Change model shards size
Browse files- pytorch_model-00001-of-00002.bin → pytorch_model-00001-of-00035.bin +2 -2
- pytorch_model-00002-of-00002.bin → pytorch_model-00002-of-00035.bin +2 -2
- pytorch_model-00003-of-00035.bin +3 -0
- pytorch_model-00004-of-00035.bin +3 -0
- pytorch_model-00005-of-00035.bin +3 -0
- pytorch_model-00006-of-00035.bin +3 -0
- pytorch_model-00007-of-00035.bin +3 -0
- pytorch_model-00008-of-00035.bin +3 -0
- pytorch_model-00009-of-00035.bin +3 -0
- pytorch_model-00010-of-00035.bin +3 -0
- pytorch_model-00011-of-00035.bin +3 -0
- pytorch_model-00012-of-00035.bin +3 -0
- pytorch_model-00013-of-00035.bin +3 -0
- pytorch_model-00014-of-00035.bin +3 -0
- pytorch_model-00015-of-00035.bin +3 -0
- pytorch_model-00016-of-00035.bin +3 -0
- pytorch_model-00017-of-00035.bin +3 -0
- pytorch_model-00018-of-00035.bin +3 -0
- pytorch_model-00019-of-00035.bin +3 -0
- pytorch_model-00020-of-00035.bin +3 -0
- pytorch_model-00021-of-00035.bin +3 -0
- pytorch_model-00022-of-00035.bin +3 -0
- pytorch_model-00023-of-00035.bin +3 -0
- pytorch_model-00024-of-00035.bin +3 -0
- pytorch_model-00025-of-00035.bin +3 -0
- pytorch_model-00026-of-00035.bin +3 -0
- pytorch_model-00027-of-00035.bin +3 -0
- pytorch_model-00028-of-00035.bin +3 -0
- pytorch_model-00029-of-00035.bin +3 -0
- pytorch_model-00030-of-00035.bin +3 -0
- pytorch_model-00031-of-00035.bin +3 -0
- pytorch_model-00032-of-00035.bin +3 -0
- pytorch_model-00033-of-00035.bin +3 -0
- pytorch_model-00034-of-00035.bin +3 -0
- pytorch_model-00035-of-00035.bin +3 -0
- pytorch_model.bin.index.json +323 -323
pytorch_model-00001-of-00002.bin → pytorch_model-00001-of-00035.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf02c4d7b83fa495ef73f290168a195ea899d0744f0fe32194046846bd87efe0
|
| 3 |
+
size 537
|
pytorch_model-00002-of-00002.bin → pytorch_model-00002-of-00035.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14c7ccb070c8dd36e4188dfdf9194ca5be944cbed5a71c0cc7022caefc43a010
|
| 3 |
+
size 409224106
|
pytorch_model-00003-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb477f9c7a5739eb17f53faccd3efd84e8f81c7104a822d1b90545b997aeb745
|
| 3 |
+
size 404770755
|
pytorch_model-00004-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:facd1d5d8e052787a2ae53c2ff21e6b82d9db9ad18c58fe5b61c1f602726c572
|
| 3 |
+
size 404770755
|
pytorch_model-00005-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:114ac2f3497abd7eba6d043bcfb2d6765000ce013714dae86d4d0b42a4032f62
|
| 3 |
+
size 404770755
|
pytorch_model-00006-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65063e8f74545cc037edbc2348d1092e3d06e01fe947bfa2472c64123a808796
|
| 3 |
+
size 404770755
|
pytorch_model-00007-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:342db63f87b74e48eedc656c485b9e4d54b01d4d30cdee8d681a6c3c1450737d
|
| 3 |
+
size 404770755
|
pytorch_model-00008-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18cc705d425f2a5871c1b333cc9807e5747ed0e5d6398481a767a84afd0b1c2b
|
| 3 |
+
size 404770755
|
pytorch_model-00009-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23db5e10a0a2e2e99bef5cbf301254954eef6a8b78ae998f8363cec112f543dc
|
| 3 |
+
size 404770755
|
pytorch_model-00010-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3608f53b22f3d457e6833fbe5a2fdccb69c2facdd528faff12c8bc0292973e3c
|
| 3 |
+
size 404770755
|
pytorch_model-00011-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43661f5036b61343995fff7709b1411b7a0fe683af513cbe8786490926ab0925
|
| 3 |
+
size 404770755
|
pytorch_model-00012-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b59a6504fc6b17082a0e254a7a9017e2e9ba03b16fbad44783358c6b743534d
|
| 3 |
+
size 404770755
|
pytorch_model-00013-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4de378119a5a34a53cea7cc3562fcf6ea778e2058fbcf1135ce8b3ae43d4297
|
| 3 |
+
size 404770755
|
pytorch_model-00014-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cda1cb91adad3eec34ff27984894641268b79192f083305b7c4236087e45fbf8
|
| 3 |
+
size 404770755
|
pytorch_model-00015-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13159a0fecfdf4f9bfdbae2805b2a3d410898b932a22889b5d09d6ccb4f73e11
|
| 3 |
+
size 404770755
|
pytorch_model-00016-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4339fbcf8e8e07a9008303c668ee055d8f3624c4c8eb3bc95ad05d295e32e473
|
| 3 |
+
size 404770755
|
pytorch_model-00017-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f929d7decef6cb18968e0801c0335cf163b8360572b203ba70d74ff4d7bb8054
|
| 3 |
+
size 404770755
|
pytorch_model-00018-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bf8a2843a8a44abf2bf2b50b6b468e7500c2f4a0c10c51dba504dca62c878c0
|
| 3 |
+
size 404770755
|
pytorch_model-00019-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56a4e1ad1023b8c85b51ec00a55361177b381425a84a731ec838bf604613a5aa
|
| 3 |
+
size 404770755
|
pytorch_model-00020-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:809c49ce2f067dfb700dd5bf517c24e307c1fabff38389b38bade1160d492609
|
| 3 |
+
size 404770755
|
pytorch_model-00021-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79fe1c987c4b869e5f2e5d45ba033cf0eaab70ac21857b994bf06425b482fefd
|
| 3 |
+
size 404770755
|
pytorch_model-00022-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a59ee3e6c3fcbeda627320f43b2bacf0bae3faaf4b2b187324ffa8cf20dc23
|
| 3 |
+
size 404770755
|
pytorch_model-00023-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a0b5fd6eca85f4794ca9e352ea1a5ac6c7fe08385275e0e88e4ded0b64679ed
