Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- model/model/language_model/layers/20/linear_attn/in_proj_a/kernel/1.0 +0 -0
- model/model/language_model/layers/20/linear_attn/in_proj_b/kernel/2.0 +0 -0
- model/model/language_model/layers/20/linear_attn/in_proj_b/kernel/3.0 +0 -0
- model/model/language_model/layers/20/linear_attn/norm/kernel/.zarray +1 -0
- model/model/language_model/layers/20/post_attention_layernorm/kernel/0 +0 -0
- model/model/language_model/layers/21/linear_attn/conv1d/kernel/.zarray +1 -0
- model/model/language_model/layers/21/linear_attn/in_proj_b/kernel/3.0 +0 -0
- model/model/language_model/layers/21/mlp/down_proj/kernel/.zarray +1 -0
- model/model/language_model/layers/21/mlp/gate_proj/kernel/.zarray +1 -0
- model/model/language_model/layers/25/input_layernorm/kernel/.zarray +1 -0
- model/model/language_model/layers/25/linear_attn/A_log/.zarray +1 -0
- model/model/language_model/layers/25/linear_attn/A_log/0 +0 -0
- model/model/language_model/layers/25/linear_attn/dt_bias/.zarray +1 -0
- model/model/language_model/layers/25/linear_attn/in_proj_a/kernel/.zarray +1 -0
- model/model/language_model/layers/25/linear_attn/in_proj_a/kernel/2.0 +0 -0
- model/model/language_model/layers/25/linear_attn/in_proj_b/kernel/0.0 +0 -0
- model/model/language_model/layers/25/linear_attn/in_proj_b/kernel/1.0 +0 -0
- model/model/language_model/layers/25/linear_attn/in_proj_b/kernel/2.0 +0 -0
- model/model/language_model/layers/25/linear_attn/in_proj_b/kernel/3.0 +0 -0
- model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/.zarray +1 -0
- model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/.zarray +1 -0
- model/model/language_model/layers/25/linear_attn/norm/kernel/.zarray +1 -0
- model/model/language_model/layers/25/linear_attn/norm/kernel/0 +0 -0
- model/model/language_model/layers/25/linear_attn/out_proj/kernel/.zarray +1 -0
- model/model/language_model/layers/25/mlp/gate_proj/kernel/.zarray +1 -0
- model/model/language_model/layers/25/post_attention_layernorm/kernel/.zarray +1 -0
- model/model/language_model/layers/25/post_attention_layernorm/kernel/0 +0 -0
- model/model/language_model/layers/26/input_layernorm/kernel/.zarray +1 -0
- model/model/language_model/layers/26/input_layernorm/kernel/0 +0 -0
- model/model/language_model/layers/26/linear_attn/A_log/.zarray +1 -0
- model/model/language_model/layers/26/linear_attn/A_log/0 +0 -0
- model/model/language_model/layers/26/linear_attn/conv1d/kernel/.zarray +1 -0
- model/model/language_model/layers/26/linear_attn/conv1d/kernel/0.0.0 +0 -0
- model/model/language_model/layers/26/linear_attn/dt_bias/.zarray +1 -0
- model/model/language_model/layers/26/linear_attn/dt_bias/0 +0 -0
- model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/.zarray +1 -0
- model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/0.0 +0 -0
- model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/1.0 +0 -0
- model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/2.0 +0 -0
- model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/3.0 +0 -0
- model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/.zarray +1 -0
- model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/0.0 +0 -0
- model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/1.0 +0 -0
- model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/2.0 +0 -0
- model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/3.0 +0 -0
- model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/.zarray +1 -0
- model/model/language_model/layers/26/linear_attn/in_proj_z/kernel/.zarray +1 -0
- model/model/language_model/layers/26/linear_attn/norm/kernel/.zarray +1 -0
- model/model/language_model/layers/26/linear_attn/norm/kernel/0 +0 -0
- model/model/language_model/layers/26/linear_attn/out_proj/kernel/.zarray +1 -0
model/model/language_model/layers/20/linear_attn/in_proj_a/kernel/1.0
ADDED
|
Binary file (32.1 kB). View file
|
|
|
model/model/language_model/layers/20/linear_attn/in_proj_b/kernel/2.0
ADDED
|
Binary file (32.2 kB). View file
|
|
|
model/model/language_model/layers/20/linear_attn/in_proj_b/kernel/3.0
ADDED
|
Binary file (32.2 kB). View file
|
|
|
model/model/language_model/layers/20/linear_attn/norm/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[128],"zarr_format":2}
|
model/model/language_model/layers/20/post_attention_layernorm/kernel/0
ADDED
|
Binary file (3.59 kB). View file
|
|
|
model/model/language_model/layers/21/linear_attn/conv1d/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4,1,8192],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4,1,8192],"zarr_format":2}
|
model/model/language_model/layers/21/linear_attn/in_proj_b/kernel/3.0
ADDED
|
Binary file (32.1 kB). View file
|
|
|
model/model/language_model/layers/21/mlp/down_proj/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[9216,640],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[9216,2560],"zarr_format":2}
|
model/model/language_model/layers/21/mlp/gate_proj/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[640,9216],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560,9216],"zarr_format":2}
|
model/model/language_model/layers/25/input_layernorm/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[2560],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560],"zarr_format":2}
