Hugging Face's logo

robertmyers
/
bpt-30b

Feature Extraction
Transformers
PyTorch
opt
Inference Endpoints
text-generation-inference
Model card Files Community
rob commited on
Commit
d2bef5f
•
1 Parent(s): b574055

v0.3

Browse files
Files changed (28) hide show
  1. config.json +29 -0
  2. convert.py +5 -0
  3. pytorch_model-00001-of-00025.bin +3 -0
  4. pytorch_model-00002-of-00025.bin +3 -0
  5. pytorch_model-00003-of-00025.bin +3 -0
  6. pytorch_model-00004-of-00025.bin +3 -0
  7. pytorch_model-00005-of-00025.bin +3 -0
  8. pytorch_model-00006-of-00025.bin +3 -0
  9. pytorch_model-00007-of-00025.bin +3 -0
  10. pytorch_model-00008-of-00025.bin +3 -0
  11. pytorch_model-00009-of-00025.bin +3 -0
  12. pytorch_model-00010-of-00025.bin +3 -0
  13. pytorch_model-00011-of-00025.bin +3 -0
  14. pytorch_model-00012-of-00025.bin +3 -0
  15. pytorch_model-00013-of-00025.bin +3 -0
  16. pytorch_model-00014-of-00025.bin +3 -0
  17. pytorch_model-00015-of-00025.bin +3 -0
  18. pytorch_model-00016-of-00025.bin +3 -0
  19. pytorch_model-00017-of-00025.bin +3 -0
  20. pytorch_model-00018-of-00025.bin +3 -0
  21. pytorch_model-00019-of-00025.bin +3 -0
  22. pytorch_model-00020-of-00025.bin +3 -0
  23. pytorch_model-00021-of-00025.bin +3 -0
  24. pytorch_model-00022-of-00025.bin +3 -0
  25. pytorch_model-00023-of-00025.bin +3 -0
  26. pytorch_model-00024-of-00025.bin +3 -0
  27. pytorch_model-00025-of-00025.bin +3 -0
  28. pytorch_model.bin.index.json +779 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTModel"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "eos_token_id": 2,
14
+ "ffn_dim": 28672,
15
+ "hidden_size": 7168,
16
+ "init_std": 0.02,
17
+ "layerdrop": 0.0,
18
+ "max_position_embeddings": 2048,
19
+ "model_type": "opt",
20
+ "num_attention_heads": 56,
21
+ "num_hidden_layers": 48,
22
+ "pad_token_id": 1,
23
+ "prefix": "</s>",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.20.1",
26
+ "use_cache": true,
27
+ "vocab_size": 50272,
28
+ "word_embed_proj_dim": 7168
29
+ }
convert.py ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ from transformers import AutoModel
2
+
3
+ model = AutoModel.from_pretrained("./")
4
+
5
+ model.save_pretrained('./', max_shard_size="5GB")
pytorch_model-00001-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeacd84d7d7cf8a2f9eef03a982c6742a2e0c25078894f78da76f552e0e6a8a2
3
+ size 4789122811
pytorch_model-00002-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a57ba0ebfec266dd5cf0d69e605dc9893f908a07df87bc41a90ffd7dffc6ea
3
+ size 4933257651
pytorch_model-00003-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4cf2092119fd7447fad241fbd405679989afe0e6a1039024bfdb2fac000b605
3
+ size 4933257651
pytorch_model-00004-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ec46d3f46d434aa70b1297d9edc9d66316b379a1fd9b9aaac382e310da7329
3
+ size 4933257651
pytorch_model-00005-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc9424308c034447279422dc65c4b12ffeac3b72ead08961c3f2832ab32e2e4
3
+ size 4933257651
pytorch_model-00006-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:507f75f03aa9a969cf43629bcdbabbe860df4987810bf967c322f34282e37670
3
+ size 4933257651
pytorch_model-00007-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6735f57cff63e80ae0437ae27ab6acc6f559671ae99c8c782f03b1db2573e565
3
+ size 4933257651
pytorch_model-00008-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e532962907ab37911c408cb2749f71c1265928e77e960b32caa06af6968d30ec
3
+ size 4933257651
pytorch_model-00009-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e3d32138515f892099dd45348a8c16d14e405753b629783591051c7deb3c79
3
+ size 4933257651
pytorch_model-00010-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4d1f76c469db0451964e223e87496e0314825a943932fa2e2c659200e7d361
3
+ size 4933257651
pytorch_model-00011-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f754747bbe971f7a8725188813606bc3c21afd98c0d8f5fa8e4702ce683641
3
+ size 4933257651
pytorch_model-00012-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad65e9cbd6e8f779ac790ed778a65961bf2eb91d417eccfb6007242a5ffa1af
3
+ size 4933257651
pytorch_model-00013-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a20b00d8afb8b06d5f88eb57ae16c9704018fd212e501d07d82242c2296391d
3
+ size 4933257651
pytorch_model-00014-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499d830fae60631fffca77985082b2f14e04dc6555a623cef1dd0b7f30243484
3
+ size 4933257651
pytorch_model-00015-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9be49852615ed9e7e84acce17bf3bee90c78cfb5b29387597b4336da76dd50
3
+ size 4933257651
pytorch_model-00016-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3312f355a380ddfc42585a409a3af870989e66407a2bc4d28f067a7b1a3238
3
+ size 4933257651
pytorch_model-00017-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9856a761d79526916dd6a7f4e535653666ac7397fd07df9868a96d72b231e8
3
+ size 4933257651
pytorch_model-00018-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c02b0584cbdf1ca6c8dc59fcdec5c5b84a8e517d0be5528c29b125a15ccf36ea
3
+ size 4933257651
pytorch_model-00019-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2561c2e6e3661ddcc7f54fb56271f931c30914f8388c33dbcaefab5d670ffb8b
3
+ size 4933257651
pytorch_model-00020-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe8a425c8714edd6480b6d6c6ab1f460e3dba35d8516d923be96e05413995e36
3
+ size 4933257651
pytorch_model-00021-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cafa20df5651e3ff2826799ea91202b9706d2775c78ae599aa08f252ced474c
3
+ size 4933257651
pytorch_model-00022-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6aa9bc1657e9fc143413bbc4b20b8c3bbf62c26a8df60aa687df5f73aec5fe
3
+ size 4933257651
pytorch_model-00023-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:195ac6d2b8a584622e88dc6907914238cd42527510489481c43a528d30daded6
3
+ size 4933257651
pytorch_model-00024-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3656c31220f41ed8a62b133db8db26a5d270a52f480984d4a7e6ac1b67d94566
3
+ size 4933257651
pytorch_model-00025-of-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa145577065b7fec8ccc3fd23f2c4c962429e9764824287516f8edbd4b20d3e2
3
+ size 1644370303
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,779 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 119898161152
4
+ },
5
+ "weight_map": {
6
+ "decoder.embed_positions.weight": "pytorch_model-00001-of-00025.bin",
7
+ "decoder.embed_tokens.weight": "pytorch_model-00001-of-00025.bin",
8
+ "decoder.final_layer_norm.bias": "pytorch_model-00001-of-00025.bin",
9
+ "decoder.final_layer_norm.weight": "pytorch_model-00001-of-00025.bin",
10
+ "decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00025.bin",
11
+ "decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00025.bin",
12
+ "decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00025.bin",
13
+ "decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00025.bin",
14
+ "decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00025.bin",
