Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +116 -0
- checkpoints/llm_large_x3047_c1860k/checkpoint +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.key.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.key.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/1.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/1.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/1.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/1.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.out.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.value.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.value.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.query.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.query.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_0.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_0.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.pre_self_attention_layer_norm.scale/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.out.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.out.kernel/1.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_1.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_1.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.value.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.value.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.query.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/1.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.key.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_0.kernel/0.0 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_0.kernel/0.1 +3 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wo.kernel/0.0 +3 -0
.gitattributes
CHANGED
|
@@ -35,3 +35,119 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
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
|
| 37 |
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
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
|
| 37 |
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
|
| 38 |
+
checkpoints/llm_large_x3047_c1860k/checkpoint filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
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
|
| 48 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
| 62 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
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
|
| 64 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
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
|
| 66 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
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
|
| 68 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
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
|
| 72 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
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
|
| 76 |
+
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
|
| 77 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
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
|
| 79 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
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
|
| 81 |
+
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
|
| 82 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
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
|
| 85 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
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
|
| 87 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
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
|
| 90 |
+
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
|
| 91 |
+
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
|
| 92 |
+
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
|
| 93 |
+
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
|
| 94 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
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
|
| 101 |
+
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
|
| 102 |
+
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
|
| 103 |
+
savedmodels/musiccoca_mv212_quant/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
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
|
| 105 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
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
|
| 107 |
+
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
|
| 108 |
+
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
|
| 109 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
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
|
| 114 |
+
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
|
| 115 |
+
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
|
| 116 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
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
|
| 120 |
+
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
|
| 121 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
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
|
| 124 |
+
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
|
| 125 |
+
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
|
| 126 |
+
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
|
| 127 |
+
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
|
| 128 |
+
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
|
| 129 |
+
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
|
| 130 |
+
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
|
| 131 |
+
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
|
| 132 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 133 |
+
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
|
| 134 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 135 |
+
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
|
| 136 |
+
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
|
| 137 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
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
|
| 140 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
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
|
| 142 |
+
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
|
| 143 |
+
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
|
| 144 |
+
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
|
| 145 |
+
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
|
| 146 |
+
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
|
| 147 |
+
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
|
| 148 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 149 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 150 |
+
savedmodels/ssv2_48k_stereo/encoder/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
|
| 151 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 152 |
+
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
|
| 153 |
+
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/checkpoint
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ccf9bcd4a85893c0b308414075688751438ddcb7661b22a5a6a59572c9675f1
|
| 3 |
+
size 4881325
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.key.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d350f41d2d6415110d4ab4e0f5ab5998e8a1402de19f27cadde2a915b8ec0359
|
| 3 |
+
size 1955236
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.key.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e9f707608851e259b37f3209408a8aea4544f57a6b9a31eac014d773be26303
|
| 3 |
+
size 1956088
