Upload ExtendedMptForCausalLM
Browse files- config.json +2 -2
- pytorch_model-00001-of-00013.bin +3 -0
- pytorch_model-00002-of-00013.bin +3 -0
- pytorch_model-00003-of-00013.bin +3 -0
- pytorch_model-00004-of-00013.bin +3 -0
- pytorch_model-00005-of-00013.bin +3 -0
- pytorch_model-00006-of-00013.bin +3 -0
- pytorch_model-00007-of-00013.bin +3 -0
- pytorch_model-00008-of-00013.bin +3 -0
- pytorch_model-00009-of-00013.bin +3 -0
- pytorch_model-00010-of-00013.bin +3 -0
- pytorch_model-00011-of-00013.bin +3 -0
- pytorch_model-00012-of-00013.bin +3 -0
- pytorch_model-00013-of-00013.bin +3 -0
- pytorch_model.bin.index.json +298 -0
config.json
CHANGED
|
@@ -7,8 +7,8 @@
|
|
| 7 |
"model_type": ""
|
| 8 |
},
|
| 9 |
"auto_map": {
|
| 10 |
-
"AutoConfig": "
|
| 11 |
-
"AutoModelForCausalLM": "
|
| 12 |
},
|
| 13 |
"d_model": 7168,
|
| 14 |
"emb_pdrop": 0,
|
|
|
|
| 7 |
"model_type": ""
|
| 8 |
},
|
| 9 |
"auto_map": {
|
| 10 |
+
"AutoConfig": "mosaicml/mpt-30b-chat--configuration_mpt.MPTConfig",
|
| 11 |
+
"AutoModelForCausalLM": "mosaicml/mpt-30b-chat--modeling_mpt.MPTForCausalLM"
|
| 12 |
},
|
| 13 |
"d_model": 7168,
|
| 14 |
"emb_pdrop": 0,
|
pytorch_model-00001-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb1e4bfad811b21ba012f0ff0a69864793f979f9f3c9b04c295a4054b3843340
|
| 3 |
+
size 9667059549
|
pytorch_model-00002-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c25bf83eed58cbda43401178ae66cb2a396fb6eaab4fb4f2dd094222dfde7d6f
|
| 3 |
+
size 9865240711
|
pytorch_model-00003-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e44514358e2cff6b5b6d5e517252b0e4722713a9c0d24c4a1b593c1ba0904517
|
| 3 |
+
size 9865240711
|
pytorch_model-00004-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19422e3e725a67b75b47224515dd527dcf08e92eeeae8d0e32e24adea5b57650
|
| 3 |
+
size 9865240711
|
pytorch_model-00005-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:871ac0c0905174ef30eb9fec4a7b610444c61f0c1a8f5f154fd1f7b66acd7b64
|
| 3 |
+
size 9865240711
|
pytorch_model-00006-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:121dc7bd6cedb355bfb3bfd0a987413db30890d332dd6c9046bfbbfb3f35e828
|
| 3 |
+
size 9865240711
|
pytorch_model-00007-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d2271947c77223076e65947d2fc2aec3d1092125dd2932c92438213330c9eeb
|
| 3 |
+
size 9865240711
|
pytorch_model-00008-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bffae1e78d9787a5aa3152ce622e6db1488dea2cdc13edf13a33fa1c655c511
|
| 3 |
+
size 9865240711
|
pytorch_model-00009-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:173e29b4ca813ae9428a5053894de458dd2b129ea5adcea1c21e332905d971ad
|
| 3 |
+
size 9865240711
|
pytorch_model-00010-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ba3cf26661366c3bf44739d6ce4ab32e273b3c264ecd396b9497782fb9336b4
|
| 3 |
+
size 9865240711
|
pytorch_model-00011-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55c4996908f7f47146ae45700e877ac98efc00878e5a145dd0deba8d6e42bd7a
|
| 3 |
+
size 9865240711
|
pytorch_model-00012-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ce1cc7738e489376936eeb8180b0b06330af03ce57c319c253297b649a5f688
|
| 3 |
+
size 9865240711
|
pytorch_model-00013-of-00013.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4908923f71c2ea5f4bb4a08c38ab594277cae393a4bb30b4cbb9041a962d1b1
|
| 3 |
+
size 1644197388
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 119828803584
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00001-of-00013.bin",
|
| 7 |
+
"transformer.blocks.0.attn.Wqkv.weight": "pytorch_model-00001-of-00013.bin",
|
| 8 |
+
"transformer.blocks.0.attn.out_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 9 |
+
