scratch / README
zhxchen17's picture
Create README
b063341 verified
weight state dict:
tok_embeddings.weight
layers.0.attention.wqkv.q.weight
layers.0.attention.wqkv.q.scales_and_zeros
layers.0.attention.wqkv.k.weight
layers.0.attention.wqkv.k.scales_and_zeros
layers.0.attention.wqkv.v.weight
layers.0.attention.wqkv.v.scales_and_zeros
layers.0.attention.wo.weight
layers.0.attention.wo.scales_and_zeros
layers.0.feed_forward.w1.weight
layers.0.feed_forward.w1.scales_and_zeros
layers.0.feed_forward.w3.weight
layers.0.feed_forward.w3.scales_and_zeros
layers.0.feed_forward.w2.weight
layers.0.feed_forward.w2.scales_and_zeros
layers.0.ffn_norm.weight
layers.0.attention_norm.weight
layers.1.attention.wqkv.q.weight
layers.1.attention.wqkv.q.scales_and_zeros
layers.1.attention.wqkv.k.weight
layers.1.attention.wqkv.k.scales_and_zeros
layers.1.attention.wqkv.v.weight
layers.1.attention.wqkv.v.scales_and_zeros
layers.1.attention.wo.weight
layers.1.attention.wo.scales_and_zeros
layers.1.feed_forward.w1.weight
layers.1.feed_forward.w1.scales_and_zeros
layers.1.feed_forward.w3.weight
layers.1.feed_forward.w3.scales_and_zeros
layers.1.feed_forward.w2.weight
layers.1.feed_forward.w2.scales_and_zeros
layers.1.ffn_norm.weight
layers.1.attention_norm.weight
layers.2.attention.wqkv.q.weight
layers.2.attention.wqkv.q.scales_and_zeros
layers.2.attention.wqkv.k.weight
layers.2.attention.wqkv.k.scales_and_zeros
layers.2.attention.wqkv.v.weight
layers.2.attention.wqkv.v.scales_and_zeros
layers.2.attention.wo.weight
layers.2.attention.wo.scales_and_zeros
layers.2.feed_forward.w1.weight
layers.2.feed_forward.w1.scales_and_zeros
layers.2.feed_forward.w3.weight
layers.2.feed_forward.w3.scales_and_zeros
layers.2.feed_forward.w2.weight
layers.2.feed_forward.w2.scales_and_zeros
layers.2.ffn_norm.weight
layers.2.attention_norm.weight
layers.3.attention.wqkv.q.weight
layers.3.attention.wqkv.q.scales_and_zeros
layers.3.attention.wqkv.k.weight
layers.3.attention.wqkv.k.scales_and_zeros
layers.3.attention.wqkv.v.weight
layers.3.attention.wqkv.v.scales_and_zeros
layers.3.attention.wo.weight
layers.3.attention.wo.scales_and_zeros
layers.3.feed_forward.w1.weight
layers.3.feed_forward.w1.scales_and_zeros
layers.3.feed_forward.w3.weight
layers.3.feed_forward.w3.scales_and_zeros
layers.3.feed_forward.w2.weight
layers.3.feed_forward.w2.scales_and_zeros
layers.3.ffn_norm.weight
layers.3.attention_norm.weight
layers.4.attention.wqkv.q.weight
layers.4.attention.wqkv.q.scales_and_zeros
layers.4.attention.wqkv.k.weight
layers.4.attention.wqkv.k.scales_and_zeros
layers.4.attention.wqkv.v.weight
layers.4.attention.wqkv.v.scales_and_zeros
layers.4.attention.wo.weight
layers.4.attention.wo.scales_and_zeros
layers.4.feed_forward.w1.weight
layers.4.feed_forward.w1.scales_and_zeros
layers.4.feed_forward.w3.weight
layers.4.feed_forward.w3.scales_and_zeros
layers.4.feed_forward.w2.weight
layers.4.feed_forward.w2.scales_and_zeros
layers.4.ffn_norm.weight
layers.4.attention_norm.weight
layers.5.attention.wqkv.q.weight
layers.5.attention.wqkv.q.scales_and_zeros
layers.5.attention.wqkv.k.weight
layers.5.attention.wqkv.k.scales_and_zeros
