| *.7z filter=lfs diff=lfs merge=lfs -text |
| *.arrow filter=lfs diff=lfs merge=lfs -text |
| *.bin filter=lfs diff=lfs merge=lfs -text |
| *.bz2 filter=lfs diff=lfs merge=lfs -text |
| *.ckpt filter=lfs diff=lfs merge=lfs -text |
| *.ftz filter=lfs diff=lfs merge=lfs -text |
| *.gz filter=lfs diff=lfs merge=lfs -text |
| *.h5 filter=lfs diff=lfs merge=lfs -text |
| *.joblib filter=lfs diff=lfs merge=lfs -text |
| *.lfs.* filter=lfs diff=lfs merge=lfs -text |
| *.mlmodel filter=lfs diff=lfs merge=lfs -text |
| *.model filter=lfs diff=lfs merge=lfs -text |
| *.msgpack filter=lfs diff=lfs merge=lfs -text |
| *.npy filter=lfs diff=lfs merge=lfs -text |
| *.npz filter=lfs diff=lfs merge=lfs -text |
| *.onnx filter=lfs diff=lfs merge=lfs -text |
| *.ot filter=lfs diff=lfs merge=lfs -text |
| *.parquet filter=lfs diff=lfs merge=lfs -text |
| *.pb filter=lfs diff=lfs merge=lfs -text |
| *.pickle filter=lfs diff=lfs merge=lfs -text |
| *.pkl filter=lfs diff=lfs merge=lfs -text |
| *.pt filter=lfs diff=lfs merge=lfs -text |
| *.pth filter=lfs diff=lfs merge=lfs -text |
| *.rar filter=lfs diff=lfs merge=lfs -text |
| *.safetensors filter=lfs diff=lfs merge=lfs -text |
| saved_model/**/* filter=lfs diff=lfs merge=lfs -text |
| *.tar.* filter=lfs diff=lfs merge=lfs -text |
| *.tar filter=lfs diff=lfs merge=lfs -text |
| *.tflite filter=lfs diff=lfs merge=lfs -text |
| *.tgz filter=lfs diff=lfs merge=lfs -text |
| *.wasm filter=lfs diff=lfs merge=lfs -text |
| *.xz filter=lfs diff=lfs merge=lfs -text |
| *.zip filter=lfs diff=lfs merge=lfs -text |
| *.zst filter=lfs diff=lfs merge=lfs -text |
| *tfevents* filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/checkpoint filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.Embed_0.embedding/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.input_proj.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_0.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_0.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_0.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_0.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_1.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_1.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_1.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_1.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_10.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_10.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_10.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_10.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_11.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_11.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_11.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_11.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_2.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_2.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_2.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_3.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_3.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_3.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_3.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_4.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_4.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_4.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_4.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_5.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_5.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_5.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_5.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_6.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_6.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_6.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_6.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_7.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_7.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_7.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_7.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_8.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_8.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_8.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_8.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_9.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_9.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_9.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_9.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.continuous_encoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.continuous_inputs_projection.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.Embed_0.embedding/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_0.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_1.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_10.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_11.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_2.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_3.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_4.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_5.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_6.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_7.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_8.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.layers_9.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.spec_out_dense.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.time_emb_dense0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.decoder.time_emb_dense1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.Embed_0.embedding/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_0.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_0.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_0.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_0.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_1.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_1.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_1.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_1.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_10.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_10.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_10.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_10.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_11.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_11.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_11.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_11.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_2.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_2.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_2.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_3.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_3.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_3.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_3.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_4.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_4.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_4.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_4.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_5.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_5.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_5.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_5.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_6.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_6.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_6.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_6.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_7.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_7.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_7.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_7.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_8.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_8.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_8.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_8.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_9.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_9.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_9.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_9.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text |
| checkpoint_500000/target.token_encoder.token_embedder.embedding/0.0 filter=lfs diff=lfs merge=lfs -text |
|
|