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 +496 -0
- model/model/language_model/embed_tokens/embedding/0.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0 +3 -0
- model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/0/mlp/down_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/0/mlp/down_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/0/mlp/down_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/0/mlp/down_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/0/mlp/up_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/0/mlp/up_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/0/mlp/up_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/0/mlp/up_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/2.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0 +3 -0
- model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/1/mlp/down_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/1/mlp/down_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/1/mlp/down_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/1/mlp/down_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/1/mlp/gate_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/1/mlp/gate_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/1/mlp/gate_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/1/mlp/up_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/1/mlp/up_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/1/mlp/up_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/1/mlp/up_proj/kernel/3.0 +3 -0
.gitattributes
CHANGED
|
@@ -56,3 +56,499 @@ model/model/visual/blocks/8/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=
|
|
| 56 |
model/model/visual/pos_embed/embedding/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 57 |
model/model/visual/blocks/7/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 58 |
model/model/visual/pos_embed/embedding/2.0 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
model/model/visual/pos_embed/embedding/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 57 |
model/model/visual/blocks/7/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 58 |
model/model/visual/pos_embed/embedding/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
model/model/visual/blocks/7/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
model/model/visual/blocks/8/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
model/model/visual/blocks/7/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
model/model/visual/blocks/8/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
model/model/visual/blocks/9/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
model/model/visual/blocks/8/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
model/model/visual/blocks/8/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
model/model/visual/blocks/8/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
model/model/visual/blocks/8/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
model/model/visual/blocks/8/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
model/model/visual/blocks/7/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
model/model/visual/blocks/9/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
model/model/visual/blocks/9/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
model/model/visual/pos_embed/embedding/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
model/model/visual/pos_embed/embedding/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
model/model/visual/merger/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
model/model/visual/merger/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
model/model/visual/merger/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
model/model/visual/merger/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
model/model/visual/merger/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
model/model/visual/merger/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
model/model/visual/merger/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
model/model/visual/merger/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
model/model/language_model/embed_tokens/embedding/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
model/model/language_model/layers/11/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
model/model/language_model/layers/11/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
model/model/language_model/layers/11/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
model/model/language_model/layers/11/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
model/model/language_model/layers/11/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
model/model/language_model/layers/11/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
model/model/language_model/layers/11/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
model/model/language_model/layers/11/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
model/model/language_model/layers/11/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
model/model/language_model/layers/11/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
model/model/language_model/layers/11/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 101 |
+
model/model/language_model/layers/11/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 102 |
+
model/model/language_model/layers/11/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 103 |
+
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
model/model/language_model/layers/14/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 105 |
+
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
model/model/language_model/layers/15/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 107 |
+
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 108 |
+
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 109 |
+
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
model/model/language_model/layers/15/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
model/model/language_model/layers/15/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
model/model/language_model/layers/15/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 114 |
+
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
model/model/language_model/layers/15/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 116 |
+
model/model/language_model/layers/15/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
model/model/language_model/layers/15/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 120 |
+
model/model/language_model/layers/14/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 121 |
+
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
model/model/language_model/layers/15/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 124 |
+
model/model/language_model/layers/14/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 125 |
+
model/model/language_model/layers/14/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 126 |
+
model/model/language_model/layers/14/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 127 |
+
model/model/language_model/layers/14/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 128 |
+
model/model/language_model/layers/15/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 129 |
+
model/model/language_model/layers/14/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 130 |
+
model/model/language_model/layers/14/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 131 |