"transformer.blocks.0.ffn.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 10 |
+
"transformer.blocks.0.ffn.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 11 |
+
"transformer.blocks.0.norm_1.weight": "pytorch_model-00001-of-00013.bin",
|
| 12 |
+
"transformer.blocks.0.norm_2.weight": "pytorch_model-00001-of-00013.bin",
|
| 13 |
+
"transformer.blocks.1.attn.Wqkv.weight": "pytorch_model-00001-of-00013.bin",
|
| 14 |
+
"transformer.blocks.1.attn.out_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 15 |
+
"transformer.blocks.1.ffn.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 16 |
+
"transformer.blocks.1.ffn.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 17 |
+
"transformer.blocks.1.norm_1.weight": "pytorch_model-00001-of-00013.bin",
|
| 18 |
+
"transformer.blocks.1.norm_2.weight": "pytorch_model-00001-of-00013.bin",
|
| 19 |
+
"transformer.blocks.10.attn.Wqkv.weight": "pytorch_model-00003-of-00013.bin",
|
| 20 |
+
"transformer.blocks.10.attn.out_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 21 |
+
"transformer.blocks.10.ffn.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 22 |
+
"transformer.blocks.10.ffn.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 23 |
+
"transformer.blocks.10.norm_1.weight": "pytorch_model-00003-of-00013.bin",
|
| 24 |
+
"transformer.blocks.10.norm_2.weight": "pytorch_model-00003-of-00013.bin",
|
| 25 |
+
"transformer.blocks.11.attn.Wqkv.weight": "pytorch_model-00003-of-00013.bin",
|
| 26 |
+
"transformer.blocks.11.attn.out_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 27 |
+
"transformer.blocks.11.ffn.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 28 |
+
"transformer.blocks.11.ffn.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 29 |
+
"transformer.blocks.11.norm_1.weight": "pytorch_model-00003-of-00013.bin",
|
| 30 |
+
"transformer.blocks.11.norm_2.weight": "pytorch_model-00003-of-00013.bin",
|
| 31 |
+
"transformer.blocks.12.attn.Wqkv.weight": "pytorch_model-00004-of-00013.bin",
|
| 32 |
+
"transformer.blocks.12.attn.out_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 33 |
+
"transformer.blocks.12.ffn.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 34 |
+
"transformer.blocks.12.ffn.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 35 |
+
"transformer.blocks.12.norm_1.weight": "pytorch_model-00004-of-00013.bin",
|
| 36 |
+
"transformer.blocks.12.norm_2.weight": "pytorch_model-00004-of-00013.bin",
|
| 37 |
+
"transformer.blocks.13.attn.Wqkv.weight": "pytorch_model-00004-of-00013.bin",
|
| 38 |
+
"transformer.blocks.13.attn.out_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 39 |
+
"transformer.blocks.13.ffn.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 40 |
+
"transformer.blocks.13.ffn.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 41 |
+
"transformer.blocks.13.norm_1.weight": "pytorch_model-00004-of-00013.bin",
|
| 42 |
+
"transformer.blocks.13.norm_2.weight": "pytorch_model-00004-of-00013.bin",
|
| 43 |
+
"transformer.blocks.14.attn.Wqkv.weight": "pytorch_model-00004-of-00013.bin",
|
| 44 |
+
"transformer.blocks.14.attn.out_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 45 |
+
"transformer.blocks.14.ffn.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 46 |
+
"transformer.blocks.14.ffn.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 47 |
+
"transformer.blocks.14.norm_1.weight": "pytorch_model-00004-of-00013.bin",
|
| 48 |
+
"transformer.blocks.14.norm_2.weight": "pytorch_model-00004-of-00013.bin",
|
| 49 |
+
"transformer.blocks.15.attn.Wqkv.weight": "pytorch_model-00004-of-00013.bin",
|
| 50 |
+
"transformer.blocks.15.attn.out_proj.weight": "pytorch_model-00004-of-00013.bin",
