StandardMoE-1B-fineweb_edu-10BT / model.safetensors.index.json
robinfaro's picture
Upload MoEGPTForCausalLM
ac20a5f verified
{
"metadata": {
"total_size": 7094112768
},
"weight_map": {
"lm_head.weight": "model-00002-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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.experts.1.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.experts.1.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.experts.2.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.experts.2.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.experts.3.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.experts.3.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.experts.4.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.experts.4.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.experts.5.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.experts.5.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.17.mlp.router.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.attn.c_attn.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.attn.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.ln_1.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.ln_2.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.0.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.0.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.1.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.1.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.2.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.2.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.3.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.3.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.4.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.4.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.5.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.experts.5.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mlp.router.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.attn.c_attn.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.attn.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.ln_1.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.ln_2.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.0.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.0.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.1.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.1.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.2.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.2.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.3.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.3.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.4.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.4.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.5.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.experts.5.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mlp.router.weight": "model-00002-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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.router.weight": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.c_attn.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.attn.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.ln_1.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.ln_2.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.0.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.0.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.1.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.1.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.2.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.2.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.3.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.3.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.4.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.4.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.5.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.experts.5.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mlp.router.weight": "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-00002-of-00002.safetensors",
"transformer.h.21.ln_2.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.0.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.0.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.1.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.1.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.2.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.2.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.3.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.3.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.4.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.4.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.5.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.experts.5.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.0.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.1.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.1.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.2.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.2.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.3.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.3.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.4.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.4.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.5.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.experts.5.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.0.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.1.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.1.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.2.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.2.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.3.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.3.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.4.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.4.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.5.c_fc.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.experts.5.c_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mlp.router.weight": "model-00002-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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.router.weight": "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.experts.0.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.1.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.2.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.3.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.4.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.4.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.5.c_fc.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.experts.5.c_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.router.weight": "model-00001-of-00002.safetensors",
"transformer.ln_f.weight": "model-00002-of-00002.safetensors",
"transformer.wpe.weight": "model-00001-of-00002.safetensors",
"transformer.wte.weight": "model-00001-of-00002.safetensors"
}
}