+
model/model/language_model/layers/14/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 132 |
+
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 133 |
+
model/model/language_model/layers/14/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 134 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 135 |
+
model/model/language_model/layers/0/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 136 |
+
model/model/language_model/layers/0/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 137 |
+
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 140 |
+
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 142 |
+
model/model/language_model/layers/0/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 143 |
+
model/model/language_model/layers/11/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 144 |
+
model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 145 |
+
model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 146 |
+
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 147 |
+
model/model/language_model/layers/0/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 148 |
+
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 149 |
+
model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 150 |
+
model/model/language_model/layers/11/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 151 |
+
model/model/language_model/layers/0/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 152 |
+
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 153 |
+
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 154 |
+
model/model/language_model/layers/0/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 155 |
+
model/model/language_model/layers/11/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 156 |
+
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 157 |
+
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 158 |
+
model/model/language_model/layers/0/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 159 |
+
model/model/language_model/layers/11/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 160 |
+
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 161 |
+
model/model/language_model/layers/11/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 162 |
+
model/model/language_model/layers/11/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 163 |
+
model/model/language_model/layers/0/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 164 |
+
model/model/language_model/layers/11/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 165 |
+
model/model/language_model/layers/11/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 166 |
+
model/model/language_model/layers/11/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 167 |
+
model/model/language_model/layers/11/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 168 |
+
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 169 |
+
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 170 |
+
model/model/language_model/layers/11/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 171 |
+
model/model/language_model/layers/21/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 172 |
+
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 173 |
+
model/model/language_model/layers/23/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 174 |
+
model/model/language_model/layers/23/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 175 |
+
model/model/language_model/layers/21/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 176 |
+
model/model/language_model/layers/23/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 177 |
+
model/model/language_model/layers/23/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 178 |
+
model/model/language_model/layers/23/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 179 |
+
model/model/language_model/layers/21/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 180 |
+
model/model/language_model/layers/21/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 181 |
+
model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 182 |
+
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 183 |
+
model/model/language_model/layers/23/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 184 |
+
model/model/language_model/layers/23/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 185 |
+
model/model/language_model/layers/21/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 186 |
+
model/model/language_model/layers/21/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 187 |
+
model/model/language_model/layers/23/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 188 |
+
model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 189 |
+
model/model/language_model/layers/25/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 190 |
+
model/model/language_model/layers/23/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 191 |
+
model/model/language_model/layers/25/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 192 |
+
model/model/language_model/layers/23/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 193 |
+
model/model/language_model/layers/21/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 194 |
+
model/model/language_model/layers/25/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 195 |
+
model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 196 |
+
model/model/language_model/layers/25/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 197 |
+
model/model/language_model/layers/23/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 198 |
+
model/model/language_model/layers/25/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 199 |
+
model/model/language_model/layers/23/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 200 |
+
model/model/language_model/layers/25/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 201 |
+
model/model/language_model/layers/25/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 202 |
+
model/model/language_model/layers/23/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 203 |
+
model/model/language_model/layers/25/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 204 |
+
model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 205 |
+
model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 206 |
+
model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 207 |
+
model/model/language_model/layers/25/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 208 |
+
model/model/language_model/layers/25/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 209 |
+
model/model/language_model/layers/25/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 210 |
+
model/model/language_model/layers/25/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 211 |
+
model/model/language_model/layers/26/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 212 |
+
model/model/language_model/layers/25/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 213 |
+
model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 214 |
+
model/model/language_model/layers/27/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 215 |
+
model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 216 |
+
model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 217 |
+
model/model/language_model/layers/26/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 218 |
+
model/model/language_model/layers/23/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 219 |
+