|
| 51 |
+
"transformer.blocks.15.ffn.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 52 |
+
"transformer.blocks.15.ffn.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 53 |
+
"transformer.blocks.15.norm_1.weight": "pytorch_model-00004-of-00013.bin",
|
| 54 |
+
"transformer.blocks.15.norm_2.weight": "pytorch_model-00004-of-00013.bin",
|
| 55 |
+
"transformer.blocks.16.attn.Wqkv.weight": "pytorch_model-00005-of-00013.bin",
|
| 56 |
+
"transformer.blocks.16.attn.out_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 57 |
+
"transformer.blocks.16.ffn.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 58 |
+
"transformer.blocks.16.ffn.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 59 |
+
"transformer.blocks.16.norm_1.weight": "pytorch_model-00005-of-00013.bin",
|
| 60 |
+
"transformer.blocks.16.norm_2.weight": "pytorch_model-00005-of-00013.bin",
|
| 61 |
+
"transformer.blocks.17.attn.Wqkv.weight": "pytorch_model-00005-of-00013.bin",
|
| 62 |
+
"transformer.blocks.17.attn.out_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 63 |
+
"transformer.blocks.17.ffn.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 64 |
+
"transformer.blocks.17.ffn.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 65 |
+
"transformer.blocks.17.norm_1.weight": "pytorch_model-00005-of-00013.bin",
|
| 66 |
+
"transformer.blocks.17.norm_2.weight": "pytorch_model-00005-of-00013.bin",
|
| 67 |
+
"transformer.blocks.18.attn.Wqkv.weight": "pytorch_model-00005-of-00013.bin",
|
| 68 |
+
"transformer.blocks.18.attn.out_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 69 |
+
"transformer.blocks.18.ffn.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 70 |
+
"transformer.blocks.18.ffn.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 71 |
+
"transformer.blocks.18.norm_1.weight": "pytorch_model-00005-of-00013.bin",
|
| 72 |
+
"transformer.blocks.18.norm_2.weight": "pytorch_model-00005-of-00013.bin",
|
| 73 |
+
"transformer.blocks.19.attn.Wqkv.weight": "pytorch_model-00005-of-00013.bin",
|
| 74 |
+
"transformer.blocks.19.attn.out_proj.weight": "pytorch_model-00005-of-00013.bin",
|
| 75 |
+
"transformer.blocks.19.ffn.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 76 |
+
"transformer.blocks.19.ffn.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 77 |
+
"transformer.blocks.19.norm_1.weight": "pytorch_model-00005-of-00013.bin",
|
| 78 |
+
"transformer.blocks.19.norm_2.weight": "pytorch_model-00005-of-00013.bin",
|
| 79 |
+
"transformer.blocks.2.attn.Wqkv.weight": "pytorch_model-00001-of-00013.bin",
|
| 80 |
+
"transformer.blocks.2.attn.out_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 81 |
+
"transformer.blocks.2.ffn.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 82 |
+
"transformer.blocks.2.ffn.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 83 |
+
"transformer.blocks.2.norm_1.weight": "pytorch_model-00001-of-00013.bin",
|
| 84 |
+
"transformer.blocks.2.norm_2.weight": "pytorch_model-00001-of-00013.bin",
|
| 85 |
+
"transformer.blocks.20.attn.Wqkv.weight": "pytorch_model-00006-of-00013.bin",
|
| 86 |
+
"transformer.blocks.20.attn.out_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 87 |
+
"transformer.blocks.20.ffn.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 88 |
+
"transformer.blocks.20.ffn.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 89 |
+
"transformer.blocks.20.norm_1.weight": "pytorch_model-00006-of-00013.bin",
|
| 90 |
+
"transformer.blocks.20.norm_2.weight": "pytorch_model-00006-of-00013.bin",
|
| 91 |
+
"transformer.blocks.21.attn.Wqkv.weight": "pytorch_model-00006-of-00013.bin",
|
| 92 |
+