layers.5.attention.wqkv.v.weight
layers.5.attention.wqkv.v.scales_and_zeros
layers.5.attention.wo.weight
layers.5.attention.wo.scales_and_zeros
layers.5.feed_forward.w1.weight
layers.5.feed_forward.w1.scales_and_zeros
layers.5.feed_forward.w3.weight
layers.5.feed_forward.w3.scales_and_zeros
layers.5.feed_forward.w2.weight
layers.5.feed_forward.w2.scales_and_zeros
layers.5.ffn_norm.weight
layers.5.attention_norm.weight
layers.6.attention.wqkv.q.weight
layers.6.attention.wqkv.q.scales_and_zeros
layers.6.attention.wqkv.k.weight
layers.6.attention.wqkv.k.scales_and_zeros
layers.6.attention.wqkv.v.weight
layers.6.attention.wqkv.v.scales_and_zeros
layers.6.attention.wo.weight
layers.6.attention.wo.scales_and_zeros
layers.6.feed_forward.w1.weight
layers.6.feed_forward.w1.scales_and_zeros
layers.6.feed_forward.w3.weight
layers.6.feed_forward.w3.scales_and_zeros
layers.6.feed_forward.w2.weight
layers.6.feed_forward.w2.scales_and_zeros
layers.6.ffn_norm.weight
layers.6.attention_norm.weight
layers.7.attention.wqkv.q.weight
layers.7.attention.wqkv.q.scales_and_zeros
layers.7.attention.wqkv.k.weight
layers.7.attention.wqkv.k.scales_and_zeros
layers.7.attention.wqkv.v.weight
layers.7.attention.wqkv.v.scales_and_zeros
layers.7.attention.wo.weight
layers.7.attention.wo.scales_and_zeros
layers.7.feed_forward.w1.weight
layers.7.feed_forward.w1.scales_and_zeros
layers.7.feed_forward.w3.weight
layers.7.feed_forward.w3.scales_and_zeros
layers.7.feed_forward.w2.weight
layers.7.feed_forward.w2.scales_and_zeros
layers.7.ffn_norm.weight
layers.7.attention_norm.weight
layers.8.attention.wqkv.q.weight
layers.8.attention.wqkv.q.scales_and_zeros
layers.8.attention.wqkv.k.weight
layers.8.attention.wqkv.k.scales_and_zeros
layers.8.attention.wqkv.v.weight
layers.8.attention.wqkv.v.scales_and_zeros
layers.8.attention.wo.weight
layers.8.attention.wo.scales_and_zeros
layers.8.feed_forward.w1.weight
layers.8.feed_forward.w1.scales_and_zeros
layers.8.feed_forward.w3.weight
layers.8.feed_forward.w3.scales_and_zeros
layers.8.feed_forward.w2.weight
layers.8.feed_forward.w2.scales_and_zeros
layers.8.ffn_norm.weight
layers.8.attention_norm.weight
layers.9.attention.wqkv.q.weight
layers.9.attention.wqkv.q.scales_and_zeros
layers.9.attention.wqkv.k.weight
layers.9.attention.wqkv.k.scales_and_zeros
layers.9.attention.wqkv.v.weight
layers.9.attention.wqkv.v.scales_and_zeros
layers.9.attention.wo.weight
layers.9.attention.wo.scales_and_zeros
layers.9.feed_forward.w1.weight
layers.9.feed_forward.w1.scales_and_zeros
layers.9.feed_forward.w3.weight
layers.9.feed_forward.w3.scales_and_zeros
layers.9.feed_forward.w2.weight
layers.9.feed_forward.w2.scales_and_zeros
layers.9.ffn_norm.weight
layers.9.attention_norm.weight
layers.10.attention.wqkv.q.weight
layers.10.attention.wqkv.q.scales_and_zeros
layers.10.attention.wqkv.k.weight
layers.10.attention.wqkv.k.scales_and_zeros
layers.10.attention.wqkv.v.weight
layers.10.attention.wqkv.v.scales_and_zeros
layers.10.attention.wo.weight
layers.10.attention.wo.scales_and_zeros
layers.10.feed_forward.w1.weight
layers.10.feed_forward.w1.scales_and_zeros
layers.10.feed_forward.w3.weight
layers.10.feed_forward.w3.scales_and_zeros