|
| 3 |
+
size 404770755
|
pytorch_model-00024-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dd274995795a26df0fe44220f624dc05ce61de7a2123538bd13766dcf9cd977
|
| 3 |
+
size 404770755
|
pytorch_model-00025-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fdbf8f946f595156eeea4576bc2143fd14f75b163fe30e2558a56dd69ea7ed3
|
| 3 |
+
size 404770755
|
pytorch_model-00026-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b105781772abeeb10dd280093d37e7ccfed712105718999ac4fc806d3fc9bfd
|
| 3 |
+
size 404770755
|
pytorch_model-00027-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb9cbf6c885ac0af05a04158ecbf86c7c1f88bc9e2f0e368ef97f7c6d6ed14
|
| 3 |
+
size 404770755
|
pytorch_model-00028-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1030b039e0bf2e09262d7be15cae3eb010b724cd4420d156d75c7d8e5206501a
|
| 3 |
+
size 404770755
|
pytorch_model-00029-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29442782e2ce159fc81b8c93b8b6e6ed5cb8a2953934abb85d0fc2e0468b4814
|
| 3 |
+
size 404770755
|
pytorch_model-00030-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fcefcba84f9ffeca482d9e042af100a1d1ceccbdf9cb06378adbe14ed1382f3
|
| 3 |
+
size 404770755
|
pytorch_model-00031-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093e95b96f7250e7b86400065d765f80e068d6aeafd34f1ea99de193332a2837
|
| 3 |
+
size 404770755
|
pytorch_model-00032-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60a60fcd1ccf1030070bf1d150e5d90e595411c6f1ed569f17cdb963a11abfae
|
| 3 |
+
size 404770755
|
pytorch_model-00033-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c86774d672c85ee93057b502d3ac07fde4ee47e671be03e2d6a212e89e47d2c
|
| 3 |
+
size 404770755
|
pytorch_model-00034-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:484f0948502c91637f5aba4ce8c0f8f70b5d33b93962c69c94bc28c55cef5e68
|
| 3 |
+
size 404779221
|
pytorch_model-00035-of-00035.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bc4bba8c450c45c1f1a74052caf386f03c16e05a8234a3620751a9350c1d8be
|
| 3 |
+
size 409224106
|
pytorch_model.bin.index.json
CHANGED
|
@@ -3,328 +3,328 @@
|
|
| 3 |
"total_size": 13770997760
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"lm_head.weight": "pytorch_model-
|
| 7 |
-
"model.embed_tokens.weight": "pytorch_model-
|
| 8 |
-
"model.layers.0.input_layernorm.weight": "pytorch_model-
|
| 9 |
-
"model.layers.0.mlp.down_proj.weight": "pytorch_model-
|
| 10 |
-
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-
|
| 11 |
-
"model.layers.0.mlp.up_proj.weight": "pytorch_model-
|
| 12 |
-
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-
|
| 13 |
-
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-
|
| 14 |
-
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-
|
| 15 |
-
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-
|
| 16 |
-
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 17 |
-
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-
|
| 18 |
-
"model.layers.1.input_layernorm.weight": "pytorch_model-
|
| 19 |
-
"model.layers.1.mlp.down_proj.weight": "pytorch_model-
|
| 20 |
-
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-
|
| 21 |
-
"model.layers.1.mlp.up_proj.weight": "pytorch_model-
|
| 22 |
-
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-
|
| 23 |
-
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-
|
| 24 |
-
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-
|
| 25 |
-
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-
|
| 26 |
-
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 27 |
-
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-
|
| 28 |
-
"model.layers.10.input_layernorm.weight": "pytorch_model-
|
| 29 |
-
"model.layers.10.mlp.down_proj.weight": "pytorch_model-
|
| 30 |
-
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-
|
| 31 |
-
"model.layers.10.mlp.up_proj.weight": "pytorch_model-
|
| 32 |
-
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-
|
| 33 |
-
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-
|
| 34 |
-
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-
|
| 35 |
-
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-
|
| 36 |
-
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 37 |
-
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-
|
| 38 |
-
"model.layers.11.input_layernorm.weight": "pytorch_model-
|
| 39 |
-
"model.layers.11.mlp.down_proj.weight": "pytorch_model-
|
| 40 |
-
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-
|
| 41 |
-
"model.layers.11.mlp.up_proj.weight": "pytorch_model-
|
| 42 |
-
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-
|
| 43 |
-
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-
|
| 44 |
-
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-
|
| 45 |
-
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-
|
| 46 |
-
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 47 |
-
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-
|
| 48 |
-
"model.layers.12.input_layernorm.weight": "pytorch_model-
|
| 49 |
-
"model.layers.12.mlp.down_proj.weight": "pytorch_model-
|
| 50 |
-
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-
|
| 51 |
-
"model.layers.12.mlp.up_proj.weight": "pytorch_model-
|
| 52 |
-
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-
|
| 53 |
-
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-
|
| 54 |
-
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-
|
| 55 |
-