model/model/language_model/layers/27/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 220 |
+
model/model/language_model/layers/25/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 221 |
+
model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 222 |
+
model/model/language_model/layers/26/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 223 |
+
model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 224 |
+
model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 225 |
+
model/model/language_model/layers/14/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 226 |
+
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 227 |
+
model/model/language_model/layers/15/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 228 |
+
model/model/language_model/layers/15/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 229 |
+
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 230 |
+
model/model/language_model/layers/15/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 231 |
+
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 232 |
+
model/model/language_model/layers/15/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 233 |
+
model/model/language_model/layers/1/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 234 |
+
model/model/language_model/layers/15/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 235 |
+
model/model/language_model/layers/15/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 236 |
+
model/model/language_model/layers/15/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 237 |
+
model/model/language_model/layers/15/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 238 |
+
model/model/language_model/layers/14/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 239 |
+
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 240 |
+
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 241 |
+
model/model/language_model/layers/15/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 242 |
+
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 243 |
+
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 244 |
+
model/model/language_model/layers/15/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 245 |
+
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 246 |
+
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 247 |
+
model/model/language_model/layers/15/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 248 |
+
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 249 |
+
model/model/language_model/layers/1/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 250 |
+
model/model/language_model/layers/15/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 251 |
+
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 252 |
+
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 253 |
+
model/model/language_model/layers/1/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 254 |
+
model/model/language_model/layers/1/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 255 |
+
model/model/language_model/layers/15/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 256 |
+
model/model/language_model/layers/15/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 257 |
+
model/model/language_model/layers/1/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 258 |
+
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 259 |
+
model/model/language_model/layers/1/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 260 |
+
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 261 |
+
model/model/language_model/layers/15/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 262 |
+
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 263 |
+
model/model/language_model/layers/1/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 264 |
+
model/model/language_model/layers/10/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 265 |
+
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 266 |
+
model/model/language_model/layers/1/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 267 |
+
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 268 |
+
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 269 |
+
model/model/language_model/layers/1/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 270 |
+
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 271 |
+
model/model/language_model/layers/17/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 272 |
+
model/model/language_model/layers/16/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 273 |
+
model/model/language_model/layers/16/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 274 |
+
model/model/language_model/layers/17/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 275 |
+
model/model/language_model/layers/16/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 276 |
+
model/model/language_model/layers/16/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 277 |
+
model/model/language_model/layers/17/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 278 |
+
model/model/language_model/layers/17/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 279 |
+
model/model/language_model/layers/17/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 280 |
+
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 281 |
+
model/model/language_model/layers/17/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 282 |
+
model/model/language_model/layers/17/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 283 |
+
model/model/language_model/layers/17/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 284 |
+
model/model/language_model/layers/19/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 285 |
+
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 286 |
+
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 287 |
+
model/model/language_model/layers/18/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 288 |
+
model/model/language_model/layers/18/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 289 |
+
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 290 |
+
model/model/language_model/layers/17/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 291 |
+
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 292 |
+
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 293 |
+
model/model/language_model/layers/17/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 294 |
+
model/model/language_model/layers/17/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 295 |
+
model/model/language_model/layers/17/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 296 |
+
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 297 |
+
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 298 |
+
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 299 |
+
model/model/language_model/layers/19/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 300 |
+
model/model/language_model/layers/19/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 301 |
+
model/model/language_model/layers/19/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 302 |
+
model/model/language_model/layers/19/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 303 |
+
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 304 |
+
model/model/language_model/layers/19/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 305 |
+
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 306 |
+
model/model/language_model/layers/19/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 307 |
+