15
+ "decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00025.bin",
16
+ "decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00025.bin",
17
+ "decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00025.bin",
18
+ "decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00025.bin",
19
+ "decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00025.bin",
20
+ "decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00025.bin",
21
+ "decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00025.bin",
22
+ "decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00025.bin",
23
+ "decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00025.bin",
24
+ "decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00025.bin",
25
+ "decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00025.bin",
26
+ "decoder.layers.1.fc1.bias": "pytorch_model-00002-of-00025.bin",
27
+ "decoder.layers.1.fc1.weight": "pytorch_model-00002-of-00025.bin",
28
+ "decoder.layers.1.fc2.bias": "pytorch_model-00002-of-00025.bin",
29
+ "decoder.layers.1.fc2.weight": "pytorch_model-00002-of-00025.bin",
30
+ "decoder.layers.1.final_layer_norm.bias": "pytorch_model-00002-of-00025.bin",
31
+ "decoder.layers.1.final_layer_norm.weight": "pytorch_model-00002-of-00025.bin",
32
+ "decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00025.bin",
33
+ "decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00025.bin",
34
+ "decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00025.bin",
35
+ "decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00025.bin",
36
+ "decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00025.bin",
37
+ "decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00025.bin",
38
+ "decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00025.bin",
39
+ "decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00025.bin",
40
+ "decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00025.bin",
41
+ "decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00025.bin",
42
+ "decoder.layers.10.fc1.bias": "pytorch_model-00006-of-00025.bin",
43
+ "decoder.layers.10.fc1.weight": "pytorch_model-00006-of-00025.bin",
44
+ "decoder.layers.10.fc2.bias": "pytorch_model-00006-of-00025.bin",
45
+ "decoder.layers.10.fc2.weight": "pytorch_model-00006-of-00025.bin",
46
+ "decoder.layers.10.final_layer_norm.bias": "pytorch_model-00006-of-00025.bin",
47
+ "decoder.layers.10.final_layer_norm.weight": "pytorch_model-00006-of-00025.bin",
48
+ "decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00006-of-00025.bin",
49
+ "decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00006-of-00025.bin",
50
+ "decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00006-of-00025.bin",
51
+ "decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00006-of-00025.bin",
52
+ "decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00006-of-00025.bin",
53
+ "decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00006-of-00025.bin",
54
+ "decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00006-of-00025.bin",
55
+ "decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00006-of-00025.bin",
56
+ "decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00006-of-00025.bin",
57
+ "decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00006-of-00025.bin",
58
+ "decoder.layers.11.fc1.bias": "pytorch_model-00007-of-00025.bin",
59
+ "decoder.layers.11.fc1.weight": "pytorch_model-00007-of-00025.bin",
60
+ "decoder.layers.11.fc2.bias": "pytorch_model-00007-of-00025.bin",
61
+ "decoder.layers.11.fc2.weight": "pytorch_model-00007-of-00025.bin",
62
+ "decoder.layers.11.final_layer_norm.bias": "pytorch_model-00007-of-00025.bin",
63
+ "decoder.layers.11.final_layer_norm.weight": "pytorch_model-00007-of-00025.bin",
64
+ "decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00006-of-00025.bin",
65
+ "decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00025.bin",
66
+ "decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00006-of-00025.bin",
67
+ "decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00006-of-00025.bin",
68
+ "decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00006-of-00025.bin",
69
+ "decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00025.bin",
70
+ "decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00006-of-00025.bin",
71
+ "decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00025.bin",
72
+ "decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00006-of-00025.bin",
73
+ "decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00006-of-00025.bin",
74
+ "decoder.layers.12.fc1.bias": "pytorch_model-00007-of-00025.bin",
75
+ "decoder.layers.12.fc1.weight": "pytorch_model-00007-of-00025.bin",
76
+ "decoder.layers.12.fc2.bias": "pytorch_model-00007-of-00025.bin",
77
+ "decoder.layers.12.fc2.weight": "pytorch_model-00007-of-00025.bin",
78
+ "decoder.layers.12.final_layer_norm.bias": "pytorch_model-00007-of-00025.bin",
79
+ "decoder.layers.12.final_layer_norm.weight": "pytorch_model-00007-of-00025.bin",
80
+ "decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00007-of-00025.bin",
81
+ "decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00007-of-00025.bin",
82
+ "decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00007-of-00025.bin",
83
+ "decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00007-of-00025.bin",
84
+ "decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00007-of-00025.bin",
85
+ "decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00007-of-00025.bin",
86
+ "decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00007-of-00025.bin",
87
+ "decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00007-of-00025.bin",
88
+ "decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00007-of-00025.bin",
89
+ "decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00007-of-00025.bin",
90
+ "decoder.layers.13.fc1.bias": "pytorch_model-00008-of-00025.bin",
91
+ "decoder.layers.13.fc1.weight": "pytorch_model-00008-of-00025.bin",
92
+ "decoder.layers.13.fc2.bias": "pytorch_model-00008-of-00025.bin",
93
+ "decoder.layers.13.fc2.weight": "pytorch_model-00008-of-00025.bin",
94
+ "decoder.layers.13.final_layer_norm.bias": "pytorch_model-00008-of-00025.bin",
95
+ "decoder.layers.13.final_layer_norm.weight": "pytorch_model-00008-of-00025.bin",
96
+ "decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00007-of-00025.bin",
97
+ "decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00007-of-00025.bin",
98
+ "decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00007-of-00025.bin",
99
+ "decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00007-of-00025.bin",
100
+ "decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00007-of-00025.bin",
101
+ "decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00007-of-00025.bin",
102
+ "decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00007-of-00025.bin",
103