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d918285bc089b4f26e97ba85dab15840fd20a36d11aa9cdff477be19d35e1bd
|
| 3 |
+
size 1955877
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12a30becb4c48b67166ddbc5a4057b80a5ab9b45f95545a5d4e27207625f5a80
|
| 3 |
+
size 1956366
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f9eca473cc699ac8a8f79b6ca47cefdd4c815085f492e8ba8b968b254ee8088
|
| 3 |
+
size 1951045
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcaad1b419d7109a260c29e2b67461899162854be8113ed2f5f1c70941e5a9fa
|
| 3 |
+
size 1950729
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:861d5ec0ce4ca61d0d131bd9c123418e1f8af4b937bf72ca2e54ece836cf70c5
|
| 3 |
+
size 1950618
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb57020bce75a6e6a86b2b73aa0ab8d2911d71227b60642148b5cb29bc3a2667
|
| 3 |
+
size 1950784
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01e8c5a9643890cc13cd32fe9843df0a280b2c72c2dff579ff7b9115617481f9
|
| 3 |
+
size 1951457
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:557e0872ca4fec0a15c5628918311aa98f6d8b39bf6b08f71c760df8687d2957
|
| 3 |
+
size 1950777
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9238d2088e32a50575f0da3aeefa96f968c53a6e5abb7274f642aa417c734c84
|
| 3 |
+
size 1960458
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fd5d3f3298819527607733d75cd7d08cd40b1c0fe8035e8deabdb3511cd6d52
|
| 3 |
+
size 1962493
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.out.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c17f4c588bc9f29140d8f3d79eba103f15ac9c3c4fc1bbe71c7a7a9f6072fe6
|
| 3 |
+
size 1953495
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.value.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e77b1e526c822c3236cc2ed2a6c5360e5b23e83124d846bdfcd2d12fc261999c
|
| 3 |
+
size 1951431
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.value.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:300492bf20392d3dc791891fd20297d5a972831ba2699bdbd633fc59807a792c
|
| 3 |
+
size 1951517
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.query.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85f09ce805ea3d11bf4668acdd9e24259ae34233d633204e779178eb7ac076e6
|
| 3 |
+
size 1950477
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.query.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d98b259c299f90467e065d70b341369f27cbaf479f430f311ae2cfb3f52bbd1
|
| 3 |
+
size 1950275
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:348c97029507c294f1bedc4fa8cddec0bcb733968c4e9b5ce9a7f76f8999448c
|
| 3 |
+
size 1955734
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5251f597b4ea566bd6cea72fd29895b25ab5daf68d76f8ca2b5a3ca673ba817e
|
| 3 |
+
size 1955863
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.out.kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024,1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_0.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e37926c4b7a15ad8e553351a55c56e9139287809d91f8d1be86a6e19dd4fde9
|
| 3 |
+
size 5378440
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_0.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b04b8d9dd1c1eccd1e68e5c653759eee86cda21010ef21dd256c1c250bf0b83
|
| 3 |
+
size 5377428
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0c07f526a555bd6960f6d73a4be940383462852f3e25427c73ae2ec5024d40a
|
| 3 |
+
size 5377684
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db988eccb0c778020f1f646739cdd58da2129541204b80212ac5d461e899bb2b
|
| 3 |
+
size 5377838
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df8c9508a416565bf2907b126836ddd6e9416500ef892df8ed9807708bee733d
|
| 3 |
+
size 5371774
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:707d62767c0fd7b7143b394fc36c5808e724e2bc182550cf2ab991c87281de7b
|
| 3 |
+
size 5372306
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f643ff29d20b50dad45cbf3695d88e440ae2a4faac3c79689a4b52bbafbb4785
|
| 3 |
+
size 1951545
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff71ec6f335fbee1e569788fc837882def7faee66658568c0a881f50c1382f06
|
| 3 |
+
size 1952336
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.pre_self_attention_layer_norm.scale/0
ADDED
|
Binary file (3.67 kB). View file
|
|
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.out.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abafd7d53f7ac4269d9cb88ac6f0471faedc958e575a012d8eb2b7ac999182a6
|
| 3 |
+
size 1954521
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.out.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1e074fe475697f10360fd1d3040133e0b3493bbb4b2e0e23da6f29cec0f6884
|
| 3 |
+
size 1956426
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afec224d0d76a7a754977241747e902afbbf0d3b6bd8c67e5cfad353a79d39a7
|
| 3 |
+
size 1953187
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5866d7ac3c95dddb26c8a85577ee1670a658189115367b4e08d5c1087996a693
|
| 3 |
+
size 1951844
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9f169d8200ff817e48cc2fcd68703139c56c959914d950393f2545e0c2f923f
|
| 3 |
+
size 1951985
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f96871b0a57ba85ed6add0aae358392be816995c33e93583a9c0d7110b5997ec
|
| 3 |
+
size 1953446
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_1.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da298ec9dab5e71aa117f30ccccbaab63927402c51c6add002c18075f9185a1
|
| 3 |
+
size 5371675
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_1.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:191ed0e81519812be808abe30d62cc295a2a81326bcde5c5edf32a338b29c8dc
|
| 3 |
+
size 5371742
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69a1f38880c65c677a71e7cdd9b3a8a9931a1bea014d4bbe26f932db984d1915
|
| 3 |
+
size 1952632
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3a0a4c6402b212914992802e3a0370a296a5664b3101a45a9ad2bfa14372241
|
| 3 |
+
size 1951577
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.value.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf4e7edb1e922aa774563f9d20319b55eed01a747edd62720431b6e296cdccda
|
| 3 |
+
size 1954842
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.value.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89fc251b4d79bef5d6898bfe4e9fe4b1c3952ce31e2bb256bc280c5891944d39
|
| 3 |
+
size 1954863
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.query.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c77365e783fdfc5adbb2f296c6f154f1a5492cddcfbaf90f81633c4cf6588860
|
| 3 |
+
size 1954000
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ef701059accc8fe7622e83acfef390a0ff123c712477e0ea14a0cada64b5526
|
| 3 |
+
size 5393798
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:334b19305d3092dde386fd3e25ddd85e4ff2ed334628eafbdc8ad789e06d0356
|
| 3 |
+
size 5393434
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.key.kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[1024,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024,1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_0.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f7018bfda6d30aa847c74640e99c4a19a58d920427225d619670f41081dcce0
|
| 3 |
+
size 5381925
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_0.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f06e063b380e9fd254dc65592b7a5c2b69893fee80b3dfae9053423915e725c
|
| 3 |
+
size 5382407
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wo.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26387651bb40064a99a92716702a5300dbe43e463a33a1286236e80e439f4499
|
| 3 |
+
size 5390825
|