|
model/model/language_model/layers/25/linear_attn/A_log/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2}
|
model/model/language_model/layers/25/linear_attn/A_log/0
ADDED
|
Binary file (73 Bytes). View file
|
|
|
model/model/language_model/layers/25/linear_attn/dt_bias/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2}
|
model/model/language_model/layers/25/linear_attn/in_proj_a/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[640,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560,32],"zarr_format":2}
|
model/model/language_model/layers/25/linear_attn/in_proj_a/kernel/2.0
ADDED
|
Binary file (32 kB). View file
|
|
|
model/model/language_model/layers/25/linear_attn/in_proj_b/kernel/0.0
ADDED
|
Binary file (32.1 kB). View file
|
|
|
model/model/language_model/layers/25/linear_attn/in_proj_b/kernel/1.0
ADDED
|
Binary file (32 kB). View file
|
|
|
model/model/language_model/layers/25/linear_attn/in_proj_b/kernel/2.0
ADDED
|
Binary file (32.1 kB). View file
|
|
|
model/model/language_model/layers/25/linear_attn/in_proj_b/kernel/3.0
ADDED
|
Binary file (32.1 kB). View file
|
|
|
model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[640,8192],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560,8192],"zarr_format":2}
|
model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[640,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560,4096],"zarr_format":2}
|
model/model/language_model/layers/25/linear_attn/norm/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[128],"zarr_format":2}
|
model/model/language_model/layers/25/linear_attn/norm/kernel/0
ADDED
|
Binary file (180 Bytes). View file
|
|
|
model/model/language_model/layers/25/linear_attn/out_proj/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,640],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2560],"zarr_format":2}
|
model/model/language_model/layers/25/mlp/gate_proj/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[640,9216],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560,9216],"zarr_format":2}
|
model/model/language_model/layers/25/post_attention_layernorm/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[2560],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560],"zarr_format":2}
|
model/model/language_model/layers/25/post_attention_layernorm/kernel/0
ADDED
|
Binary file (3.02 kB). View file
|
|
|
model/model/language_model/layers/26/input_layernorm/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[2560],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560],"zarr_format":2}
|
model/model/language_model/layers/26/input_layernorm/kernel/0
ADDED
|
Binary file (2.77 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/A_log/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2}
|
model/model/language_model/layers/26/linear_attn/A_log/0
ADDED
|
Binary file (73 Bytes). View file
|
|
|
model/model/language_model/layers/26/linear_attn/conv1d/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4,1,8192],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4,1,8192],"zarr_format":2}
|
model/model/language_model/layers/26/linear_attn/conv1d/kernel/0.0.0
ADDED
|
Binary file (54.2 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/dt_bias/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2}
|
model/model/language_model/layers/26/linear_attn/dt_bias/0
ADDED
|
Binary file (73 Bytes). View file
|
|
|
model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[640,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560,32],"zarr_format":2}
|
model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/0.0
ADDED
|
Binary file (32.2 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/1.0
ADDED
|
Binary file (31.9 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/2.0
ADDED
|
Binary file (31.8 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/in_proj_a/kernel/3.0
ADDED
|
Binary file (31.9 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[640,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560,32],"zarr_format":2}
|
model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/0.0
ADDED
|
Binary file (32.1 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/1.0
ADDED
|
Binary file (32.1 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/2.0
ADDED
|
Binary file (32.1 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/in_proj_b/kernel/3.0
ADDED
|
Binary file (32.1 kB). View file
|
|
|
model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[640,8192],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560,8192],"zarr_format":2}
|
model/model/language_model/layers/26/linear_attn/in_proj_z/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[640,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2560,4096],"zarr_format":2}
|
model/model/language_model/layers/26/linear_attn/norm/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[128],"zarr_format":2}
|
model/model/language_model/layers/26/linear_attn/norm/kernel/0
ADDED
|
Binary file (179 Bytes). View file
|
|
|
model/model/language_model/layers/26/linear_attn/out_proj/kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,640],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2560],"zarr_format":2}
|