TF-Keras
magenta-realtime / .gitattributes
chrisdonahue-goog's picture
Add files using upload-large-folder tool
e82735f verified
raw
history blame
74.7 kB
*.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
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/checkpoint filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
savedmodels/musiccoca_mv212_quant/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
savedmodels/ssv2_48k_stereo/encoder/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
savedmodels/ssv2_48k_stereo/quantizer/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
savedmodels/ssv2_48k_stereo/decoder/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
savedmodels/musiccoca_mv212f_cpu_compat/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text