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-
|
| 56 |
-
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 57 |
-
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-
|
| 58 |
-
"model.layers.13.input_layernorm.weight": "pytorch_model-
|
| 59 |
-
"model.layers.13.mlp.down_proj.weight": "pytorch_model-
|
| 60 |
-
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-
|
| 61 |
-
"model.layers.13.mlp.up_proj.weight": "pytorch_model-
|
| 62 |
-
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-
|
| 63 |
-
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-
|
| 64 |
-
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-
|
| 65 |
-
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-
|
| 66 |
-
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 67 |
-
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-
|
| 68 |
-
"model.layers.14.input_layernorm.weight": "pytorch_model-
|
| 69 |
-
"model.layers.14.mlp.down_proj.weight": "pytorch_model-
|
| 70 |
-
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-
|
| 71 |
-
"model.layers.14.mlp.up_proj.weight": "pytorch_model-
|
| 72 |
-
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-
|
| 73 |
-
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-
|
| 74 |
-
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-
|
| 75 |
-
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-
|
| 76 |
-
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 77 |
-
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-
|
| 78 |
-
"model.layers.15.input_layernorm.weight": "pytorch_model-
|
| 79 |
-
"model.layers.15.mlp.down_proj.weight": "pytorch_model-
|
| 80 |
-
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-
|
| 81 |
-
"model.layers.15.mlp.up_proj.weight": "pytorch_model-
|
| 82 |
-
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-
|
| 83 |
-
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-
|
| 84 |
-
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-
|
| 85 |
-
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-
|
| 86 |
-
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 87 |
-
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-
|
| 88 |
-
"model.layers.16.input_layernorm.weight": "pytorch_model-
|
| 89 |
-
"model.layers.16.mlp.down_proj.weight": "pytorch_model-
|
| 90 |
-
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-
|
| 91 |
-
"model.layers.16.mlp.up_proj.weight": "pytorch_model-
|
| 92 |
-
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-
|
| 93 |
-
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-
|
| 94 |
-
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-
|
| 95 |
-
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-
|
| 96 |
-
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 97 |
-
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-
|
| 98 |
-
"model.layers.17.input_layernorm.weight": "pytorch_model-
|
| 99 |
-
"model.layers.17.mlp.down_proj.weight": "pytorch_model-
|
| 100 |
-
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-
|
| 101 |
-
"model.layers.17.mlp.up_proj.weight": "pytorch_model-
|
| 102 |
-
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-
|
| 103 |
-
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-
|
| 104 |
-
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-
|
| 105 |
-
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-
|
| 106 |
-
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 107 |
-
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-
|
| 108 |
-
"model.layers.18.input_layernorm.weight": "pytorch_model-
|
| 109 |
-
"model.layers.18.mlp.down_proj.weight": "pytorch_model-
|
| 110 |
-
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-
|
| 111 |
-
"model.layers.18.mlp.up_proj.weight": "pytorch_model-
|
| 112 |
-
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-
|
| 113 |
-
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-
|
| 114 |
-
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-
|
| 115 |
-
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-
|
| 116 |
-
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 117 |
-
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-
|
| 118 |
-
"model.layers.19.input_layernorm.weight": "pytorch_model-
|
| 119 |
-
"model.layers.19.mlp.down_proj.weight": "pytorch_model-
|
| 120 |
-
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-
|
| 121 |
-
"model.layers.19.mlp.up_proj.weight": "pytorch_model-
|
| 122 |
-
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-
|
| 123 |
-
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-
|
| 124 |
-
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-
|
| 125 |
-
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-
|
| 126 |
-
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 127 |
-
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-
|
| 128 |
-
"model.layers.2.input_layernorm.weight": "pytorch_model-
|
| 129 |
-
"model.layers.2.mlp.down_proj.weight": "pytorch_model-
|
| 130 |
-
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-
|
| 131 |
-
"model.layers.2.mlp.up_proj.weight": "pytorch_model-
|
| 132 |
-
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-
|
| 133 |
-
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-
|
| 134 |
-
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-
|
| 135 |
-
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-
|
| 136 |
-
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 137 |
-