+ "decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00007-of-00025.bin",
104
+ "decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00007-of-00025.bin",
105
+ "decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00007-of-00025.bin",
106
+ "decoder.layers.14.fc1.bias": "pytorch_model-00008-of-00025.bin",
107
+ "decoder.layers.14.fc1.weight": "pytorch_model-00008-of-00025.bin",
108
+ "decoder.layers.14.fc2.bias": "pytorch_model-00008-of-00025.bin",
109
+ "decoder.layers.14.fc2.weight": "pytorch_model-00008-of-00025.bin",
110
+ "decoder.layers.14.final_layer_norm.bias": "pytorch_model-00008-of-00025.bin",
111
+ "decoder.layers.14.final_layer_norm.weight": "pytorch_model-00008-of-00025.bin",
112
+ "decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00008-of-00025.bin",
113
+ "decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00008-of-00025.bin",
114
+ "decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00008-of-00025.bin",
115
+ "decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00008-of-00025.bin",
116
+ "decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00008-of-00025.bin",
117
+ "decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00008-of-00025.bin",
118
+ "decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00008-of-00025.bin",
119
+ "decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00008-of-00025.bin",
120
+ "decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00008-of-00025.bin",
121
+ "decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00008-of-00025.bin",
122
+ "decoder.layers.15.fc1.bias": "pytorch_model-00009-of-00025.bin",
123
+ "decoder.layers.15.fc1.weight": "pytorch_model-00009-of-00025.bin",
124
+ "decoder.layers.15.fc2.bias": "pytorch_model-00009-of-00025.bin",
125
+ "decoder.layers.15.fc2.weight": "pytorch_model-00009-of-00025.bin",
126
+ "decoder.layers.15.final_layer_norm.bias": "pytorch_model-00009-of-00025.bin",
127
+ "decoder.layers.15.final_layer_norm.weight": "pytorch_model-00009-of-00025.bin",
128
+ "decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00008-of-00025.bin",
129
+ "decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00008-of-00025.bin",
130
+ "decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00008-of-00025.bin",
131
+ "decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00008-of-00025.bin",
132
+ "decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00008-of-00025.bin",
133
+ "decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00008-of-00025.bin",
134
+ "decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00008-of-00025.bin",
135
+ "decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00008-of-00025.bin",
136
+ "decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00008-of-00025.bin",
137
+ "decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00008-of-00025.bin",
138
+ "decoder.layers.16.fc1.bias": "pytorch_model-00009-of-00025.bin",
139
+ "decoder.layers.16.fc1.weight": "pytorch_model-00009-of-00025.bin",
140
+ "decoder.layers.16.fc2.bias": "pytorch_model-00009-of-00025.bin",
141
+ "decoder.layers.16.fc2.weight": "pytorch_model-00009-of-00025.bin",
142
+ "decoder.layers.16.final_layer_norm.bias": "pytorch_model-00009-of-00025.bin",
143
+ "decoder.layers.16.final_layer_norm.weight": "pytorch_model-00009-of-00025.bin",
144
+ "decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00009-of-00025.bin",
145
+ "decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00009-of-00025.bin",
146
+ "decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00009-of-00025.bin",
147
+ "decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00009-of-00025.bin",
148
+ "decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00009-of-00025.bin",
149
+ "decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00009-of-00025.bin",
150
+ "decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00009-of-00025.bin",
151
+ "decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00009-of-00025.bin",
152
+ "decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00009-of-00025.bin",
153
+ "decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00009-of-00025.bin",
154
+ "decoder.layers.17.fc1.bias": "pytorch_model-00010-of-00025.bin",
155
+ "decoder.layers.17.fc1.weight": "pytorch_model-00010-of-00025.bin",
156
+ "decoder.layers.17.fc2.bias": "pytorch_model-00010-of-00025.bin",
157
+ "decoder.layers.17.fc2.weight": "pytorch_model-00010-of-00025.bin",
158
+ "decoder.layers.17.final_layer_norm.bias": "pytorch_model-00010-of-00025.bin",
159
+ "decoder.layers.17.final_layer_norm.weight": "pytorch_model-00010-of-00025.bin",
160
+ "decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00009-of-00025.bin",
161
+ "decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00009-of-00025.bin",
162
+ "decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00009-of-00025.bin",
163
+ "decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00009-of-00025.bin",
164
+ "decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00009-of-00025.bin",
165
+ "decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00009-of-00025.bin",
166
+ "decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00009-of-00025.bin",
167
+ "decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00009-of-00025.bin",
168
+ "decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00009-of-00025.bin",
169
+ "decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00009-of-00025.bin",
170
+ "decoder.layers.18.fc1.bias": "pytorch_model-00010-of-00025.bin",
171
+ "decoder.layers.18.fc1.weight": "pytorch_model-00010-of-00025.bin",
172
+ "decoder.layers.18.fc2.bias": "pytorch_model-00010-of-00025.bin",
173
+ "decoder.layers.18.fc2.weight": "pytorch_model-00010-of-00025.bin",
174
+ "decoder.layers.18.final_layer_norm.bias": "pytorch_model-00010-of-00025.bin",
175
+ "decoder.layers.18.final_layer_norm.weight": "pytorch_model-00010-of-00025.bin",
176
+ "decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00010-of-00025.bin",
177
+ "decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00010-of-00025.bin",
178
+ "decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00010-of-00025.bin",
179
+ "decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00010-of-00025.bin",
180
+ "decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00010-of-00025.bin",
181
+ "decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00010-of-00025.bin",
182
+ "decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00010-of-00025.bin",
183
+ "decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00010-of-00025.bin",
184
+ "decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00010-of-00025.bin",
185
+ "decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00010-of-00025.bin",
186
+ "decoder.layers.19.fc1.bias": "pytorch_model-00011-of-00025.bin",
187
+ "decoder.layers.19.fc1.weight": "pytorch_model-00011-of-00025.bin",
188
+ "decoder.layers.19.fc2.bias": "pytorch_model-00011-of-00025.bin",
