Cerebras-GPT-Intermediate / CerebrasGPT-111_muP /pytorch_model.bin.index.json
Yishi Xu
add CerebrasGPT-111_muP
898d006
raw
history blame
9.79 kB
{
"metadata": {
"total_size": 598591488
},
"weight_map": {
"transformer.wte.weight": "pytorch_model-00001-of-00001.bin",
"transformer.wpe.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
"transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
"transformer.ln_f.weight": "pytorch_model-00001-of-00001.bin",
"transformer.ln_f.bias": "pytorch_model-00001-of-00001.bin",
"lm_head.weight": "pytorch_model-00001-of-00001.bin"
}
}