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-
|
| 138 |
-
"model.layers.20.input_layernorm.weight": "pytorch_model-
|
| 139 |
-
"model.layers.20.mlp.down_proj.weight": "pytorch_model-
|
| 140 |
-
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-
|
| 141 |
-
"model.layers.20.mlp.up_proj.weight": "pytorch_model-
|
| 142 |
-
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-
|
| 143 |
-
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-
|
| 144 |
-
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-
|
| 145 |
-
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-
|
| 146 |
-
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 147 |
-
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-
|
| 148 |
-
"model.layers.21.input_layernorm.weight": "pytorch_model-
|
| 149 |
-
"model.layers.21.mlp.down_proj.weight": "pytorch_model-
|
| 150 |
-
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-
|
| 151 |
-
"model.layers.21.mlp.up_proj.weight": "pytorch_model-
|
| 152 |
-
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-
|
| 153 |
-
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-
|
| 154 |
-
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-
|
| 155 |
-
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-
|
| 156 |
-
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 157 |
-
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-
|
| 158 |
-
"model.layers.22.input_layernorm.weight": "pytorch_model-
|
| 159 |
-
"model.layers.22.mlp.down_proj.weight": "pytorch_model-
|
| 160 |
-
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-
|
| 161 |
-
"model.layers.22.mlp.up_proj.weight": "pytorch_model-
|
| 162 |
-
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-
|
| 163 |
-
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-
|
| 164 |
-
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-
|
| 165 |
-
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-
|
| 166 |
-
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 167 |
-
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-
|
| 168 |
-
"model.layers.23.input_layernorm.weight": "pytorch_model-
|
| 169 |
-
"model.layers.23.mlp.down_proj.weight": "pytorch_model-
|
| 170 |
-
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-
|
| 171 |
-
"model.layers.23.mlp.up_proj.weight": "pytorch_model-
|
| 172 |
-
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-
|
| 173 |
-
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-
|
| 174 |
-
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-
|
| 175 |
-
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-
|
| 176 |
-
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 177 |
-
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-
|
| 178 |
-
"model.layers.24.input_layernorm.weight": "pytorch_model-
|
| 179 |
-
"model.layers.24.mlp.down_proj.weight": "pytorch_model-
|
| 180 |
-
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-
|
| 181 |
-
"model.layers.24.mlp.up_proj.weight": "pytorch_model-
|
| 182 |
-
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-
|
| 183 |
-
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-
|
| 184 |
-
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-
|
| 185 |
-
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-
|
| 186 |
-
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 187 |
-
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-
|
| 188 |
-
"model.layers.25.input_layernorm.weight": "pytorch_model-
|
| 189 |
-
"model.layers.25.mlp.down_proj.weight": "pytorch_model-
|
| 190 |
-
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-
|
| 191 |
-
"model.layers.25.mlp.up_proj.weight": "pytorch_model-
|
| 192 |
-
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-
|
| 193 |
-
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-
|
| 194 |
-
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-
|
| 195 |
-
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-
|
| 196 |
-
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 197 |
-
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-
|
| 198 |
-
"model.layers.26.input_layernorm.weight": "pytorch_model-
|
| 199 |
-
"model.layers.26.mlp.down_proj.weight": "pytorch_model-
|
| 200 |
-
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-
|
| 201 |
-
"model.layers.26.mlp.up_proj.weight": "pytorch_model-
|
| 202 |
-
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-
|
| 203 |
-
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-
|
| 204 |
-
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-
|
| 205 |
-
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-
|
| 206 |
-
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 207 |
-
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-
|
| 208 |
-
"model.layers.27.input_layernorm.weight": "pytorch_model-
|
| 209 |
-
"model.layers.27.mlp.down_proj.weight": "pytorch_model-
|
| 210 |
-
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-
|
| 211 |
-
"model.layers.27.mlp.up_proj.weight": "pytorch_model-
|
| 212 |
-
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-
|
| 213 |
-
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-
|
| 214 |
-
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-
|
| 215 |
-
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-
|
| 216 |
-
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 217 |
-
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-
|
