{ "metadata": { "total_size": 6728253440 }, "weight_map": { "lm_head.weight": "model-00002-of-00002.safetensors", "transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.1.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.1.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.11.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.11.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.13.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.13.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.15.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.15.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.17.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.17.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.19.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.19.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.21.attn.c_attn.bias": "model-00002-of-00002.safetensors", "transformer.h.21.attn.c_attn.weight": "model-00002-of-00002.safetensors", "transformer.h.21.attn.c_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.21.ln_2.weight": "model-00002-of-00002.safetensors", "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.21.mlp.w1.weight": "model-00002-of-00002.safetensors", "transformer.h.21.mlp.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.attn.c_attn.bias": "model-00002-of-00002.safetensors", "transformer.h.22.attn.c_attn.weight": "model-00002-of-00002.safetensors", "transformer.h.22.attn.c_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.22.ln_1.weight": "model-00002-of-00002.safetensors", "transformer.h.22.ln_2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.mlp.deepspeed_moe.gate.wg.weight": "model-00002-of-00002.safetensors", "transformer.h.23.attn.c_attn.bias": "model-00002-of-00002.safetensors", "transformer.h.23.attn.c_attn.weight": "model-00002-of-00002.safetensors", "transformer.h.23.attn.c_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors", "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors", "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors", "transformer.h.23.mlp.w1.weight": "model-00002-of-00002.safetensors", "transformer.h.23.mlp.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.3.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.3.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.5.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.5.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.7.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.7.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors", "transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors", "transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors", "transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors", "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors", "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.9.mlp.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.9.mlp.w2.weight": "model-00001-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors", "transformer.image_tower.image_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors", "transformer.ln_f.weight": "model-00002-of-00002.safetensors", "transformer.mm_projector.image_spatial_proj.0.bias": "model-00002-of-00002.safetensors", "transformer.mm_projector.image_spatial_proj.0.weight": "model-00002-of-00002.safetensors", "transformer.mm_projector.image_spatial_proj.2.bias": "model-00002-of-00002.safetensors", "transformer.mm_projector.image_spatial_proj.2.weight": "model-00002-of-00002.safetensors", "transformer.wte.weight": "model-00001-of-00002.safetensors" } }