layers.10.feed_forward.w2.weight
layers.10.feed_forward.w2.scales_and_zeros
layers.10.ffn_norm.weight
layers.10.attention_norm.weight
layers.11.attention.wqkv.q.weight
layers.11.attention.wqkv.q.scales_and_zeros
layers.11.attention.wqkv.k.weight
layers.11.attention.wqkv.k.scales_and_zeros
layers.11.attention.wqkv.v.weight
layers.11.attention.wqkv.v.scales_and_zeros
layers.11.attention.wo.weight
layers.11.attention.wo.scales_and_zeros
layers.11.feed_forward.w1.weight
layers.11.feed_forward.w1.scales_and_zeros
layers.11.feed_forward.w3.weight
layers.11.feed_forward.w3.scales_and_zeros
layers.11.feed_forward.w2.weight
layers.11.feed_forward.w2.scales_and_zeros
layers.11.ffn_norm.weight
layers.11.attention_norm.weight
layers.12.attention.wqkv.q.weight
layers.12.attention.wqkv.q.scales_and_zeros
layers.12.attention.wqkv.k.weight
layers.12.attention.wqkv.k.scales_and_zeros
layers.12.attention.wqkv.v.weight
layers.12.attention.wqkv.v.scales_and_zeros
layers.12.attention.wo.weight
layers.12.attention.wo.scales_and_zeros
layers.12.feed_forward.w1.weight
layers.12.feed_forward.w1.scales_and_zeros
layers.12.feed_forward.w3.weight
layers.12.feed_forward.w3.scales_and_zeros
layers.12.feed_forward.w2.weight
layers.12.feed_forward.w2.scales_and_zeros
layers.12.ffn_norm.weight
layers.12.attention_norm.weight
layers.13.attention.wqkv.q.weight
layers.13.attention.wqkv.q.scales_and_zeros
layers.13.attention.wqkv.k.weight
layers.13.attention.wqkv.k.scales_and_zeros
layers.13.attention.wqkv.v.weight
layers.13.attention.wqkv.v.scales_and_zeros
layers.13.attention.wo.weight
layers.13.attention.wo.scales_and_zeros
layers.13.feed_forward.w1.weight
layers.13.feed_forward.w1.scales_and_zeros
layers.13.feed_forward.w3.weight
layers.13.feed_forward.w3.scales_and_zeros
layers.13.feed_forward.w2.weight
layers.13.feed_forward.w2.scales_and_zeros
layers.13.ffn_norm.weight
layers.13.attention_norm.weight
layers.14.attention.wqkv.q.weight
layers.14.attention.wqkv.q.scales_and_zeros
layers.14.attention.wqkv.k.weight
layers.14.attention.wqkv.k.scales_and_zeros
layers.14.attention.wqkv.v.weight
layers.14.attention.wqkv.v.scales_and_zeros
layers.14.attention.wo.weight
layers.14.attention.wo.scales_and_zeros
layers.14.feed_forward.w1.weight
layers.14.feed_forward.w1.scales_and_zeros
layers.14.feed_forward.w3.weight
layers.14.feed_forward.w3.scales_and_zeros
layers.14.feed_forward.w2.weight
layers.14.feed_forward.w2.scales_and_zeros
layers.14.ffn_norm.weight
layers.14.attention_norm.weight
layers.15.attention.wqkv.q.weight
layers.15.attention.wqkv.q.scales_and_zeros
layers.15.attention.wqkv.k.weight
layers.15.attention.wqkv.k.scales_and_zeros
layers.15.attention.wqkv.v.weight
layers.15.attention.wqkv.v.scales_and_zeros
layers.15.attention.wo.weight
layers.15.attention.wo.scales_and_zeros
layers.15.feed_forward.w1.weight
layers.15.feed_forward.w1.scales_and_zeros
layers.15.feed_forward.w3.weight
layers.15.feed_forward.w3.scales_and_zeros
layers.15.feed_forward.w2.weight
layers.15.feed_forward.w2.scales_and_zeros
layers.15.ffn_norm.weight
layers.15.attention_norm.weight
layers.16.attention.wqkv.q.weight