| 218 |
-
"model.layers.28.input_layernorm.weight": "pytorch_model-
|
| 219 |
-
"model.layers.28.mlp.down_proj.weight": "pytorch_model-
|
| 220 |
-
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-
|
| 221 |
-
"model.layers.28.mlp.up_proj.weight": "pytorch_model-
|
| 222 |
-
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-
|
| 223 |
-
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-
|
| 224 |
-
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-
|
| 225 |
-
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-
|
| 226 |
-
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 227 |
-
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-
|
| 228 |
-
"model.layers.29.input_layernorm.weight": "pytorch_model-
|
| 229 |
-
"model.layers.29.mlp.down_proj.weight": "pytorch_model-
|
| 230 |
-
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-
|
| 231 |
-
"model.layers.29.mlp.up_proj.weight": "pytorch_model-
|
| 232 |
-
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-
|
| 233 |
-
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-
|
| 234 |
-
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-
|
| 235 |
-
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-
|
| 236 |
-
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 237 |
-
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-
|
| 238 |
-
"model.layers.3.input_layernorm.weight": "pytorch_model-
|
| 239 |
-
"model.layers.3.mlp.down_proj.weight": "pytorch_model-
|
| 240 |
-
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-
|
| 241 |
-
"model.layers.3.mlp.up_proj.weight": "pytorch_model-
|
| 242 |
-
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-
|
| 243 |
-
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-
|
| 244 |
-
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-
|
| 245 |
-
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-
|
| 246 |
-
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 247 |
-
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-
|
| 248 |
-
"model.layers.30.input_layernorm.weight": "pytorch_model-
|
| 249 |
-
"model.layers.30.mlp.down_proj.weight": "pytorch_model-
|
| 250 |
-
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-
|
| 251 |
-
"model.layers.30.mlp.up_proj.weight": "pytorch_model-
|
| 252 |
-
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-
|
| 253 |
-
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-
|
| 254 |
-
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-
|
| 255 |
-
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-
|
| 256 |
-
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 257 |
-
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-
|
| 258 |
-
"model.layers.31.input_layernorm.weight": "pytorch_model-
|
| 259 |
-
"model.layers.31.mlp.down_proj.weight": "pytorch_model-
|
| 260 |
-
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-
|
| 261 |
-
"model.layers.31.mlp.up_proj.weight": "pytorch_model-
|
| 262 |
-
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-
|
| 263 |
-
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-
|
| 264 |
-
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-
|
| 265 |
-
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-
|
| 266 |
-
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 267 |
-
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-
|
| 268 |
-
"model.layers.4.input_layernorm.weight": "pytorch_model-
|
| 269 |
-
"model.layers.4.mlp.down_proj.weight": "pytorch_model-
|
| 270 |
-
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-
|
| 271 |
-
"model.layers.4.mlp.up_proj.weight": "pytorch_model-
|
| 272 |
-
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-
|
| 273 |
-
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-
|
| 274 |
-
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-
|
| 275 |
-
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-
|
| 276 |
-
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 277 |
-
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-
|
| 278 |
-
"model.layers.5.input_layernorm.weight": "pytorch_model-
|
| 279 |
-
"model.layers.5.mlp.down_proj.weight": "pytorch_model-
|
| 280 |
-
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-
|
| 281 |
-
"model.layers.5.mlp.up_proj.weight": "pytorch_model-
|
| 282 |
-
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-
|
| 283 |
-
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-
|
| 284 |
-
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-
|
| 285 |
-
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-
|
| 286 |
-
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 287 |
-
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-
|
| 288 |
-
"model.layers.6.input_layernorm.weight": "pytorch_model-
|
| 289 |
-
"model.layers.6.mlp.down_proj.weight": "pytorch_model-
|
| 290 |
-
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-
|
| 291 |
-
"model.layers.6.mlp.up_proj.weight": "pytorch_model-
|
| 292 |
-
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-
|
| 293 |
-
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-
|
| 294 |
-
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-
|
| 295 |
-
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-
|
| 296 |
-
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 297 |
-
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-
|
| 298 |
-
"model.layers.7.input_layernorm.weight": "pytorch_model-
|