model/model/language_model/layers/19/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 308 |
+
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 309 |
+
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 310 |
+
model/model/language_model/layers/17/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 311 |
+
model/model/language_model/layers/18/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 312 |
+
model/model/language_model/layers/18/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 313 |
+
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 314 |
+
model/model/language_model/layers/18/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 315 |
+
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 316 |
+
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 317 |
+
model/model/language_model/layers/19/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 318 |
+
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 319 |
+
model/model/language_model/layers/18/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 320 |
+
model/model/language_model/layers/28/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 321 |
+
model/model/language_model/layers/3/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 322 |
+
model/model/language_model/layers/3/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 323 |
+
model/model/language_model/layers/3/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 324 |
+
model/model/language_model/layers/3/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 325 |
+
model/model/language_model/layers/3/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 326 |
+
model/model/language_model/layers/28/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 327 |
+
model/model/language_model/layers/28/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 328 |
+
model/model/language_model/layers/28/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 329 |
+
model/model/language_model/layers/27/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 330 |
+
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 331 |
+
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 332 |
+
model/model/language_model/layers/3/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 333 |
+
model/model/language_model/layers/3/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 334 |
+
model/model/language_model/layers/27/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 335 |
+
model/model/language_model/layers/28/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 336 |
+
model/model/language_model/layers/28/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 337 |
+
model/model/language_model/layers/28/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 338 |
+
model/model/language_model/layers/3/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 339 |
+
model/model/language_model/layers/28/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 340 |
+
model/model/language_model/layers/27/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 341 |
+
model/model/language_model/layers/3/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 342 |
+
model/model/language_model/layers/3/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 343 |
+
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 344 |
+
model/model/language_model/layers/28/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 345 |
+
model/model/language_model/layers/28/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 346 |
+
model/model/language_model/layers/3/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 347 |
+
model/model/language_model/layers/28/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 348 |
+
model/model/language_model/layers/3/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 349 |
+
model/model/language_model/layers/28/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 350 |
+
model/model/language_model/layers/28/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 351 |
+
model/model/language_model/layers/3/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 352 |
+
model/model/language_model/layers/28/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 353 |
+
model/model/language_model/layers/3/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 354 |
+
model/model/language_model/layers/28/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 355 |
+
model/model/language_model/layers/3/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 356 |
+
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 357 |
+
model/model/language_model/layers/30/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 358 |
+
model/model/language_model/layers/30/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 359 |
+
model/model/language_model/layers/30/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 360 |
+
model/model/language_model/layers/30/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 361 |
+
model/model/language_model/layers/30/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 362 |
+
model/model/language_model/layers/31/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 363 |
+
model/model/language_model/layers/31/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 364 |
+
model/model/language_model/layers/3/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 365 |
+
model/model/language_model/layers/30/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 366 |
+
model/model/language_model/layers/3/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 367 |
+
model/model/language_model/layers/3/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 368 |
+
model/model/language_model/layers/30/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 369 |
+
model/model/language_model/layers/31/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 370 |
+
model/model/language_model/layers/3/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 371 |
+
model/model/language_model/layers/30/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 372 |
+
model/model/language_model/layers/30/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 373 |
+
model/model/language_model/layers/3/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 374 |
+
model/model/language_model/layers/31/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 375 |
+
model/model/language_model/layers/3/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 376 |
+
model/model/language_model/layers/19/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 377 |
+
model/model/language_model/layers/18/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 378 |
+
model/model/language_model/layers/19/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 379 |
+
model/model/language_model/layers/19/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 380 |
+
model/model/language_model/layers/19/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 381 |
+
model/model/language_model/layers/18/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 382 |
+
model/model/language_model/layers/18/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 383 |
+
model/model/language_model/layers/2/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 384 |
+
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 385 |
+
model/model/language_model/layers/18/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 386 |
+
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 387 |
+
model/model/language_model/layers/18/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 388 |