layers.16.attention.wqkv.q.scales_and_zeros
layers.16.attention.wqkv.k.weight
layers.16.attention.wqkv.k.scales_and_zeros
layers.16.attention.wqkv.v.weight
layers.16.attention.wqkv.v.scales_and_zeros
layers.16.attention.wo.weight
layers.16.attention.wo.scales_and_zeros
layers.16.feed_forward.w1.weight
layers.16.feed_forward.w1.scales_and_zeros
layers.16.feed_forward.w3.weight
layers.16.feed_forward.w3.scales_and_zeros
layers.16.feed_forward.w2.weight
layers.16.feed_forward.w2.scales_and_zeros
layers.16.ffn_norm.weight
layers.16.attention_norm.weight
layers.17.attention.wqkv.q.weight
layers.17.attention.wqkv.q.scales_and_zeros
layers.17.attention.wqkv.k.weight
layers.17.attention.wqkv.k.scales_and_zeros
layers.17.attention.wqkv.v.weight
layers.17.attention.wqkv.v.scales_and_zeros
layers.17.attention.wo.weight
layers.17.attention.wo.scales_and_zeros
layers.17.feed_forward.w1.weight
layers.17.feed_forward.w1.scales_and_zeros
layers.17.feed_forward.w3.weight
layers.17.feed_forward.w3.scales_and_zeros
layers.17.feed_forward.w2.weight
layers.17.feed_forward.w2.scales_and_zeros
layers.17.ffn_norm.weight
layers.17.attention_norm.weight
layers.18.attention.wqkv.q.weight
layers.18.attention.wqkv.q.scales_and_zeros
layers.18.attention.wqkv.k.weight
layers.18.attention.wqkv.k.scales_and_zeros
layers.18.attention.wqkv.v.weight
layers.18.attention.wqkv.v.scales_and_zeros
layers.18.attention.wo.weight
layers.18.attention.wo.scales_and_zeros
layers.18.feed_forward.w1.weight
layers.18.feed_forward.w1.scales_and_zeros
layers.18.feed_forward.w3.weight
layers.18.feed_forward.w3.scales_and_zeros
layers.18.feed_forward.w2.weight
layers.18.feed_forward.w2.scales_and_zeros
layers.18.ffn_norm.weight
layers.18.attention_norm.weight
layers.19.attention.wqkv.q.weight
layers.19.attention.wqkv.q.scales_and_zeros
layers.19.attention.wqkv.k.weight
layers.19.attention.wqkv.k.scales_and_zeros
layers.19.attention.wqkv.v.weight
layers.19.attention.wqkv.v.scales_and_zeros
layers.19.attention.wo.weight
layers.19.attention.wo.scales_and_zeros
layers.19.feed_forward.w1.weight
layers.19.feed_forward.w1.scales_and_zeros
layers.19.feed_forward.w3.weight
layers.19.feed_forward.w3.scales_and_zeros
layers.19.feed_forward.w2.weight
layers.19.feed_forward.w2.scales_and_zeros
layers.19.ffn_norm.weight
layers.19.attention_norm.weight
layers.20.attention.wqkv.q.weight
layers.20.attention.wqkv.q.scales_and_zeros
layers.20.attention.wqkv.k.weight
layers.20.attention.wqkv.k.scales_and_zeros
layers.20.attention.wqkv.v.weight
layers.20.attention.wqkv.v.scales_and_zeros
layers.20.attention.wo.weight
layers.20.attention.wo.scales_and_zeros
layers.20.feed_forward.w1.weight
layers.20.feed_forward.w1.scales_and_zeros
layers.20.feed_forward.w3.weight
layers.20.feed_forward.w3.scales_and_zeros
layers.20.feed_forward.w2.weight
layers.20.feed_forward.w2.scales_and_zeros
layers.20.ffn_norm.weight
layers.20.attention_norm.weight
layers.21.attention.wqkv.q.weight
layers.21.attention.wqkv.q.scales_and_zeros
layers.21.attention.wqkv.k.weight
layers.21.attention.wqkv.k.scales_and_zeros
layers.21.attention.wqkv.v.weight
layers.21.attention.wqkv.v.scales_and_zeros