"transformer.blocks.21.attn.out_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 93 |
+
"transformer.blocks.21.ffn.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 94 |
+
"transformer.blocks.21.ffn.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 95 |
+
"transformer.blocks.21.norm_1.weight": "pytorch_model-00006-of-00013.bin",
|
| 96 |
+
"transformer.blocks.21.norm_2.weight": "pytorch_model-00006-of-00013.bin",
|
| 97 |
+
"transformer.blocks.22.attn.Wqkv.weight": "pytorch_model-00006-of-00013.bin",
|
| 98 |
+
"transformer.blocks.22.attn.out_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 99 |
+
"transformer.blocks.22.ffn.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 100 |
+
"transformer.blocks.22.ffn.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 101 |
+
"transformer.blocks.22.norm_1.weight": "pytorch_model-00006-of-00013.bin",
|
| 102 |
+
"transformer.blocks.22.norm_2.weight": "pytorch_model-00006-of-00013.bin",
|
| 103 |
+
"transformer.blocks.23.attn.Wqkv.weight": "pytorch_model-00006-of-00013.bin",
|
| 104 |
+
"transformer.blocks.23.attn.out_proj.weight": "pytorch_model-00006-of-00013.bin",
|
| 105 |
+
"transformer.blocks.23.ffn.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 106 |
+
"transformer.blocks.23.ffn.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 107 |
+
"transformer.blocks.23.norm_1.weight": "pytorch_model-00006-of-00013.bin",
|
| 108 |
+
"transformer.blocks.23.norm_2.weight": "pytorch_model-00006-of-00013.bin",
|
| 109 |
+
"transformer.blocks.24.attn.Wqkv.weight": "pytorch_model-00007-of-00013.bin",
|
| 110 |
+
"transformer.blocks.24.attn.out_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 111 |
+
"transformer.blocks.24.ffn.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 112 |
+
"transformer.blocks.24.ffn.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 113 |
+
"transformer.blocks.24.norm_1.weight": "pytorch_model-00007-of-00013.bin",
|
| 114 |
+
"transformer.blocks.24.norm_2.weight": "pytorch_model-00007-of-00013.bin",
|
| 115 |
+
"transformer.blocks.25.attn.Wqkv.weight": "pytorch_model-00007-of-00013.bin",
|
| 116 |
+
"transformer.blocks.25.attn.out_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 117 |
+
"transformer.blocks.25.ffn.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 118 |
+
"transformer.blocks.25.ffn.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 119 |
+
"transformer.blocks.25.norm_1.weight": "pytorch_model-00007-of-00013.bin",
|
| 120 |
+
"transformer.blocks.25.norm_2.weight": "pytorch_model-00007-of-00013.bin",
|
| 121 |
+
"transformer.blocks.26.attn.Wqkv.weight": "pytorch_model-00007-of-00013.bin",
|
| 122 |
+
"transformer.blocks.26.attn.out_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 123 |
+
"transformer.blocks.26.ffn.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 124 |
+
"transformer.blocks.26.ffn.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 125 |
+
"transformer.blocks.26.norm_1.weight": "pytorch_model-00007-of-00013.bin",
|
| 126 |
+
"transformer.blocks.26.norm_2.weight": "pytorch_model-00007-of-00013.bin",
|
| 127 |
+
"transformer.blocks.27.attn.Wqkv.weight": "pytorch_model-00007-of-00013.bin",
|
| 128 |
+
"transformer.blocks.27.attn.out_proj.weight": "pytorch_model-00007-of-00013.bin",
|
| 129 |
+
"transformer.blocks.27.ffn.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 130 |
+
"transformer.blocks.27.ffn.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 131 |
+
"transformer.blocks.27.norm_1.weight": "pytorch_model-00007-of-00013.bin",
|
| 132 |
+
"transformer.blocks.27.norm_2.weight": "pytorch_model-00007-of-00013.bin",
|
| 133 |