189
+ "decoder.layers.19.fc2.weight": "pytorch_model-00011-of-00025.bin",
190
+ "decoder.layers.19.final_layer_norm.bias": "pytorch_model-00011-of-00025.bin",
191
+ "decoder.layers.19.final_layer_norm.weight": "pytorch_model-00011-of-00025.bin",
192
+ "decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00010-of-00025.bin",
193
+ "decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00010-of-00025.bin",
194
+ "decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00010-of-00025.bin",
195
+ "decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00010-of-00025.bin",
196
+ "decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00010-of-00025.bin",
197
+ "decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00010-of-00025.bin",
198
+ "decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00010-of-00025.bin",
199
+ "decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00010-of-00025.bin",
200
+ "decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00010-of-00025.bin",
201
+ "decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00010-of-00025.bin",
202
+ "decoder.layers.2.fc1.bias": "pytorch_model-00002-of-00025.bin",
203
+ "decoder.layers.2.fc1.weight": "pytorch_model-00002-of-00025.bin",
204
+ "decoder.layers.2.fc2.bias": "pytorch_model-00002-of-00025.bin",
205
+ "decoder.layers.2.fc2.weight": "pytorch_model-00002-of-00025.bin",
206
+ "decoder.layers.2.final_layer_norm.bias": "pytorch_model-00002-of-00025.bin",
207
+ "decoder.layers.2.final_layer_norm.weight": "pytorch_model-00002-of-00025.bin",
208
+ "decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00025.bin",
209
+ "decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00025.bin",
210
+ "decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00025.bin",
211
+ "decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00025.bin",
212
+ "decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00025.bin",
213
+ "decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00025.bin",
214
+ "decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00025.bin",
215
+ "decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00025.bin",
216
+ "decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00002-of-00025.bin",
217
+ "decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00002-of-00025.bin",
218
+ "decoder.layers.20.fc1.bias": "pytorch_model-00011-of-00025.bin",
219
+ "decoder.layers.20.fc1.weight": "pytorch_model-00011-of-00025.bin",
220
+ "decoder.layers.20.fc2.bias": "pytorch_model-00011-of-00025.bin",
221
+ "decoder.layers.20.fc2.weight": "pytorch_model-00011-of-00025.bin",
222
+ "decoder.layers.20.final_layer_norm.bias": "pytorch_model-00011-of-00025.bin",
223
+ "decoder.layers.20.final_layer_norm.weight": "pytorch_model-00011-of-00025.bin",
224
+ "decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00011-of-00025.bin",
225
+ "decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00011-of-00025.bin",
226
+ "decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00011-of-00025.bin",
227
+ "decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00011-of-00025.bin",
228
+ "decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00011-of-00025.bin",
229
+ "decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00011-of-00025.bin",
230
+ "decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00011-of-00025.bin",
231
+ "decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00011-of-00025.bin",
232
+ "decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00011-of-00025.bin",
233
+ "decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00011-of-00025.bin",
234
+ "decoder.layers.21.fc1.bias": "pytorch_model-00012-of-00025.bin",
235
+ "decoder.layers.21.fc1.weight": "pytorch_model-00012-of-00025.bin",
236
+ "decoder.layers.21.fc2.bias": "pytorch_model-00012-of-00025.bin",
237
+ "decoder.layers.21.fc2.weight": "pytorch_model-00012-of-00025.bin",
238
+ "decoder.layers.21.final_layer_norm.bias": "pytorch_model-00012-of-00025.bin",
239
+ "decoder.layers.21.final_layer_norm.weight": "pytorch_model-00012-of-00025.bin",
240
+ "decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00011-of-00025.bin",
241
+ "decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00011-of-00025.bin",
242
+ "decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00011-of-00025.bin",
243
+ "decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00011-of-00025.bin",
244
+ "decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00011-of-00025.bin",
245
+ "decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00011-of-00025.bin",
246
+ "decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00011-of-00025.bin",
247
+ "decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00011-of-00025.bin",
248
+ "decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00011-of-00025.bin",
249
+ "decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00011-of-00025.bin",
250
+ "decoder.layers.22.fc1.bias": "pytorch_model-00012-of-00025.bin",
251
+ "decoder.layers.22.fc1.weight": "pytorch_model-00012-of-00025.bin",
252
+ "decoder.layers.22.fc2.bias": "pytorch_model-00012-of-00025.bin",
253
+ "decoder.layers.22.fc2.weight": "pytorch_model-00012-of-00025.bin",
254
+ "decoder.layers.22.final_layer_norm.bias": "pytorch_model-00012-of-00025.bin",
255
+ "decoder.layers.22.final_layer_norm.weight": "pytorch_model-00012-of-00025.bin",
256
+ "decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00012-of-00025.bin",
257
+ "decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00012-of-00025.bin",
258
+ "decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00012-of-00025.bin",
259
+ "decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00012-of-00025.bin",
260
+ "decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00012-of-00025.bin",
261
+ "decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00012-of-00025.bin",
262
+ "decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00012-of-00025.bin",
263
+ "decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00012-of-00025.bin",
264
+ "decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00012-of-00025.bin",
265
+ "decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00012-of-00025.bin",
266
+ "decoder.layers.23.fc1.bias": "pytorch_model-00013-of-00025.bin",
267
+ "decoder.layers.23.fc1.weight": "pytorch_model-00013-of-00025.bin",
268
+ "decoder.layers.23.fc2.bias": "pytorch_model-00013-of-00025.bin",
269
+ "decoder.layers.23.fc2.weight": "pytorch_model-00013-of-00025.bin",
270
+ "decoder.layers.23.final_layer_norm.bias": "pytorch_model-00013-of-00025.bin",
271
+ "decoder.layers.23.final_layer_norm.weight": "pytorch_model-00013-of-00025.bin",
272
+ "decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00012-of-00025.bin",
273
+ "decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00012-of-00025.bin",
274
+ "decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00012-of-00025.bin",