+
model/model/language_model/layers/19/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 389 |
+
model/model/language_model/layers/2/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 390 |
+
model/model/language_model/layers/18/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 391 |
+
model/model/language_model/layers/19/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 392 |
+
model/model/language_model/layers/2/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 393 |
+
model/model/language_model/layers/19/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 394 |
+
model/model/language_model/layers/2/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 395 |
+
model/model/language_model/layers/19/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 396 |
+
model/model/language_model/layers/19/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 397 |
+
model/model/language_model/layers/2/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 398 |
+
model/model/language_model/layers/2/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 399 |
+
model/model/language_model/layers/2/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 400 |
+
model/model/language_model/layers/19/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 401 |
+
model/model/language_model/layers/19/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 402 |
+
model/model/language_model/layers/19/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 403 |
+
model/model/language_model/layers/2/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 404 |
+
model/model/language_model/layers/2/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 405 |
+
model/model/language_model/layers/20/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 406 |
+
model/model/language_model/layers/2/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 407 |
+
model/model/language_model/layers/2/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 408 |
+
model/model/language_model/layers/19/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 409 |
+
model/model/language_model/layers/2/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 410 |
+
model/model/language_model/layers/2/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 411 |
+
model/model/language_model/layers/19/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 412 |
+
model/model/language_model/layers/2/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 413 |
+
model/model/language_model/layers/2/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 414 |
+
model/model/language_model/layers/2/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 415 |
+
model/model/language_model/layers/2/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 416 |
+
model/model/language_model/layers/2/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 417 |
+
model/model/language_model/layers/2/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 418 |
+
model/model/language_model/layers/19/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 419 |
+
model/model/language_model/layers/2/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 420 |
+
model/model/language_model/layers/2/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 421 |
+
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 422 |
+
model/model/language_model/layers/20/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 423 |
+
model/model/language_model/layers/2/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 424 |
+
model/model/language_model/layers/20/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 425 |
+
model/model/language_model/layers/20/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 426 |
+
model/model/language_model/layers/20/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 427 |
+
model/model/language_model/layers/2/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 428 |
+
model/model/visual/blocks/25/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 429 |
+
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 430 |
+
model/model/visual/blocks/24/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 431 |
+
model/model/visual/blocks/23/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 432 |
+
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 433 |
+
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 434 |
+
model/model/visual/blocks/23/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 435 |
+
model/model/visual/blocks/25/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 436 |
+
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 437 |
+
model/model/visual/blocks/23/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 438 |
+
model/model/visual/blocks/23/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 439 |
+
model/model/visual/blocks/23/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 440 |
+
model/model/visual/blocks/24/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 441 |
+
model/model/visual/blocks/24/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 442 |
+
model/model/visual/blocks/24/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 443 |
+
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 444 |
+
model/model/visual/blocks/24/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 445 |
+
model/model/visual/blocks/24/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 446 |
+
model/model/visual/blocks/24/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 447 |
+
model/model/visual/blocks/25/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 448 |
+
model/model/visual/blocks/24/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 449 |
+
model/model/visual/blocks/24/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 450 |
+
model/model/visual/blocks/24/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 451 |
+
model/model/visual/blocks/24/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 452 |
+
model/model/visual/blocks/25/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 453 |
+
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 454 |
+
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 455 |
+
model/model/visual/blocks/25/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 456 |
+
model/model/visual/blocks/25/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 457 |
+
model/model/visual/blocks/25/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 458 |
+
model/model/visual/blocks/26/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 459 |
+
model/model/visual/blocks/26/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 460 |
+
model/model/visual/blocks/26/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 461 |
+
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 462 |
+
model/model/visual/blocks/25/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 463 |
+
model/model/visual/blocks/3/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 464 |
+
model/model/visual/blocks/26/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 465 |
+
model/model/visual/blocks/26/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 466 |
+
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 467 |
+
model/model/visual/blocks/25/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 468 |
+
model/model/visual/blocks/26/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 469 |
+
model/model/visual/blocks/26/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 470 |
+