+
"transformer.blocks.28.attn.Wqkv.weight": "pytorch_model-00008-of-00013.bin",
|
| 134 |
+
"transformer.blocks.28.attn.out_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 135 |
+
"transformer.blocks.28.ffn.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 136 |
+
"transformer.blocks.28.ffn.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 137 |
+
"transformer.blocks.28.norm_1.weight": "pytorch_model-00008-of-00013.bin",
|
| 138 |
+
"transformer.blocks.28.norm_2.weight": "pytorch_model-00008-of-00013.bin",
|
| 139 |
+
"transformer.blocks.29.attn.Wqkv.weight": "pytorch_model-00008-of-00013.bin",
|
| 140 |
+
"transformer.blocks.29.attn.out_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 141 |
+
"transformer.blocks.29.ffn.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 142 |
+
"transformer.blocks.29.ffn.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 143 |
+
"transformer.blocks.29.norm_1.weight": "pytorch_model-00008-of-00013.bin",
|
| 144 |
+
"transformer.blocks.29.norm_2.weight": "pytorch_model-00008-of-00013.bin",
|
| 145 |
+
"transformer.blocks.3.attn.Wqkv.weight": "pytorch_model-00001-of-00013.bin",
|
| 146 |
+
"transformer.blocks.3.attn.out_proj.weight": "pytorch_model-00001-of-00013.bin",
|
| 147 |
+
"transformer.blocks.3.ffn.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 148 |
+
"transformer.blocks.3.ffn.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 149 |
+
"transformer.blocks.3.norm_1.weight": "pytorch_model-00001-of-00013.bin",
|
| 150 |
+
"transformer.blocks.3.norm_2.weight": "pytorch_model-00001-of-00013.bin",
|
| 151 |
+
"transformer.blocks.30.attn.Wqkv.weight": "pytorch_model-00008-of-00013.bin",
|
| 152 |
+
"transformer.blocks.30.attn.out_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 153 |
+
"transformer.blocks.30.ffn.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 154 |
+
"transformer.blocks.30.ffn.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 155 |
+
"transformer.blocks.30.norm_1.weight": "pytorch_model-00008-of-00013.bin",
|
| 156 |
+
"transformer.blocks.30.norm_2.weight": "pytorch_model-00008-of-00013.bin",
|
| 157 |
+
"transformer.blocks.31.attn.Wqkv.weight": "pytorch_model-00008-of-00013.bin",
|
| 158 |
+
"transformer.blocks.31.attn.out_proj.weight": "pytorch_model-00008-of-00013.bin",
|
| 159 |
+
"transformer.blocks.31.ffn.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 160 |
+
"transformer.blocks.31.ffn.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 161 |
+
"transformer.blocks.31.norm_1.weight": "pytorch_model-00008-of-00013.bin",
|
| 162 |
+
"transformer.blocks.31.norm_2.weight": "pytorch_model-00008-of-00013.bin",
|
| 163 |
+
"transformer.blocks.32.attn.Wqkv.weight": "pytorch_model-00009-of-00013.bin",
|
| 164 |
+
"transformer.blocks.32.attn.out_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 165 |
+
"transformer.blocks.32.ffn.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 166 |
+
"transformer.blocks.32.ffn.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 167 |
+
"transformer.blocks.32.norm_1.weight": "pytorch_model-00009-of-00013.bin",
|
| 168 |
+
"transformer.blocks.32.norm_2.weight": "pytorch_model-00009-of-00013.bin",
|
| 169 |
+
"transformer.blocks.33.attn.Wqkv.weight": "pytorch_model-00009-of-00013.bin",
|
| 170 |
+
"transformer.blocks.33.attn.out_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 171 |
+
"transformer.blocks.33.ffn.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 172 |
+
"transformer.blocks.33.ffn.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 173 |
+
"transformer.blocks.33.norm_1.weight": "pytorch_model-00009-of-00013.bin",
|