275
+ "decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00012-of-00025.bin",
276
+ "decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00012-of-00025.bin",
277
+ "decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00012-of-00025.bin",
278
+ "decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00012-of-00025.bin",
279
+ "decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00012-of-00025.bin",
280
+ "decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00012-of-00025.bin",
281
+ "decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00012-of-00025.bin",
282
+ "decoder.layers.24.fc1.bias": "pytorch_model-00013-of-00025.bin",
283
+ "decoder.layers.24.fc1.weight": "pytorch_model-00013-of-00025.bin",
284
+ "decoder.layers.24.fc2.bias": "pytorch_model-00013-of-00025.bin",
285
+ "decoder.layers.24.fc2.weight": "pytorch_model-00013-of-00025.bin",
286
+ "decoder.layers.24.final_layer_norm.bias": "pytorch_model-00013-of-00025.bin",
287
+ "decoder.layers.24.final_layer_norm.weight": "pytorch_model-00013-of-00025.bin",
288
+ "decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00013-of-00025.bin",
289
+ "decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00013-of-00025.bin",
290
+ "decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00013-of-00025.bin",
291
+ "decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00013-of-00025.bin",
292
+ "decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00013-of-00025.bin",
293
+ "decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00013-of-00025.bin",
294
+ "decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00013-of-00025.bin",
295
+ "decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00013-of-00025.bin",
296
+ "decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00013-of-00025.bin",
297
+ "decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00013-of-00025.bin",
298
+ "decoder.layers.25.fc1.bias": "pytorch_model-00014-of-00025.bin",
299
+ "decoder.layers.25.fc1.weight": "pytorch_model-00014-of-00025.bin",
300
+ "decoder.layers.25.fc2.bias": "pytorch_model-00014-of-00025.bin",
301
+ "decoder.layers.25.fc2.weight": "pytorch_model-00014-of-00025.bin",
302
+ "decoder.layers.25.final_layer_norm.bias": "pytorch_model-00014-of-00025.bin",
303
+ "decoder.layers.25.final_layer_norm.weight": "pytorch_model-00014-of-00025.bin",
304
+ "decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00013-of-00025.bin",
305
+ "decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00013-of-00025.bin",
306
+ "decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00013-of-00025.bin",
307
+ "decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00013-of-00025.bin",
308
+ "decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00013-of-00025.bin",
309
+ "decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00013-of-00025.bin",
310
+ "decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00013-of-00025.bin",
311
+ "decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00013-of-00025.bin",
312
+ "decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00013-of-00025.bin",
313
+ "decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00013-of-00025.bin",
314
+ "decoder.layers.26.fc1.bias": "pytorch_model-00014-of-00025.bin",
315
+ "decoder.layers.26.fc1.weight": "pytorch_model-00014-of-00025.bin",
316
+ "decoder.layers.26.fc2.bias": "pytorch_model-00014-of-00025.bin",
317
+ "decoder.layers.26.fc2.weight": "pytorch_model-00014-of-00025.bin",
318
+ "decoder.layers.26.final_layer_norm.bias": "pytorch_model-00014-of-00025.bin",
319
+ "decoder.layers.26.final_layer_norm.weight": "pytorch_model-00014-of-00025.bin",
320
+ "decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00014-of-00025.bin",
321
+ "decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00014-of-00025.bin",
322
+ "decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00014-of-00025.bin",
323
+ "decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00014-of-00025.bin",
324
+ "decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00014-of-00025.bin",
325
+ "decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00014-of-00025.bin",
326
+ "decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00014-of-00025.bin",
327
+ "decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00014-of-00025.bin",
328
+ "decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00014-of-00025.bin",
329
+ "decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00014-of-00025.bin",
330
+ "decoder.layers.27.fc1.bias": "pytorch_model-00015-of-00025.bin",
331
+ "decoder.layers.27.fc1.weight": "pytorch_model-00015-of-00025.bin",
332
+ "decoder.layers.27.fc2.bias": "pytorch_model-00015-of-00025.bin",
333
+ "decoder.layers.27.fc2.weight": "pytorch_model-00015-of-00025.bin",
334
+ "decoder.layers.27.final_layer_norm.bias": "pytorch_model-00015-of-00025.bin",
335
+ "decoder.layers.27.final_layer_norm.weight": "pytorch_model-00015-of-00025.bin",
336
+ "decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00014-of-00025.bin",
337
+ "decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00014-of-00025.bin",
338
+ "decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00014-of-00025.bin",
339
+ "decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00014-of-00025.bin",
340
+ "decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00014-of-00025.bin",
341
+ "decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00014-of-00025.bin",
342
+ "decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00014-of-00025.bin",
343
+ "decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00014-of-00025.bin",
344
+ "decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00014-of-00025.bin",
345
+ "decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00014-of-00025.bin",
346
+ "decoder.layers.28.fc1.bias": "pytorch_model-00015-of-00025.bin",
347
+ "decoder.layers.28.fc1.weight": "pytorch_model-00015-of-00025.bin",
348
+ "decoder.layers.28.fc2.bias": "pytorch_model-00015-of-00025.bin",
349
+ "decoder.layers.28.fc2.weight": "pytorch_model-00015-of-00025.bin",
350
+ "decoder.layers.28.final_layer_norm.bias": "pytorch_model-00015-of-00025.bin",
351
+ "decoder.layers.28.final_layer_norm.weight": "pytorch_model-00015-of-00025.bin",
352
+ "decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00015-of-00025.bin",
353
+ "decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00015-of-00025.bin",
354
+ "decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00015-of-00025.bin",
355
+ "decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00015-of-00025.bin",
356
+ "decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00015-of-00025.bin",
357
+ "decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00015-of-00025.bin",
358
+ "decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00015-of-00025.bin",
359
+ "decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00015-of-00025.bin",
360