| 299 |
-
"model.layers.7.mlp.down_proj.weight": "pytorch_model-
|
| 300 |
-
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-
|
| 301 |
-
"model.layers.7.mlp.up_proj.weight": "pytorch_model-
|
| 302 |
-
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-
|
| 303 |
-
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-
|
| 304 |
-
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-
|
| 305 |
-
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-
|
| 306 |
-
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 307 |
-
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-
|
| 308 |
-
"model.layers.8.input_layernorm.weight": "pytorch_model-
|
| 309 |
-
"model.layers.8.mlp.down_proj.weight": "pytorch_model-
|
| 310 |
-
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-
|
| 311 |
-
"model.layers.8.mlp.up_proj.weight": "pytorch_model-
|
| 312 |
-
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-
|
| 313 |
-
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-
|
| 314 |
-
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-
|
| 315 |
-
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-
|
| 316 |
-
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 317 |
-
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-
|
| 318 |
-
"model.layers.9.input_layernorm.weight": "pytorch_model-
|
| 319 |
-
"model.layers.9.mlp.down_proj.weight": "pytorch_model-
|
| 320 |
-
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-
|
| 321 |
-
"model.layers.9.mlp.up_proj.weight": "pytorch_model-
|
| 322 |
-
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-
|
| 323 |
-
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-
|
| 324 |
-
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-
|
| 325 |
-
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-
|
| 326 |
-
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 327 |
-
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-
|
| 328 |
-
"model.norm.weight": "pytorch_model-
|
| 329 |
}
|
| 330 |
}
|
|
|
|
| 3 |
"total_size": 13770997760
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00035-of-00035.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00002-of-00035.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00035.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00035.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00035.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00035.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00004-of-00035.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00035.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00035.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00004-of-00035.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00013-of-00035.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00013-of-00035.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00035.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00035.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00014-of-00035.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00014-of-00035.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00035.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00035.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00015-of-00035.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00015-of-00035.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00035.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00035.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00016-of-00035.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00016-of-00035.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00035.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00035.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00017-of-00035.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00017-of-00035.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00035.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00017-of-00035.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00018-of-00035.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00018-of-00035.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00035.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00018-of-00035.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00019-of-00035.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00019-of-00035.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00035.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00019-of-00035.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00020-of-00035.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00020-of-00035.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00035.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00020-of-00035.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00021-of-00035.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00021-of-00035.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00035.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00021-of-00035.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00022-of-00035.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00022-of-00035.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00035.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00022-of-00035.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00005-of-00035.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00005-of-00035.