| 174 |
+
"transformer.blocks.33.norm_2.weight": "pytorch_model-00009-of-00013.bin",
|
| 175 |
+
"transformer.blocks.34.attn.Wqkv.weight": "pytorch_model-00009-of-00013.bin",
|
| 176 |
+
"transformer.blocks.34.attn.out_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 177 |
+
"transformer.blocks.34.ffn.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 178 |
+
"transformer.blocks.34.ffn.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 179 |
+
"transformer.blocks.34.norm_1.weight": "pytorch_model-00009-of-00013.bin",
|
| 180 |
+
"transformer.blocks.34.norm_2.weight": "pytorch_model-00009-of-00013.bin",
|
| 181 |
+
"transformer.blocks.35.attn.Wqkv.weight": "pytorch_model-00009-of-00013.bin",
|
| 182 |
+
"transformer.blocks.35.attn.out_proj.weight": "pytorch_model-00009-of-00013.bin",
|
| 183 |
+
"transformer.blocks.35.ffn.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 184 |
+
"transformer.blocks.35.ffn.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 185 |
+
"transformer.blocks.35.norm_1.weight": "pytorch_model-00009-of-00013.bin",
|
| 186 |
+
"transformer.blocks.35.norm_2.weight": "pytorch_model-00009-of-00013.bin",
|
| 187 |
+
"transformer.blocks.36.attn.Wqkv.weight": "pytorch_model-00010-of-00013.bin",
|
| 188 |
+
"transformer.blocks.36.attn.out_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 189 |
+
"transformer.blocks.36.ffn.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 190 |
+
"transformer.blocks.36.ffn.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 191 |
+
"transformer.blocks.36.norm_1.weight": "pytorch_model-00010-of-00013.bin",
|
| 192 |
+
"transformer.blocks.36.norm_2.weight": "pytorch_model-00010-of-00013.bin",
|
| 193 |
+
"transformer.blocks.37.attn.Wqkv.weight": "pytorch_model-00010-of-00013.bin",
|
| 194 |
+
"transformer.blocks.37.attn.out_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 195 |
+
"transformer.blocks.37.ffn.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 196 |
+
"transformer.blocks.37.ffn.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 197 |
+
"transformer.blocks.37.norm_1.weight": "pytorch_model-00010-of-00013.bin",
|
| 198 |
+
"transformer.blocks.37.norm_2.weight": "pytorch_model-00010-of-00013.bin",
|
| 199 |
+
"transformer.blocks.38.attn.Wqkv.weight": "pytorch_model-00010-of-00013.bin",
|
| 200 |
+
"transformer.blocks.38.attn.out_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 201 |
+
"transformer.blocks.38.ffn.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 202 |
+
"transformer.blocks.38.ffn.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 203 |
+
"transformer.blocks.38.norm_1.weight": "pytorch_model-00010-of-00013.bin",
|
| 204 |
+
"transformer.blocks.38.norm_2.weight": "pytorch_model-00010-of-00013.bin",
|
| 205 |
+
"transformer.blocks.39.attn.Wqkv.weight": "pytorch_model-00010-of-00013.bin",
|
| 206 |
+
"transformer.blocks.39.attn.out_proj.weight": "pytorch_model-00010-of-00013.bin",
|
| 207 |
+
"transformer.blocks.39.ffn.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 208 |
+
"transformer.blocks.39.ffn.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 209 |
+
"transformer.blocks.39.norm_1.weight": "pytorch_model-00010-of-00013.bin",
|
| 210 |
+
"transformer.blocks.39.norm_2.weight": "pytorch_model-00010-of-00013.bin",
|
| 211 |
+
"transformer.blocks.4.attn.Wqkv.weight": "pytorch_model-00002-of-00013.bin",
|
| 212 |
+
"transformer.blocks.4.attn.out_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 213 |
+
"transformer.blocks.4.ffn.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 214 |
+
"transformer.blocks.4.ffn.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 215 |