+ "decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00015-of-00025.bin",
361
+ "decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00015-of-00025.bin",
362
+ "decoder.layers.29.fc1.bias": "pytorch_model-00016-of-00025.bin",
363
+ "decoder.layers.29.fc1.weight": "pytorch_model-00016-of-00025.bin",
364
+ "decoder.layers.29.fc2.bias": "pytorch_model-00016-of-00025.bin",
365
+ "decoder.layers.29.fc2.weight": "pytorch_model-00016-of-00025.bin",
366
+ "decoder.layers.29.final_layer_norm.bias": "pytorch_model-00016-of-00025.bin",
367
+ "decoder.layers.29.final_layer_norm.weight": "pytorch_model-00016-of-00025.bin",
368
+ "decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00015-of-00025.bin",
369
+ "decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00015-of-00025.bin",
370
+ "decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00015-of-00025.bin",
371
+ "decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00015-of-00025.bin",
372
+ "decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00015-of-00025.bin",
373
+ "decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00015-of-00025.bin",
374
+ "decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00015-of-00025.bin",
375
+ "decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00015-of-00025.bin",
376
+ "decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00015-of-00025.bin",
377
+ "decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00015-of-00025.bin",
378
+ "decoder.layers.3.fc1.bias": "pytorch_model-00003-of-00025.bin",
379
+ "decoder.layers.3.fc1.weight": "pytorch_model-00003-of-00025.bin",
380
+ "decoder.layers.3.fc2.bias": "pytorch_model-00003-of-00025.bin",
381
+ "decoder.layers.3.fc2.weight": "pytorch_model-00003-of-00025.bin",
382
+ "decoder.layers.3.final_layer_norm.bias": "pytorch_model-00003-of-00025.bin",
383
+ "decoder.layers.3.final_layer_norm.weight": "pytorch_model-00003-of-00025.bin",
384
+ "decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00025.bin",
385
+ "decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00025.bin",
386
+ "decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00025.bin",
387
+ "decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00025.bin",
388
+ "decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00025.bin",
389
+ "decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00025.bin",
390
+ "decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00025.bin",
391
+ "decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00025.bin",
392
+ "decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00002-of-00025.bin",
393
+ "decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00002-of-00025.bin",
394
+ "decoder.layers.30.fc1.bias": "pytorch_model-00016-of-00025.bin",
395
+ "decoder.layers.30.fc1.weight": "pytorch_model-00016-of-00025.bin",
396
+ "decoder.layers.30.fc2.bias": "pytorch_model-00016-of-00025.bin",
397
+ "decoder.layers.30.fc2.weight": "pytorch_model-00016-of-00025.bin",
398
+ "decoder.layers.30.final_layer_norm.bias": "pytorch_model-00016-of-00025.bin",
399
+ "decoder.layers.30.final_layer_norm.weight": "pytorch_model-00016-of-00025.bin",
400
+ "decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00016-of-00025.bin",
401
+ "decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00016-of-00025.bin",
402
+ "decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00016-of-00025.bin",
403
+ "decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00016-of-00025.bin",
404
+ "decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00016-of-00025.bin",
405
+ "decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00016-of-00025.bin",
406
+ "decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00016-of-00025.bin",
407
+ "decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00016-of-00025.bin",
408
+ "decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00016-of-00025.bin",
409
+ "decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00016-of-00025.bin",
410
+ "decoder.layers.31.fc1.bias": "pytorch_model-00017-of-00025.bin",
411
+ "decoder.layers.31.fc1.weight": "pytorch_model-00017-of-00025.bin",
412
+ "decoder.layers.31.fc2.bias": "pytorch_model-00017-of-00025.bin",
413
+ "decoder.layers.31.fc2.weight": "pytorch_model-00017-of-00025.bin",
414
+ "decoder.layers.31.final_layer_norm.bias": "pytorch_model-00017-of-00025.bin",
415
+ "decoder.layers.31.final_layer_norm.weight": "pytorch_model-00017-of-00025.bin",
416
+ "decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00016-of-00025.bin",
417
+ "decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00016-of-00025.bin",
418
+ "decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00016-of-00025.bin",
419
+ "decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00016-of-00025.bin",
420
+ "decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00016-of-00025.bin",
421
+ "decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00016-of-00025.bin",
422
+ "decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00016-of-00025.bin",
423
+ "decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00016-of-00025.bin",
424
+ "decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00016-of-00025.bin",
425
+ "decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00016-of-00025.bin",
426
+ "decoder.layers.32.fc1.bias": "pytorch_model-00017-of-00025.bin",
427
+ "decoder.layers.32.fc1.weight": "pytorch_model-00017-of-00025.bin",
428
+ "decoder.layers.32.fc2.bias": "pytorch_model-00017-of-00025.bin",
429
+ "decoder.layers.32.fc2.weight": "pytorch_model-00017-of-00025.bin",
430
+ "decoder.layers.32.final_layer_norm.bias": "pytorch_model-00017-of-00025.bin",
431
+ "decoder.layers.32.final_layer_norm.weight": "pytorch_model-00017-of-00025.bin",
432
+ "decoder.layers.32.self_attn.k_proj.bias": "pytorch_model-00017-of-00025.bin",
433
+ "decoder.layers.32.self_attn.k_proj.weight": "pytorch_model-00017-of-00025.bin",
434
+ "decoder.layers.32.self_attn.out_proj.bias": "pytorch_model-00017-of-00025.bin",
435
+ "decoder.layers.32.self_attn.out_proj.weight": "pytorch_model-00017-of-00025.bin",
436
+ "decoder.layers.32.self_attn.q_proj.bias": "pytorch_model-00017-of-00025.bin",
437
+ "decoder.layers.32.self_attn.q_proj.weight": "pytorch_model-00017-of-00025.bin",
438
+ "decoder.layers.32.self_attn.v_proj.bias": "pytorch_model-00017-of-00025.bin",
439
+ "decoder.layers.32.self_attn.v_proj.weight": "pytorch_model-00017-of-00025.bin",
440
+ "decoder.layers.32.self_attn_layer_norm.bias": "pytorch_model-00017-of-00025.bin",
441
+ "decoder.layers.32.self_attn_layer_norm.weight": "pytorch_model-00017-of-00025.bin",
442
+ "decoder.layers.33.fc1.bias": "pytorch_model-00018-of-00025.bin",
443
+ "decoder.layers.33.fc1.weight": "pytorch_model-00018-of-00025.bin",
444
+ "decoder.layers.33.fc2.bias": "pytorch_model-00018-of-00025.bin",
445
+ "decoder.layers.33.fc2.weight": "pytorch_model-00018-of-00025.bin",
446