model/model/visual/blocks/26/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 471 |
+
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 472 |
+
model/model/language_model/layers/20/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 473 |
+
model/model/language_model/layers/20/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 474 |
+
model/model/language_model/layers/20/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 475 |
+
model/model/language_model/layers/20/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 476 |
+
model/model/language_model/layers/20/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 477 |
+
model/model/language_model/layers/20/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 478 |
+
model/model/language_model/layers/2/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 479 |
+
model/model/language_model/layers/20/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 480 |
+
model/model/language_model/layers/20/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 481 |
+
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 482 |
+
model/model/language_model/layers/20/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 483 |
+
model/model/language_model/layers/20/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 484 |
+
model/model/language_model/layers/20/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 485 |
+
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 486 |
+
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 487 |
+
model/model/language_model/layers/23/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 488 |
+
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 489 |
+
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 490 |
+
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 491 |
+
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 492 |
+
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 493 |
+
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 494 |
+
model/model/language_model/layers/23/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 495 |
+
model/model/language_model/layers/20/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 496 |
+
model/model/language_model/layers/23/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 497 |
+
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 498 |
+
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 499 |
+
model/model/language_model/layers/21/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 500 |
+
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 501 |
+
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 502 |
+
model/model/language_model/layers/23/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 503 |
+
model/model/language_model/layers/21/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 504 |
+
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 505 |
+
model/model/language_model/layers/23/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 506 |
+
model/model/language_model/layers/21/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 507 |
+
model/model/language_model/layers/20/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 508 |
+
model/model/language_model/layers/20/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 509 |
+
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 510 |
+
model/model/language_model/layers/23/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 511 |
+
model/model/language_model/layers/23/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 512 |
+
model/model/language_model/layers/20/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 513 |
+
model/model/language_model/layers/21/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 514 |
+
model/model/language_model/layers/23/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 515 |
+
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 516 |
+
model/model/language_model/layers/23/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 517 |
+
model/model/language_model/layers/23/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 518 |
+
model/model/language_model/layers/21/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 519 |
+
model/model/language_model/layers/1/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 520 |
+
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 521 |
+
model/model/language_model/layers/10/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 522 |
+
model/model/language_model/layers/1/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 523 |
+
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 524 |
+
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 525 |
+
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 526 |
+
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 527 |
+
model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 528 |
+
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 529 |
+
model/model/language_model/layers/10/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 530 |
+
model/model/language_model/layers/10/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 531 |
+
model/model/language_model/layers/10/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 532 |
+
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 533 |
+
model/model/language_model/layers/10/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 534 |
+
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 535 |
+
model/model/language_model/layers/10/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 536 |
+
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 537 |
+
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 538 |
+
model/model/language_model/layers/10/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 539 |
+
model/model/language_model/layers/10/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 540 |
+
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 541 |
+
model/model/language_model/layers/12/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 542 |
+
model/model/language_model/layers/10/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 543 |
+
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 544 |
+
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 545 |
+
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 546 |
+
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 547 |
+
model/model/language_model/layers/10/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 548 |
+
model/model/language_model/layers/12/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 549 |
+
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 550 |
+
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 551 |
+
model/model/language_model/layers/10/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 552 |
+
model/model/language_model/layers/12/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 553 |
+
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 554 |
+
model/model/language_model/layers/12/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
model/model/language_model/embed_tokens/embedding/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f5ac548a6b160d0321118d1789c2d7a5cc42957f2ca5452b3add91f1b250a6a
|
| 3 |
+
size 395077801
|
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6859ae0e4d48c668608cffd3e0545183967d6ab6f3923bfa6f7e7421f1f079c7
|
| 3 |
+
size 13080439
|
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3009d5f21f3e717690814609bd91fadcd44e651171401f335021ac334f6cab2
