model-00020-of-00020.safetensors", "model.mm_projector.experts.0.2.weight": "model-00020-of-00020.safetensors", "model.mm_projector.experts.1.0.bias": "model-00020-of-00020.safetensors", "model.mm_projector.experts.1.0.weight": "model-00020-of-00020.safetensors", "model.mm_projector.experts.1.2.bias": "model-00020-of-00020.safetensors", "model.mm_projector.experts.1.2.weight": "model-00020-of-00020.safetensors", "model.mm_projector.experts.2.0.bias": "model-00020-of-00020.safetensors", "model.mm_projector.experts.2.0.weight": "model-00020-of-00020.safetensors", "model.mm_projector.experts.2.2.bias": "model-00020-of-00020.safetensors", "model.mm_projector.experts.2.2.weight": "model-00020-of-00020.safetensors", "model.mm_projector.experts.3.0.bias": "model-00020-of-00020.safetensors", "model.mm_projector.experts.3.0.weight": "model-00020-of-00020.safetensors", "model.mm_projector.experts.3.2.bias": "model-00020-of-00020.safetensors", "model.mm_projector.experts.3.2.weight": "model-00020-of-00020.safetensors", "model.mm_projector.gate.weight": "model-00020-of-00020.safetensors", "model.norm.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.embeddings.class_embedding": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.0.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.0.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.0.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.0.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.1.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.1.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.1.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.1.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.2.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.2.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.2.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.2.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.3.fc1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.3.fc1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.3.fc2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.experts.3.fc2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.gate.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.0.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.0.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.0.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.0.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.1.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.1.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.1.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.1.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.2.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.2.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.2.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.2.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.3.fc1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.3.fc1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.3.fc2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.experts.3.fc2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.gate.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.pre_layrnorm.bias": "model-00019-of-00020.safetensors", "model.vision_tower.vision_model.pre_layrnorm.weight": "model-00019-of-00020.safetensors" } }