+ "decoder.layers.33.final_layer_norm.bias": "pytorch_model-00018-of-00025.bin",
447
+ "decoder.layers.33.final_layer_norm.weight": "pytorch_model-00018-of-00025.bin",
448
+ "decoder.layers.33.self_attn.k_proj.bias": "pytorch_model-00017-of-00025.bin",
449
+ "decoder.layers.33.self_attn.k_proj.weight": "pytorch_model-00017-of-00025.bin",
450
+ "decoder.layers.33.self_attn.out_proj.bias": "pytorch_model-00017-of-00025.bin",
451
+ "decoder.layers.33.self_attn.out_proj.weight": "pytorch_model-00017-of-00025.bin",
452
+ "decoder.layers.33.self_attn.q_proj.bias": "pytorch_model-00017-of-00025.bin",
453
+ "decoder.layers.33.self_attn.q_proj.weight": "pytorch_model-00017-of-00025.bin",
454
+ "decoder.layers.33.self_attn.v_proj.bias": "pytorch_model-00017-of-00025.bin",
455
+ "decoder.layers.33.self_attn.v_proj.weight": "pytorch_model-00017-of-00025.bin",
456
+ "decoder.layers.33.self_attn_layer_norm.bias": "pytorch_model-00017-of-00025.bin",
457
+ "decoder.layers.33.self_attn_layer_norm.weight": "pytorch_model-00017-of-00025.bin",
458
+ "decoder.layers.34.fc1.bias": "pytorch_model-00018-of-00025.bin",
459
+ "decoder.layers.34.fc1.weight": "pytorch_model-00018-of-00025.bin",
460
+ "decoder.layers.34.fc2.bias": "pytorch_model-00018-of-00025.bin",
461
+ "decoder.layers.34.fc2.weight": "pytorch_model-00018-of-00025.bin",
462
+ "decoder.layers.34.final_layer_norm.bias": "pytorch_model-00018-of-00025.bin",
463
+ "decoder.layers.34.final_layer_norm.weight": "pytorch_model-00018-of-00025.bin",
464
+ "decoder.layers.34.self_attn.k_proj.bias": "pytorch_model-00018-of-00025.bin",
465
+ "decoder.layers.34.self_attn.k_proj.weight": "pytorch_model-00018-of-00025.bin",
466
+ "decoder.layers.34.self_attn.out_proj.bias": "pytorch_model-00018-of-00025.bin",
467
+ "decoder.layers.34.self_attn.out_proj.weight": "pytorch_model-00018-of-00025.bin",
468
+ "decoder.layers.34.self_attn.q_proj.bias": "pytorch_model-00018-of-00025.bin",
469
+ "decoder.layers.34.self_attn.q_proj.weight": "pytorch_model-00018-of-00025.bin",
470
+ "decoder.layers.34.self_attn.v_proj.bias": "pytorch_model-00018-of-00025.bin",
471
+ "decoder.layers.34.self_attn.v_proj.weight": "pytorch_model-00018-of-00025.bin",
472
+ "decoder.layers.34.self_attn_layer_norm.bias": "pytorch_model-00018-of-00025.bin",
473
+ "decoder.layers.34.self_attn_layer_norm.weight": "pytorch_model-00018-of-00025.bin",
474
+ "decoder.layers.35.fc1.bias": "pytorch_model-00019-of-00025.bin",
475
+ "decoder.layers.35.fc1.weight": "pytorch_model-00019-of-00025.bin",
476
+ "decoder.layers.35.fc2.bias": "pytorch_model-00019-of-00025.bin",
477
+ "decoder.layers.35.fc2.weight": "pytorch_model-00019-of-00025.bin",
478
+ "decoder.layers.35.final_layer_norm.bias": "pytorch_model-00019-of-00025.bin",
479
+ "decoder.layers.35.final_layer_norm.weight": "pytorch_model-00019-of-00025.bin",
480
+ "decoder.layers.35.self_attn.k_proj.bias": "pytorch_model-00018-of-00025.bin",
481
+ "decoder.layers.35.self_attn.k_proj.weight": "pytorch_model-00018-of-00025.bin",
482
+ "decoder.layers.35.self_attn.out_proj.bias": "pytorch_model-00018-of-00025.bin",
483
+ "decoder.layers.35.self_attn.out_proj.weight": "pytorch_model-00018-of-00025.bin",
484
+ "decoder.layers.35.self_attn.q_proj.bias": "pytorch_model-00018-of-00025.bin",
485
+ "decoder.layers.35.self_attn.q_proj.weight": "pytorch_model-00018-of-00025.bin",
486
+ "decoder.layers.35.self_attn.v_proj.bias": "pytorch_model-00018-of-00025.bin",
487
+ "decoder.layers.35.self_attn.v_proj.weight": "pytorch_model-00018-of-00025.bin",
488
+ "decoder.layers.35.self_attn_layer_norm.bias": "pytorch_model-00018-of-00025.bin",
489
+ "decoder.layers.35.self_attn_layer_norm.weight": "pytorch_model-00018-of-00025.bin",
490
+ "decoder.layers.36.fc1.bias": "pytorch_model-00019-of-00025.bin",
491
+ "decoder.layers.36.fc1.weight": "pytorch_model-00019-of-00025.bin",
492
+ "decoder.layers.36.fc2.bias": "pytorch_model-00019-of-00025.bin",
493
+ "decoder.layers.36.fc2.weight": "pytorch_model-00019-of-00025.bin",
494
+ "decoder.layers.36.final_layer_norm.bias": "pytorch_model-00019-of-00025.bin",
495
+ "decoder.layers.36.final_layer_norm.weight": "pytorch_model-00019-of-00025.bin",
496
+ "decoder.layers.36.self_attn.k_proj.bias": "pytorch_model-00019-of-00025.bin",
497
+ "decoder.layers.36.self_attn.k_proj.weight": "pytorch_model-00019-of-00025.bin",
498
+ "decoder.layers.36.self_attn.out_proj.bias": "pytorch_model-00019-of-00025.bin",
499
+ "decoder.layers.36.self_attn.out_proj.weight": "pytorch_model-00019-of-00025.bin",
500
+ "decoder.layers.36.self_attn.q_proj.bias": "pytorch_model-00019-of-00025.bin",
501
+ "decoder.layers.36.self_attn.q_proj.weight": "pytorch_model-00019-of-00025.bin",
502
+ "decoder.layers.36.self_attn.v_proj.bias": "pytorch_model-00019-of-00025.bin",
503
+ "decoder.layers.36.self_attn.v_proj.weight": "pytorch_model-00019-of-00025.bin",
504
+ "decoder.layers.36.self_attn_layer_norm.bias": "pytorch_model-00019-of-00025.bin",
505
+ "decoder.layers.36.self_attn_layer_norm.weight": "pytorch_model-00019-of-00025.bin",
506
+ "decoder.layers.37.fc1.bias": "pytorch_model-00020-of-00025.bin",
507
+ "decoder.layers.37.fc1.weight": "pytorch_model-00020-of-00025.bin",
508
+ "decoder.layers.37.fc2.bias": "pytorch_model-00020-of-00025.bin",
509
+ "decoder.layers.37.fc2.weight": "pytorch_model-00020-of-00025.bin",
510
+ "decoder.layers.37.final_layer_norm.bias": "pytorch_model-00020-of-00025.bin",
511
+ "decoder.layers.37.final_layer_norm.weight": "pytorch_model-00020-of-00025.bin",
512
+ "decoder.layers.37.self_attn.k_proj.bias": "pytorch_model-00019-of-00025.bin",
513
+ "decoder.layers.37.self_attn.k_proj.weight": "pytorch_model-00019-of-00025.bin",
514
+ "decoder.layers.37.self_attn.out_proj.bias": "pytorch_model-00019-of-00025.bin",
515
+ "decoder.layers.37.self_attn.out_proj.weight": "pytorch_model-00019-of-00025.bin",
516
+ "decoder.layers.37.self_attn.q_proj.bias": "pytorch_model-00019-of-00025.bin",
517
+ "decoder.layers.37.self_attn.q_proj.weight": "pytorch_model-00019-of-00025.bin",
518
+ "decoder.layers.37.self_attn.v_proj.bias": "pytorch_model-00019-of-00025.bin",
519
+ "decoder.layers.37.self_attn.v_proj.weight": "pytorch_model-00019-of-00025.bin",
520
+ "decoder.layers.37.self_attn_layer_norm.bias": "pytorch_model-00019-of-00025.bin",
521
+ "decoder.layers.37.self_attn_layer_norm.weight": "pytorch_model-00019-of-00025.bin",
522
+ "decoder.layers.38.fc1.bias": "pytorch_model-00020-of-00025.bin",
523
+ "decoder.layers.38.fc1.weight": "pytorch_model-00020-of-00025.bin",
524
+ "decoder.layers.38.fc2.bias": "pytorch_model-00020-of-00025.bin",
525
+ "decoder.layers.38.fc2.weight": "pytorch_model-00020-of-00025.bin",
526
+ "decoder.layers.38.final_layer_norm.bias": "pytorch_model-00020-of-00025.bin",
527
+ "decoder.layers.38.final_layer_norm.weight": "pytorch_model-00020-of-00025.bin",
528
+ "decoder.layers.38.self_attn.k_proj.bias": "pytorch_model-00020-of-00025.bin",
529