layers.21.attention.wo.weight
layers.21.attention.wo.scales_and_zeros
layers.21.feed_forward.w1.weight
layers.21.feed_forward.w1.scales_and_zeros
layers.21.feed_forward.w3.weight
layers.21.feed_forward.w3.scales_and_zeros
layers.21.feed_forward.w2.weight
layers.21.feed_forward.w2.scales_and_zeros
layers.21.ffn_norm.weight
layers.21.attention_norm.weight
layers.22.attention.wqkv.q.weight
layers.22.attention.wqkv.q.scales_and_zeros
layers.22.attention.wqkv.k.weight
layers.22.attention.wqkv.k.scales_and_zeros
layers.22.attention.wqkv.v.weight
layers.22.attention.wqkv.v.scales_and_zeros
layers.22.attention.wo.weight
layers.22.attention.wo.scales_and_zeros
layers.22.feed_forward.w1.weight
layers.22.feed_forward.w1.scales_and_zeros
layers.22.feed_forward.w3.weight
layers.22.feed_forward.w3.scales_and_zeros
layers.22.feed_forward.w2.weight
layers.22.feed_forward.w2.scales_and_zeros
layers.22.ffn_norm.weight
layers.22.attention_norm.weight
layers.23.attention.wqkv.q.weight
layers.23.attention.wqkv.q.scales_and_zeros
layers.23.attention.wqkv.k.weight
layers.23.attention.wqkv.k.scales_and_zeros
layers.23.attention.wqkv.v.weight
layers.23.attention.wqkv.v.scales_and_zeros
layers.23.attention.wo.weight
layers.23.attention.wo.scales_and_zeros
layers.23.feed_forward.w1.weight
layers.23.feed_forward.w1.scales_and_zeros
layers.23.feed_forward.w3.weight
layers.23.feed_forward.w3.scales_and_zeros
layers.23.feed_forward.w2.weight
layers.23.feed_forward.w2.scales_and_zeros
layers.23.ffn_norm.weight
layers.23.attention_norm.weight
layers.24.attention.wqkv.q.weight
layers.24.attention.wqkv.q.scales_and_zeros
layers.24.attention.wqkv.k.weight
layers.24.attention.wqkv.k.scales_and_zeros
layers.24.attention.wqkv.v.weight
layers.24.attention.wqkv.v.scales_and_zeros
layers.24.attention.wo.weight
layers.24.attention.wo.scales_and_zeros
layers.24.feed_forward.w1.weight
layers.24.feed_forward.w1.scales_and_zeros
layers.24.feed_forward.w3.weight
layers.24.feed_forward.w3.scales_and_zeros
layers.24.feed_forward.w2.weight
layers.24.feed_forward.w2.scales_and_zeros
layers.24.ffn_norm.weight
layers.24.attention_norm.weight
layers.25.attention.wqkv.q.weight
layers.25.attention.wqkv.q.scales_and_zeros
layers.25.attention.wqkv.k.weight
layers.25.attention.wqkv.k.scales_and_zeros
layers.25.attention.wqkv.v.weight
layers.25.attention.wqkv.v.scales_and_zeros
layers.25.attention.wo.weight
layers.25.attention.wo.scales_and_zeros
layers.25.feed_forward.w1.weight
layers.25.feed_forward.w1.scales_and_zeros
layers.25.feed_forward.w3.weight
layers.25.feed_forward.w3.scales_and_zeros
layers.25.feed_forward.w2.weight
layers.25.feed_forward.w2.scales_and_zeros
layers.25.ffn_norm.weight
layers.25.attention_norm.weight
layers.26.attention.wqkv.q.weight
layers.26.attention.wqkv.q.scales_and_zeros
layers.26.attention.wqkv.k.weight
layers.26.attention.wqkv.k.scales_and_zeros
layers.26.attention.wqkv.v.weight
layers.26.attention.wqkv.v.scales_and_zeros
layers.26.attention.wo.weight
layers.26.attention.wo.scales_and_zeros
layers.26.feed_forward.w1.weight
layers.26.feed_forward.w1.scales_and_zeros
layers.26.feed_forward.w3.weight
layers.26.feed_forward.w3.scales_and_zeros