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00035.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00005-of-00035.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00023-of-00035.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00023-of-00035.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00035.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00023-of-00035.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00024-of-00035.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00024-of-00035.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00035.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00024-of-00035.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00025-of-00035.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00025-of-00035.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00035.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00025-of-00035.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00026-of-00035.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00026-of-00035.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00035.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00026-of-00035.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00027-of-00035.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00027-of-00035.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00035.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00027-of-00035.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00028-of-00035.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00028-of-00035.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00035.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00028-of-00035.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00029-of-00035.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00029-of-00035.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00035.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00029-of-00035.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00030-of-00035.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00030-of-00035.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00035.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00030-of-00035.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00031-of-00035.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00031-of-00035.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00035.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00031-of-00035.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00032-of-00035.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00032-of-00035.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00035.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00032-of-00035.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00006-of-00035.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00006-of-00035.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00035.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00006-of-00035.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00033-of-00035.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00033-of-00035.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00035.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00033-of-00035.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00034-of-00035.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00034-of-00035.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00035.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00034-of-00035.bin",
|
| 268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00035.bin",
|
| 269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00035.bin",
|
| 273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00035.bin",
|
| 277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00007-of-00035.bin",
|
| 278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00035.bin",
|
| 279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00035.bin",
|
| 283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00035.bin",
|
| 287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00008-of-00035.bin",
|
| 288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00035.bin",
|
| 289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00035.bin",
|
| 293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00035.bin",
|
| 297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00009-of-00035.bin",
|
| 298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00035.bin",
|
| 299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00035.bin",
|
| 303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00035.bin",
|
| 307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00010-of-00035.bin",
|
| 308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00035.bin",
|
| 309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00035.bin",
|
| 313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00035.bin",
|
| 317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00035.bin",
|
| 318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00035.bin",
|
| 319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00035.bin",
|
| 323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00035.bin",
|
| 327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00035.bin",
|
| 328 |
+
"model.norm.weight": "pytorch_model-00034-of-00035.bin"
|
| 329 |
}
|
| 330 |
}
|