+
"transformer.blocks.4.norm_1.weight": "pytorch_model-00002-of-00013.bin",
|
| 216 |
+
"transformer.blocks.4.norm_2.weight": "pytorch_model-00002-of-00013.bin",
|
| 217 |
+
"transformer.blocks.40.attn.Wqkv.weight": "pytorch_model-00011-of-00013.bin",
|
| 218 |
+
"transformer.blocks.40.attn.out_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 219 |
+
"transformer.blocks.40.ffn.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 220 |
+
"transformer.blocks.40.ffn.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 221 |
+
"transformer.blocks.40.norm_1.weight": "pytorch_model-00011-of-00013.bin",
|
| 222 |
+
"transformer.blocks.40.norm_2.weight": "pytorch_model-00011-of-00013.bin",
|
| 223 |
+
"transformer.blocks.41.attn.Wqkv.weight": "pytorch_model-00011-of-00013.bin",
|
| 224 |
+
"transformer.blocks.41.attn.out_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 225 |
+
"transformer.blocks.41.ffn.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 226 |
+
"transformer.blocks.41.ffn.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 227 |
+
"transformer.blocks.41.norm_1.weight": "pytorch_model-00011-of-00013.bin",
|
| 228 |
+
"transformer.blocks.41.norm_2.weight": "pytorch_model-00011-of-00013.bin",
|
| 229 |
+
"transformer.blocks.42.attn.Wqkv.weight": "pytorch_model-00011-of-00013.bin",
|
| 230 |
+
"transformer.blocks.42.attn.out_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 231 |
+
"transformer.blocks.42.ffn.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 232 |
+
"transformer.blocks.42.ffn.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 233 |
+
"transformer.blocks.42.norm_1.weight": "pytorch_model-00011-of-00013.bin",
|
| 234 |
+
"transformer.blocks.42.norm_2.weight": "pytorch_model-00011-of-00013.bin",
|
| 235 |
+
"transformer.blocks.43.attn.Wqkv.weight": "pytorch_model-00011-of-00013.bin",
|
| 236 |
+
"transformer.blocks.43.attn.out_proj.weight": "pytorch_model-00011-of-00013.bin",
|
| 237 |
+
"transformer.blocks.43.ffn.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 238 |
+
"transformer.blocks.43.ffn.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 239 |
+
"transformer.blocks.43.norm_1.weight": "pytorch_model-00011-of-00013.bin",
|
| 240 |
+
"transformer.blocks.43.norm_2.weight": "pytorch_model-00011-of-00013.bin",
|
| 241 |
+
"transformer.blocks.44.attn.Wqkv.weight": "pytorch_model-00012-of-00013.bin",
|
| 242 |
+
"transformer.blocks.44.attn.out_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 243 |
+
"transformer.blocks.44.ffn.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 244 |
+
"transformer.blocks.44.ffn.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 245 |
+
"transformer.blocks.44.norm_1.weight": "pytorch_model-00012-of-00013.bin",
|
| 246 |
+
"transformer.blocks.44.norm_2.weight": "pytorch_model-00012-of-00013.bin",
|
| 247 |
+
"transformer.blocks.45.attn.Wqkv.weight": "pytorch_model-00012-of-00013.bin",
|
| 248 |
+
"transformer.blocks.45.attn.out_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 249 |
+
"transformer.blocks.45.ffn.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 250 |
+
"transformer.blocks.45.ffn.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 251 |
+
"transformer.blocks.45.norm_1.weight": "pytorch_model-00012-of-00013.bin",
|
| 252 |
+
"transformer.blocks.45.norm_2.weight": "pytorch_model-00012-of-00013.bin",
|
| 253 |
+
"transformer.blocks.46.attn.Wqkv.weight": "pytorch_model-00012-of-00013.bin",
|
| 254 |
+
"transformer.blocks.46.attn.out_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 255 |
+
"transformer.blocks.46.ffn.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 256 |