|
| 3 |
+
size 13080660
|
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:868f31e2fb15aba44fe0019f904d49c90cee48097ef780869f13dd3f252572a9
|
| 3 |
+
size 13079925
|
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88e299992016f0aaca798f1aa36f83087a652518056f53f391da08277030d5d4
|
| 3 |
+
size 13081069
|
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ffa673e0b8b1b91eddf787e7546cafac1a5b1661c65c307420e8d02d76b4f2a
|
| 3 |
+
size 6533973
|
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f057593fa2c831072efa22dd2c6f11a713caa05b2e7d607f6ee23d9a9b369f9
|
| 3 |
+
size 6534105
|
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60d7806c9e88a5dd747aa8fa78c9aa935826b20c42c4070f95bff4117994b78
|
| 3 |
+
size 6532453
|
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fa7a74b48c31289419d5118f48032d088b1920ca8133ac458f2993e4628832f
|
| 3 |
+
size 6533990
|
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3611401fb269e1863c6208f3d168de1fd138ebc2d17d90122dcb993d77a58c84
|
| 3 |
+
size 6550045
|
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f29de5549b8ec5ce07f0412da96fb17c29f0a14633cfe38edcc920a9b23edd4a
|
| 3 |
+
size 6549182
|
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c944d4fc334710f75f0646573cd0ee28417de249e8c5544d91291d92ed6ee19
|
| 3 |
+
size 6546985
|
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:630b448d4ed47d1f44bc9faf215fea64c6945056f2cfcceff5757afa1efbeff6
|
| 3 |
+
size 6550407
|
model/model/language_model/layers/0/mlp/down_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bf140dbb490a467762ece29739d219d63447e70a95c2202b143ea00c7251221
|
| 3 |
+
size 19587961
|
model/model/language_model/layers/0/mlp/down_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a69246ef390c63ffc58f4864a2bccd9ef6212386efb28e41b6dd75c85c3bd27c
|
| 3 |
+
size 19584546
|
model/model/language_model/layers/0/mlp/down_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:039b91319b98afbd3189e7edb33a0f0bb9807847beb0d80117147575fed96ad2
|
| 3 |
+
size 19585099
|
model/model/language_model/layers/0/mlp/down_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecba5078ac5380e3335fb40fd9c8ae9d4b596ef667e7993bae7c11f96d0bbce4
|
| 3 |
+
size 19588311
|
model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c17b374ea2dc55e42f85194dc7210c93a52ee5c0748e1d2cb75eeb0494308285
|
| 3 |
+
size 19577672
|
model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf5fa382ffc59cb6724c26e007b6ac7d33eb11a80ae2ad95419c4cf3cbf1191a
|
| 3 |
+
size 19575295
|
model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2e0cd7aed2ebfe6b9ce5ba88bb4cb6c85775d1763a71e02331526ffd9daea00
|
| 3 |
+
size 19574962
|
model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6371dd7e7def210336191622362c6335c3b494a959117650c049a7b74bb9c3e8
|
| 3 |
+
size 19575843
|
model/model/language_model/layers/0/mlp/up_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8084892313154516c38de6879f93875aebe7372344e871a71985abaad90c751
|
| 3 |
+
size 19590176
|
model/model/language_model/layers/0/mlp/up_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e329a022ff0050a41ec66b598fb4886c82ef0cf82f857387d12b44c683e2f18
|
| 3 |
+
size 19588591
|
model/model/language_model/layers/0/mlp/up_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:555945dc0f8477740068e3f96ee65f626ce12e68078b2364e77a6e374f69d6e6
|
| 3 |
+
size 19589017
|
model/model/language_model/layers/0/mlp/up_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:169219d259db8c0599eea52d272c1055fa151baea26ab455469ff89de77a84f6
|
| 3 |
+
size 19591600
|
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb475ec73b8ea42357393b23f977820ffd222634ec8cc7f07efea14c9e1a9d66
|
| 3 |
+
size 13059213
|
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c68dc1360ce0cfff0775ed93821da8676858725649c1151cfe7b0d1c32a9c12c
|
| 3 |
+
size 13056431
|
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b723f03405a9d9d7aa1e3e7181e1daa886d3e8a9f6f0a1fe031e4d39203f95bc
|
| 3 |
+
size 13056718
|
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21c97f0d334eaff7dec32f1157ef6387c8aa79b6a8beab025869ec7d1354690e
|
| 3 |
+
size 13057838
|
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4fb414f551afa957e9faa5e776501a8f6c32242fda23ecfa1de365443b67e2e
|
| 3 |
+
size 6534393
|
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0eaee696465ca7b373c37310b95c4dc0605acffe4b0c385febf5a892d954151f
|
| 3 |
+
size 6533560
|
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:166ed65dcb09b1662b6e0326f6a324e139b280e09b039f5ba69a0c84522cd9dd
|
| 3 |
+
size 6533276
|
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ab537345216ae95df81edd47f58e7e1b2d017f140b4563e568b90015239a0d3
|
| 3 |
+
size 6533932
|
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1078d6b3ebc03a56f50d36ce351632649a056129b42968265759f04ac2a7c046
|
| 3 |
+
size 6530367
|
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00ef6b99933329d46695cebfac4c9c2af6eb74faa0ee95d41fad91a93d95ed7d
|
| 3 |
+
size 6529426
|
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b3daed658fcbdff871d4e5c481954d0f8a5e6cfc505ac67b5c069b83efe6f56
|
| 3 |
+
size 6529785
|
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b05c17f4fad37b859bf095f04263c629641b80bb80216584c8f953fe35bdcabb
|
| 3 |
+
size 6531262
|
model/model/language_model/layers/1/mlp/down_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ae747e1272c285df47de20f762de9e90066ef48c38c655fdeeacb4eeac235e1
|
| 3 |
+
size 19595811
|
model/model/language_model/layers/1/mlp/down_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49fedf858d2ca96abc9cafd5f00f42718646be7b878d1c064d8c45e8515ba6a8
|
| 3 |
+
size 19594121
|
model/model/language_model/layers/1/mlp/down_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d87b1a89b160711b5aa6073aa141c8b9b44c641f7830f6f1d9d1250ab7d6c7d
|
| 3 |
+
size 19594278
|
model/model/language_model/layers/1/mlp/down_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91834308ab340316c2d78dc317ed6021444dd6d22b44c3b0fcc6a4fcc9e54458
|
| 3 |
+
size 19596525
|
model/model/language_model/layers/1/mlp/gate_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c742364c1a4605864f0c0ab315cc71174591171cfee375204d5296087315b59b
|
| 3 |
+
size 19567562
|
model/model/language_model/layers/1/mlp/gate_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d452c4bc2d9da7cdd2259ba1b7f121b10f2533c3664cdab8885990c0f810d0c
|
| 3 |
+
size 19564812
|
model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e288a77b9b2447e0b46b48ffd67577917b464e78a565f8430851eb754c77e46
|
| 3 |
+
size 19565136
|
model/model/language_model/layers/1/mlp/gate_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3f1a87abf352e826d03c6c83b12bf5b6885eebef98192e21ad47f7f5726de75
|
| 3 |
+
size 19566376
|
model/model/language_model/layers/1/mlp/up_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd8f1deb1653fc46bffd63e832cf8bc052739212962974e0405019ad68fa0e20
|
| 3 |
+
size 19589888
|
model/model/language_model/layers/1/mlp/up_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a15b201dc42d4f55fbd222bcfa5afac2ae4483531f2c22f8fe463c295624a3e7
|
| 3 |
+
size 19582858
|
model/model/language_model/layers/1/mlp/up_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b93ee3784ffc397a46b36174baba829eec4b47f0acc95addd1cf79e2761cef44
|
| 3 |
+
size 19584374
|
model/model/language_model/layers/1/mlp/up_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ae34a076821e7467504bd91dc5ea5f954959dd5aef0d538a716e308e5aea0f5
|
| 3 |
+
size 19587496
|