| { | |
| "metadata": { | |
| "total_size": 5345657856 | |
| }, | |
| "weight_map": { | |
| "decoder.embed_tokens.weight": "model-00001-of-00002.safetensors", | |
| "decoder.final_layer_norm.weight": "model-00002-of-00002.safetensors", | |
| "decoder.layer.0.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.self_attention.attention.relative_attention_bias.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.0.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.1.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.10.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.11.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.12.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.13.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.14.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.15.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.16.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.mlp.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors", | |
| "decoder.layer.17.mlp.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors", | |
| "decoder.layer.17.mlp.layer_norm.weight": "model-00002-of-00002.safetensors", | |
| "decoder.layer.17.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.17.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.2.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.3.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.4.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.5.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.6.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.7.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.8.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.encoder_decoder_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.encoder_decoder_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.encoder_decoder_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.encoder_decoder_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.encoder_decoder_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.mlp.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.mlp.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.mlp.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.mlp.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.self_attention.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.self_attention.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.self_attention.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.self_attention.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "decoder.layer.9.self_attention.layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "decoder.lm_head.weight": "model-00002-of-00002.safetensors", | |
| "encoder.embeddings.column_embedder.weight": "model-00001-of-00002.safetensors", | |
| "encoder.embeddings.patch_projection.bias": "model-00001-of-00002.safetensors", | |
| "encoder.embeddings.patch_projection.weight": "model-00001-of-00002.safetensors", | |
| "encoder.embeddings.row_embedder.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.0.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.0.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.0.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.0.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.0.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.0.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.0.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.0.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.0.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.1.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.1.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.1.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.1.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.1.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.1.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.1.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.1.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.1.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.10.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.10.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.10.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.10.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.10.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.10.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.10.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.10.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.10.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.11.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.11.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.11.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.11.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.11.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.11.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.11.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.11.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.11.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.12.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.12.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.12.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.12.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.12.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.12.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.12.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.12.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.12.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.13.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.13.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.13.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.13.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.13.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.13.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.13.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.13.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.13.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.14.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.14.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.14.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.14.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.14.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.14.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.14.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.14.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.14.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.15.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.15.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.15.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.15.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.15.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.15.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.15.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.15.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.15.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.16.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.16.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.16.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.16.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.16.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.16.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.16.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.16.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.16.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.17.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.17.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.17.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.17.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.17.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.17.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.17.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.17.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.17.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.2.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.2.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.2.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.2.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.2.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.2.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.2.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.2.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.2.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.3.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.3.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.3.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.3.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.3.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.3.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.3.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.3.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.3.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.4.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.4.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.4.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.4.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.4.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.4.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.4.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.4.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.4.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.5.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.5.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.5.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.5.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.5.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.5.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.5.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.5.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.5.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.6.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.6.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.6.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.6.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.6.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.6.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.6.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.6.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.6.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.7.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.7.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.7.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.7.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.7.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.7.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.7.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.7.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.7.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.8.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.8.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.8.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.8.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.8.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.8.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.8.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.8.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.8.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.9.attention.key.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.9.attention.output.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.9.attention.query.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.9.attention.value.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.9.mlp.wi_0.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.9.mlp.wi_1.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.9.mlp.wo.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.9.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.encoder.layer.9.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors", | |
| "encoder.layernorm.weight": "model-00001-of-00002.safetensors" | |
| } | |
| } | |