llama-3.1-405b-inst-mp8-orig / mp8 /consolidated.03 /consolidated.pth.index.json
thamada
add mp8
efd5d24
raw
history blame contribute delete
No virus
82.9 kB
{
"metadata": {
"total_size": 101470601216
},
"weight_map": {
"tok_embeddings.weight": "consolidated-00001-of-00022.pth",
"layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth",
"layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth",
"layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth",
"layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth",
"layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
"layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
"layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
"layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth",
"layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth",
"layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth",
"layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth",
"layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth",
"layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth",
"layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
"layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
"layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
"layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth",
"layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth",
"layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth",
"layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth",
"layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth",
"layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth",
"layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
"layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
"layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
"layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth",
"layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth",
"layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth",
"layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth",
"layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth",
"layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth",
"layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
"layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
"layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
"layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth",
"layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth",
"layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth",
"layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth",
"layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth",
"layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth",
"layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
"layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
"layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
"layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth",
"layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth",
"layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth",
"layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth",
"layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth",
"layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth",
"layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
"layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
"layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
"layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth",
"layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth",
"layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth",
"layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth",
"layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth",
"layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth",
"layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
"layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
"layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
"layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth",
"layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth",
"layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth",
"layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth",
"layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth",
"layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth",
"layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
"layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
"layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
"layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth",
"layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth",
"layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth",
"layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth",
"layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth",
"layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth",
"layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
"layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
"layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
"layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth",
"layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth",
"layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth",
"layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth",
"layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth",
"layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth",
"layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
"layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
"layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
"layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth",
"layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth",
"layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth",
"layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth",
"layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth",
"layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth",
"layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
"layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
"layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
"layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth",
"layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth",
"layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth",
"layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth",
"layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth",
"layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth",
"layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
"layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
"layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
"layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth",
"layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth",
"layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth",
"layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth",
"layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth",
"layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth",
"layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
"layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
"layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
"layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth",
"layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth",
"layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth",
"layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth",
"layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth",
"layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth",
"layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
"layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
"layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
"layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth",
"layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth",
"layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth",
"layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth",
"layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth",
"layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth",
"layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
"layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
"layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
"layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth",
"layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth",
"layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth",
"layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth",
"layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth",
"layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth",
"layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
"layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
"layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
"layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth",
"layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth",
"layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth",
"layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth",
"layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth",
"layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth",
"layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
"layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
"layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
"layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth",
"layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth",
"layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth",
"layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth",
"layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth",
"layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth",
"layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
"layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
"layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
"layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth",
"layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth",
"layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth",
"layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth",
"layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth",
"layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth",
"layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
"layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
"layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
"layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth",
"layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth",
"layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth",
"layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth",
"layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth",
"layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth",
"layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
"layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
"layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
"layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth",
"layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth",
"layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth",
"layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth",
"layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth",
"layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth",
"layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
"layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
"layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
"layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth",
"layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth",
"layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth",
"layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth",
"layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth",
"layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth",
"layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
"layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
"layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
"layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth",
"layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth",
"layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth",
"layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth",
"layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth",
"layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth",
"layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
"layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
"layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
"layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth",
"layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth",
"layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth",
"layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth",
"layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth",
"layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth",
"layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
"layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
"layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
"layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth",
"layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth",
"layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth",
"layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth",
"layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth",
"layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth",
"layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
"layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
"layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
"layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth",
"layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth",
"layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth",
"layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth",
"layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth",
"layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth",
"layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
"layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
"layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
"layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth",
"layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth",
"layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth",
"layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth",
"layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth",
"layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth",
"layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
"layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
"layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
"layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth",
"layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth",
"layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth",
"layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth",
"layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth",
"layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth",
"layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
"layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
"layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
"layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth",
"layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth",
"layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth",
"layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth",
"layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth",
"layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth",
"layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
"layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
"layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
"layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth",
"layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth",
"layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth",
"layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth",
"layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth",
"layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth",
"layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
"layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
"layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
"layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth",
"layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth",
"layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth",
"layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth",
"layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth",
"layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth",
"layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
"layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
"layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
"layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth",
"layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth",
"layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth",
"layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth",
"layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth",
"layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth",
"layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
"layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
"layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
"layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth",
"layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth",
"layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth",
"layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth",
"layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth",
"layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth",
"layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
"layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
"layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
"layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth",
"layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth",
"layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth",
"layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth",
"layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth",
"layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth",
"layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
"layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
"layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
"layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth",
"layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth",
"layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth",
"layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth",
"layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth",
"layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth",
"layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
"layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
"layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
"layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth",
"layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth",
"layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth",
"layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth",
"layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth",
"layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth",
"layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
"layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
"layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
"layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth",
"layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth",
"layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth",
"layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth",
"layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth",
"layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth",
"layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
"layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
"layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
"layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth",
"layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth",
"layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth",
"layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth",
"layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth",
"layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth",
"layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
"layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
"layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
"layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth",
"layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth",
"layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth",
"layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth",
"layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth",
"layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth",
"layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
"layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
"layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
"layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth",
"layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth",
"layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth",
"layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth",
"layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth",
"layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth",
"layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
"layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
"layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
"layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth",
"layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth",
"layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth",
"layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth",
"layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth",
"layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth",
"layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
"layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
"layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
"layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth",
"layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth",
"layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth",
"layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth",
"layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth",
"layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth",
"layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
"layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
"layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
"layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth",
"layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth",
"layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth",
"layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth",
"layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth",
"layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth",
"layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
"layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
"layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
"layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth",
"layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth",
"layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth",
"layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth",
"layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth",
"layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth",
"layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
"layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
"layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
"layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth",
"layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth",
"layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth",
"layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth",
"layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth",
"layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth",
"layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
"layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
"layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
"layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth",
"layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth",
"layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth",
"layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth",
"layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth",
"layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth",
"layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
"layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
"layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
"layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth",
"layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth",
"layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth",
"layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth",
"layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth",
"layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth",
"layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
"layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
"layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
"layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth",
"layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth",
"layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth",
"layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth",
"layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth",
"layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth",
"layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
"layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
"layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
"layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth",
"layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth",
"layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth",
"layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth",
"layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth",
"layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth",
"layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
"layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
"layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
"layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth",
"layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth",
"layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth",
"layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth",
"layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth",
"layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth",
"layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
"layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
"layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
"layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth",
"layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth",
"layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth",
"layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth",
"layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth",
"layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth",
"layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
"layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
"layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
"layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth",
"layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth",
"layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth",
"layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth",
"layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth",
"layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth",
"layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
"layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
"layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
"layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth",
"layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth",
"layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth",
"layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth",
"layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth",
"layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth",
"layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
"layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
"layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
"layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth",
"layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth",
"layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth",
"layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth",
"layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth",
"layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth",
"layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
"layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
"layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
"layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth",
"layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth",
"layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth",
"layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth",
"layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth",
"layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth",
"layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
"layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
"layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
"layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth",
"layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth",
"layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth",
"layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth",
"layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth",
"layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth",
"layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
"layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
"layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
"layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth",
"layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth",
"layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth",
"layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth",
"layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth",
"layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth",
"layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
"layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
"layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
"layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth",
"layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth",
"layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth",
"layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth",
"layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth",
"layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth",
"layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
"layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
"layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
"layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth",
"layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth",
"layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth",
"layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth",
"layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth",
"layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth",
"layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
"layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
"layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
"layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth",
"layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth",
"layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth",
"layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth",
"layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth",
"layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth",
"layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
"layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
"layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
"layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth",
"layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth",
"layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth",
"layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth",
"layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth",
"layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth",
"layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
"layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
"layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
"layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth",
"layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth",
"layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth",
"layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth",
"layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth",
"layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth",
"layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
"layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
"layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
"layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth",
"layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth",
"layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth",
"layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth",
"layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth",
"layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth",
"layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
"layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
"layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
"layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth",
"layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth",
"layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth",
"layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth",
"layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth",
"layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth",
"layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
"layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
"layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
"layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth",
"layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth",
"layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth",
"layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth",
"layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth",
"layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth",
"layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
"layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
"layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
"layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth",
"layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth",
"layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth",
"layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth",
"layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth",
"layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth",
"layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
"layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
"layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
"layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth",
"layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth",
"layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth",
"layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth",
"layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth",
"layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth",
"layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
"layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
"layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
"layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth",
"layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth",
"layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth",
"layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth",
"layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth",
"layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth",
"layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
"layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
"layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
"layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth",
"layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth",
"layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth",
"layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth",
"layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth",
"layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth",
"layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
"layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
"layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
"layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth",
"layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth",
"layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth",
"layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth",
"layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth",
"layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth",
"layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
"layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
"layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
"layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth",
"layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth",
"layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth",
"layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth",
"layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth",
"layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth",
"layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
"layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
"layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
"layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth",
"layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth",
"layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth",
"layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth",
"layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth",
"layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth",
"layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
"layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
"layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
"layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth",
"layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth",
"layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth",
"layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth",
"layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth",
"layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth",
"layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
"layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
"layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
"layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth",
"layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth",
"layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth",
"layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth",
"layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth",
"layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth",
"layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
"layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
"layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
"layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth",
"layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth",
"layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth",
"layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth",
"layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth",
"layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth",
"layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
"layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
"layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
"layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth",
"layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth",
"layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth",
"layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth",
"layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth",
"layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth",
"layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
"layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
"layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
"layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth",
"layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth",
"layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth",
"layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth",
"layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth",
"layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth",
"layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
"layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
"layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
"layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth",
"layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth",
"layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth",
"layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth",
"layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth",
"layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth",
"layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
"layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
"layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
"layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth",
"layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth",
"layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth",
"layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth",
"layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth",
"layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth",
"layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
"layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
"layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
"layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth",
"layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth",
"layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth",
"layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth",
"layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth",
"layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth",
"layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
"layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
"layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
"layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth",
"layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth",
"layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth",
"layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth",
"layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth",
"layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth",
"layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
"layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
"layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
"layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth",
"layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth",
"layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth",
"layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth",
"layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth",
"layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth",
"layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
"layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
"layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
"layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth",
"layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth",
"layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth",
"layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth",
"layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth",
"layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth",
"layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
"layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
"layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
"layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth",
"layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth",
"layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth",
"layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth",
"layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth",
"layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth",
"layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
"layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
"layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
"layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth",
"layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth",
"layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth",
"layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth",
"layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth",
"layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth",
"layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
"layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
"layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
"layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth",
"layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth",
"layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth",
"layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth",
"layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth",
"layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth",
"layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
"layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
"layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
"layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth",
"layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth",
"layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth",
"layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth",
"layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth",
"layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth",
"layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
"layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
"layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
"layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth",
"layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth",
"layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth",
"layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth",
"layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth",
"layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth",
"layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
"layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
"layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
"layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth",
"layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth",
"layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth",
"layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth",
"layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth",
"layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth",
"layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
"layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
"layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
"layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth",
"layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth",
"layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth",
"layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth",
"layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth",
"layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth",
"layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
"layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
"layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
"layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth",
"layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth",
"layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth",
"layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth",
"layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth",
"layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth",
"layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
"layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
"layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
"layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth",
"layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth",
"layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth",
"layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth",
"layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth",
"layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth",
"layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
"layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
"layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
"layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth",
"layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth",
"layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth",
"layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth",
"layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth",
"layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth",
"layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
"layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
"layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
"layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth",
"layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth",
"layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth",
"layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth",
"layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth",
"layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth",
"layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
"layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
"layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
"layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth",
"layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth",
"layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth",
"layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth",
"layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth",
"layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth",
"layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
"layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
"layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
"layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth",
"layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth",
"layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth",
"layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth",
"layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth",
"layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth",
"layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
"layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
"layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
"layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth",
"layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth",
"layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth",
"layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth",
"layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth",
"layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth",
"layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
"layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
"layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
"layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth",
"layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth",
"layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth",
"layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth",
"layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth",
"layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth",
"layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
"layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
"layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
"layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth",
"layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth",
"layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth",
"layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth",
"layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth",
"layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth",
"layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
"layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
"layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
"layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth",
"layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth",
"layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth",
"layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth",
"layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth",
"layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth",
"layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
"layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
"layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
"layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth",
"layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth",
"layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth",
"layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth",
"layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth",
"layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth",
"layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
"layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
"layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
"layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth",
"layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth",
"layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth",
"layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth",
"layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth",
"layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth",
"layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
"layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
"layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
"layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth",
"layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth",
"layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth",
"layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth",
"layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth",
"layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth",
"layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
"layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
"layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
"layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth",
"layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth",
"layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth",
"layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth",
"layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth",
"layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth",
"layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
"layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
"layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
"layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth",
"layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth",
"layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth",
"layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth",
"layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth",
"layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth",
"layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
"layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
"layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
"layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth",
"layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth",
"layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth",
"layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth",
"layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth",
"layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth",
"layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
"layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
"layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
"layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth",
"layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth",
"layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth",
"layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth",
"layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth",
"layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth",
"layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
"layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
"layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
"layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth",
"layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth",
"layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth",
"layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth",
"layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth",
"layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth",
"layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
"layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
"layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
"layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth",
"layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth",
"layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth",
"layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth",
"layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth",
"layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth",
"layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
"layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
"layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
"layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth",
"layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth",
"layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth",
"layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth",
"layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth",
"layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth",
"layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
"layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
"layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
"layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth",
"layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth",
"layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth",
"layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth",
"layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth",
"layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth",
"layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
"layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
"layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
"layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth",
"layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth",
"layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth",
"layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth",
"layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth",
"layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth",
"layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
"layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
"layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
"layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth",
"layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth",
"layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth",
"layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth",
"layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth",
"layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth",
"layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
"layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
"layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
"layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth",
"layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth",
"layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth",
"layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth",
"layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth",
"layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth",
"layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
"layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
"layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
"layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth",
"layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth",
"layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth",
"layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth",
"layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth",
"layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth",
"layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
"layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
"layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
"layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth",
"layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth",
"layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth",
"layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth",
"layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth",
"layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth",
"layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
"layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
"layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
"layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth",
"layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth",
"layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth",
"layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth",
"layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth",
"layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth",
"layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
"layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
"layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
"layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth",
"layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth",
"layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth",
"layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth",
"layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth",
"layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth",
"layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
"layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
"layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
"layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth",
"layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth",
"layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth",
"layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth",
"layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth",
"layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth",
"layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
"layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
"layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
"layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth",
"layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth",
"layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth",
"layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth",
"layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth",
"layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth",
"layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
"layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
"layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
"layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth",
"layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth",
"layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth",
"layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth",
"layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth",
"layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth",
"layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
"layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
"layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
"layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth",
"layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth",
"layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth",
"layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth",
"layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth",
"layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth",
"layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
"layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
"layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
"layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth",
"layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth",
"layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth",
"layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth",
"layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth",
"layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth",
"layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
"layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
"layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
"layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth",
"layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth",
"layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth",
"layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth",
"layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth",
"layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth",
"layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
"layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
"layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
"layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth",
"layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth",
"layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth",
"layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth",
"layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth",
"layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth",
"layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
"layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
"layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
"layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth",
"layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth",
"layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth",
"layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth",
"layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth",
"layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth",
"layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
"layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth",
"layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth",
"layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth",
"layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth",
"norm.weight": "consolidated-00022-of-00022.pth",
"output.weight": "consolidated-00022-of-00022.pth"
}
}