+
"transformer.blocks.46.ffn.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 257 |
+
"transformer.blocks.46.norm_1.weight": "pytorch_model-00012-of-00013.bin",
|
| 258 |
+
"transformer.blocks.46.norm_2.weight": "pytorch_model-00012-of-00013.bin",
|
| 259 |
+
"transformer.blocks.47.attn.Wqkv.weight": "pytorch_model-00012-of-00013.bin",
|
| 260 |
+
"transformer.blocks.47.attn.out_proj.weight": "pytorch_model-00012-of-00013.bin",
|
| 261 |
+
"transformer.blocks.47.ffn.down_proj.weight": "pytorch_model-00013-of-00013.bin",
|
| 262 |
+
"transformer.blocks.47.ffn.up_proj.weight": "pytorch_model-00013-of-00013.bin",
|
| 263 |
+
"transformer.blocks.47.norm_1.weight": "pytorch_model-00012-of-00013.bin",
|
| 264 |
+
"transformer.blocks.47.norm_2.weight": "pytorch_model-00012-of-00013.bin",
|
| 265 |
+
"transformer.blocks.5.attn.Wqkv.weight": "pytorch_model-00002-of-00013.bin",
|
| 266 |
+
"transformer.blocks.5.attn.out_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 267 |
+
"transformer.blocks.5.ffn.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 268 |
+
"transformer.blocks.5.ffn.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 269 |
+
"transformer.blocks.5.norm_1.weight": "pytorch_model-00002-of-00013.bin",
|
| 270 |
+
"transformer.blocks.5.norm_2.weight": "pytorch_model-00002-of-00013.bin",
|
| 271 |
+
"transformer.blocks.6.attn.Wqkv.weight": "pytorch_model-00002-of-00013.bin",
|
| 272 |
+
"transformer.blocks.6.attn.out_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 273 |
+
"transformer.blocks.6.ffn.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 274 |
+
"transformer.blocks.6.ffn.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 275 |
+
"transformer.blocks.6.norm_1.weight": "pytorch_model-00002-of-00013.bin",
|
| 276 |
+
"transformer.blocks.6.norm_2.weight": "pytorch_model-00002-of-00013.bin",
|
| 277 |
+
"transformer.blocks.7.attn.Wqkv.weight": "pytorch_model-00002-of-00013.bin",
|
| 278 |
+
"transformer.blocks.7.attn.out_proj.weight": "pytorch_model-00002-of-00013.bin",
|
| 279 |
+
"transformer.blocks.7.ffn.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 280 |
+
"transformer.blocks.7.ffn.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 281 |
+
"transformer.blocks.7.norm_1.weight": "pytorch_model-00002-of-00013.bin",
|
| 282 |
+
"transformer.blocks.7.norm_2.weight": "pytorch_model-00002-of-00013.bin",
|
| 283 |
+
"transformer.blocks.8.attn.Wqkv.weight": "pytorch_model-00003-of-00013.bin",
|
| 284 |
+
"transformer.blocks.8.attn.out_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 285 |
+
"transformer.blocks.8.ffn.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 286 |
+
"transformer.blocks.8.ffn.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 287 |
+
"transformer.blocks.8.norm_1.weight": "pytorch_model-00003-of-00013.bin",
|
| 288 |
+
"transformer.blocks.8.norm_2.weight": "pytorch_model-00003-of-00013.bin",
|
| 289 |
+
"transformer.blocks.9.attn.Wqkv.weight": "pytorch_model-00003-of-00013.bin",
|
| 290 |
+
"transformer.blocks.9.attn.out_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 291 |
+
"transformer.blocks.9.ffn.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 292 |
+
"transformer.blocks.9.ffn.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
| 293 |
+
"transformer.blocks.9.norm_1.weight": "pytorch_model-00003-of-00013.bin",
|
| 294 |
+
"transformer.blocks.9.norm_2.weight": "pytorch_model-00003-of-00013.bin",
|
| 295 |
+
"transformer.norm_f.weight": "pytorch_model-00013-of-00013.bin",
|
| 296 |
+
"transformer.wte.weight": "pytorch_model-00001-of-00013.bin"
|
| 297 |
+
}
|
| 298 |
+
}
|