|
{ |
|
"metadata": { |
|
"total_size": 9261428736 |
|
}, |
|
"weight_map": { |
|
"block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors", |
|
"block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors", |
|
"block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors", |
|
"block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors", |
|
"block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors", |
|
"block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors", |
|
"block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", |
|
"block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", |
|
"block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors", |
|
"block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", |
|
"block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", |
|
"block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", |
|
"block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", |
|
"block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", |
|
"block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", |
|
"block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", |
|
"block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", |
|
"final_layer_norm.weight": "model-00002-of-00002.safetensors" |
|
} |
|
} |
|
|