Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_2.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_2.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_6.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_6.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/0.0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/1.0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_11.pre_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_11.pre_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_23.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_23.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.pre_self_attention_layer_norm.scale/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.pre_self_attention_layer_norm.scale/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.value.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.pre_self_attention_layer_norm.scale/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.pre_self_attention_layer_norm.scale/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.query.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.value.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.key.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.value.kernel/.zarray +1 -0
- checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.out.kernel/.zarray +1 -0
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (3.62 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_self_attention_layer_norm.scale.v/0
ADDED
Binary file (3.68 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (3.63 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0
ADDED
Binary file (3.76 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_2.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_2.pre_cross_attention_layer_norm.scale.v/0
ADDED
Binary file (3.81 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_6.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_6.pre_self_attention_layer_norm.scale.v/0
ADDED
Binary file (3.8 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[8,128],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[16,128],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/0.0
ADDED
Binary file (1.58 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/1.0
ADDED
Binary file (1.57 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_11.pre_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_11.pre_attention_layer_norm.scale.v/0
ADDED
Binary file (3.78 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_23.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_23.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (3.72 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (3.72 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.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.depth_decoder.depth_layers_1.self_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.depth_decoder.depth_layers_2.self_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.depth_decoder.depth_layers_3.self_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_1.self_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_12.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_15.mlp.wi_0.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024,1408],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024,2816],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024,1408],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024,2816],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.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_16.self_attention.query.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_17.encoder_decoder_attention.value.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_18.self_attention.query.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_19.pre_self_attention_layer_norm.scale/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.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_19.self_attention.value.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_2.mlp.wo.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1408,1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[2816,1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.pre_self_attention_layer_norm.scale/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.pre_self_attention_layer_norm.scale/0
ADDED
Binary file (3.81 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.pre_cross_attention_layer_norm.scale/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.pre_cross_attention_layer_norm.scale/0
ADDED
Binary file (3.71 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.pre_cross_attention_layer_norm.scale/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.pre_cross_attention_layer_norm.scale/0
ADDED
Binary file (3.72 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.query.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_5.self_attention.value.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_6.pre_cross_attention_layer_norm.scale/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.pre_cross_attention_layer_norm.scale/0
ADDED
Binary file (3.73 kB). View file
|
|
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.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_7.self_attention.value.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_8.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}
|