layers.26.feed_forward.w2.weight
layers.26.feed_forward.w2.scales_and_zeros
layers.26.ffn_norm.weight
layers.26.attention_norm.weight
layers.27.attention.wqkv.q.weight
layers.27.attention.wqkv.q.scales_and_zeros
layers.27.attention.wqkv.k.weight
layers.27.attention.wqkv.k.scales_and_zeros
layers.27.attention.wqkv.v.weight
layers.27.attention.wqkv.v.scales_and_zeros
layers.27.attention.wo.weight
layers.27.attention.wo.scales_and_zeros
layers.27.feed_forward.w1.weight
layers.27.feed_forward.w1.scales_and_zeros
layers.27.feed_forward.w3.weight
layers.27.feed_forward.w3.scales_and_zeros
layers.27.feed_forward.w2.weight
layers.27.feed_forward.w2.scales_and_zeros
layers.27.ffn_norm.weight
layers.27.attention_norm.weight
layers.28.attention.wqkv.q.weight
layers.28.attention.wqkv.q.scales_and_zeros
layers.28.attention.wqkv.k.weight
layers.28.attention.wqkv.k.scales_and_zeros
layers.28.attention.wqkv.v.weight
layers.28.attention.wqkv.v.scales_and_zeros
layers.28.attention.wo.weight
layers.28.attention.wo.scales_and_zeros
layers.28.feed_forward.w1.weight
layers.28.feed_forward.w1.scales_and_zeros
layers.28.feed_forward.w3.weight
layers.28.feed_forward.w3.scales_and_zeros
layers.28.feed_forward.w2.weight
layers.28.feed_forward.w2.scales_and_zeros
layers.28.ffn_norm.weight
layers.28.attention_norm.weight
layers.29.attention.wqkv.q.weight
layers.29.attention.wqkv.q.scales_and_zeros
layers.29.attention.wqkv.k.weight
layers.29.attention.wqkv.k.scales_and_zeros
layers.29.attention.wqkv.v.weight
layers.29.attention.wqkv.v.scales_and_zeros
layers.29.attention.wo.weight
layers.29.attention.wo.scales_and_zeros
layers.29.feed_forward.w1.weight
layers.29.feed_forward.w1.scales_and_zeros
layers.29.feed_forward.w3.weight
layers.29.feed_forward.w3.scales_and_zeros
layers.29.feed_forward.w2.weight
layers.29.feed_forward.w2.scales_and_zeros
layers.29.ffn_norm.weight
layers.29.attention_norm.weight
layers.30.attention.wqkv.q.weight
layers.30.attention.wqkv.q.scales_and_zeros
layers.30.attention.wqkv.k.weight
layers.30.attention.wqkv.k.scales_and_zeros
layers.30.attention.wqkv.v.weight
layers.30.attention.wqkv.v.scales_and_zeros
layers.30.attention.wo.weight
layers.30.attention.wo.scales_and_zeros
layers.30.feed_forward.w1.weight
layers.30.feed_forward.w1.scales_and_zeros
layers.30.feed_forward.w3.weight
layers.30.feed_forward.w3.scales_and_zeros
layers.30.feed_forward.w2.weight
layers.30.feed_forward.w2.scales_and_zeros
layers.30.ffn_norm.weight
layers.30.attention_norm.weight
layers.31.attention.wqkv.q.weight
layers.31.attention.wqkv.q.scales_and_zeros
layers.31.attention.wqkv.k.weight
layers.31.attention.wqkv.k.scales_and_zeros
layers.31.attention.wqkv.v.weight
layers.31.attention.wqkv.v.scales_and_zeros
layers.31.attention.wo.weight
layers.31.attention.wo.scales_and_zeros
layers.31.feed_forward.w1.weight
layers.31.feed_forward.w1.scales_and_zeros
layers.31.feed_forward.w3.weight
layers.31.feed_forward.w3.scales_and_zeros
layers.31.feed_forward.w2.weight
layers.31.feed_forward.w2.scales_and_zeros
layers.31.ffn_norm.weight
layers.31.attention_norm.weight
norm.weight
output.weight
output.scales_and_zeros