+ "decoder.layers.38.self_attn.k_proj.weight": "pytorch_model-00020-of-00025.bin",
530
+ "decoder.layers.38.self_attn.out_proj.bias": "pytorch_model-00020-of-00025.bin",
531
+ "decoder.layers.38.self_attn.out_proj.weight": "pytorch_model-00020-of-00025.bin",
532
+ "decoder.layers.38.self_attn.q_proj.bias": "pytorch_model-00020-of-00025.bin",
533
+ "decoder.layers.38.self_attn.q_proj.weight": "pytorch_model-00020-of-00025.bin",
534
+ "decoder.layers.38.self_attn.v_proj.bias": "pytorch_model-00020-of-00025.bin",
535
+ "decoder.layers.38.self_attn.v_proj.weight": "pytorch_model-00020-of-00025.bin",
536
+ "decoder.layers.38.self_attn_layer_norm.bias": "pytorch_model-00020-of-00025.bin",
537
+ "decoder.layers.38.self_attn_layer_norm.weight": "pytorch_model-00020-of-00025.bin",
538
+ "decoder.layers.39.fc1.bias": "pytorch_model-00021-of-00025.bin",
539
+ "decoder.layers.39.fc1.weight": "pytorch_model-00021-of-00025.bin",
540
+ "decoder.layers.39.fc2.bias": "pytorch_model-00021-of-00025.bin",
541
+ "decoder.layers.39.fc2.weight": "pytorch_model-00021-of-00025.bin",
542
+ "decoder.layers.39.final_layer_norm.bias": "pytorch_model-00021-of-00025.bin",
543
+ "decoder.layers.39.final_layer_norm.weight": "pytorch_model-00021-of-00025.bin",
544
+ "decoder.layers.39.self_attn.k_proj.bias": "pytorch_model-00020-of-00025.bin",
545
+ "decoder.layers.39.self_attn.k_proj.weight": "pytorch_model-00020-of-00025.bin",
546
+ "decoder.layers.39.self_attn.out_proj.bias": "pytorch_model-00020-of-00025.bin",
547
+ "decoder.layers.39.self_attn.out_proj.weight": "pytorch_model-00020-of-00025.bin",
548
+ "decoder.layers.39.self_attn.q_proj.bias": "pytorch_model-00020-of-00025.bin",
549
+ "decoder.layers.39.self_attn.q_proj.weight": "pytorch_model-00020-of-00025.bin",
550
+ "decoder.layers.39.self_attn.v_proj.bias": "pytorch_model-00020-of-00025.bin",
551
+ "decoder.layers.39.self_attn.v_proj.weight": "pytorch_model-00020-of-00025.bin",
552
+ "decoder.layers.39.self_attn_layer_norm.bias": "pytorch_model-00020-of-00025.bin",
553
+ "decoder.layers.39.self_attn_layer_norm.weight": "pytorch_model-00020-of-00025.bin",
554
+ "decoder.layers.4.fc1.bias": "pytorch_model-00003-of-00025.bin",
555
+ "decoder.layers.4.fc1.weight": "pytorch_model-00003-of-00025.bin",
556
+ "decoder.layers.4.fc2.bias": "pytorch_model-00003-of-00025.bin",
557
+ "decoder.layers.4.fc2.weight": "pytorch_model-00003-of-00025.bin",
558
+ "decoder.layers.4.final_layer_norm.bias": "pytorch_model-00003-of-00025.bin",
559
+ "decoder.layers.4.final_layer_norm.weight": "pytorch_model-00003-of-00025.bin",
560
+ "decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00025.bin",
561
+ "decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00025.bin",
562
+ "decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00025.bin",
563
+ "decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00025.bin",
564
+ "decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00025.bin",
565
+ "decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00025.bin",
566
+ "decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00025.bin",
567
+ "decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00025.bin",
568
+ "decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00003-of-00025.bin",
569
+ "decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00003-of-00025.bin",
570
+ "decoder.layers.40.fc1.bias": "pytorch_model-00021-of-00025.bin",
571
+ "decoder.layers.40.fc1.weight": "pytorch_model-00021-of-00025.bin",
572
+ "decoder.layers.40.fc2.bias": "pytorch_model-00021-of-00025.bin",
573
+ "decoder.layers.40.fc2.weight": "pytorch_model-00021-of-00025.bin",
574
+ "decoder.layers.40.final_layer_norm.bias": "pytorch_model-00021-of-00025.bin",
575
+ "decoder.layers.40.final_layer_norm.weight": "pytorch_model-00021-of-00025.bin",
576
+ "decoder.layers.40.self_attn.k_proj.bias": "pytorch_model-00021-of-00025.bin",
577
+ "decoder.layers.40.self_attn.k_proj.weight": "pytorch_model-00021-of-00025.bin",
578
+ "decoder.layers.40.self_attn.out_proj.bias": "pytorch_model-00021-of-00025.bin",
579
+ "decoder.layers.40.self_attn.out_proj.weight": "pytorch_model-00021-of-00025.bin",
580
+ "decoder.layers.40.self_attn.q_proj.bias": "pytorch_model-00021-of-00025.bin",
581
+ "decoder.layers.40.self_attn.q_proj.weight": "pytorch_model-00021-of-00025.bin",
582
+ "decoder.layers.40.self_attn.v_proj.bias": "pytorch_model-00021-of-00025.bin",
583
+ "decoder.layers.40.self_attn.v_proj.weight": "pytorch_model-00021-of-00025.bin",
584
+ "decoder.layers.40.self_attn_layer_norm.bias": "pytorch_model-00021-of-00025.bin",
585
+ "decoder.layers.40.self_attn_layer_norm.weight": "pytorch_model-00021-of-00025.bin",
586
+ "decoder.layers.41.fc1.bias": "pytorch_model-00022-of-00025.bin",
587
+ "decoder.layers.41.fc1.weight": "pytorch_model-00022-of-00025.bin",
588
+ "decoder.layers.41.fc2.bias": "pytorch_model-00022-of-00025.bin",
589
+ "decoder.layers.41.fc2.weight": "pytorch_model-00022-of-00025.bin",
590
+ "decoder.layers.41.final_layer_norm.bias": "pytorch_model-00022-of-00025.bin",
591
+ "decoder.layers.41.final_layer_norm.weight": "pytorch_model-00022-of-00025.bin",
592
+ "decoder.layers.41.self_attn.k_proj.bias": "pytorch_model-00021-of-00025.bin",
593
+ "decoder.layers.41.self_attn.k_proj.weight": "pytorch_model-00021-of-00025.bin",
594
+ "decoder.layers.41.self_attn.out_proj.bias": "pytorch_model-00021-of-00025.bin",
595
+ "decoder.layers.41.self_attn.out_proj.weight": "pytorch_model-00021-of-00025.bin",
596
+ "decoder.layers.41.self_attn.q_proj.bias": "pytorch_model-00021-of-00025.bin",
597
+ "decoder.layers.41.self_attn.q_proj.weight": "pytorch_model-00021-of-00025.bin",
598
+ "decoder.layers.41.self_attn.v_proj.bias": "pytorch_model-00021-of-00025.bin",
599
+ "decoder.layers.41.self_attn.v_proj.weight": "pytorch_model-00021-of-00025.bin",
600
+ "decoder.layers.41.self_attn_layer_norm.bias": "pytorch_model-00021-of-00025.bin",
601
+ "decoder.layers.41.self_attn_layer_norm.weight": "pytorch_model-00021-of-00025.bin",
602
+ "decoder.layers.42.fc1.bias": "pytorch_model-00022-of-00025.bin",
603
+ "decoder.layers.42.fc1.weight": "pytorch_model-00022-of-00025.bin",
604
+ "decoder.layers.42.fc2.bias": "pytorch_model-00022-of-00025.bin",
605
+ "decoder.layers.42.fc2.weight": "pytorch_model-00022-of-00025.bin",
606
+ "decoder.layers.42.final_layer_norm.bias": "pytorch_model-00022-of-00025.bin",
607
+ "decoder.layers.42.final_layer_norm.weight": "pytorch_model-00022-of-00025.bin",
608
+ "decoder.layers.42.self_attn.k_proj.bias": "pytorch_model-00022-of-00025.bin",
609
+ "decoder.layers.42.self_attn.k_proj.weight": "pytorch_model-00022-of-00025.bin",
610
+ "decoder.layers.42.self_attn.out_proj.bias": "pytorch_model-00022-of-00025.bin",
611
+ "decoder.layers.42.self_attn.out_proj.weight": "pytorch_model-00022-of-00025.bin",
612
+ "decoder.layers.42.self_attn.q_proj.bias": "pytorch_model-00022-of-00025.bin",
613
+ "decoder.layers.42.self_attn.q_proj.weight": "pytorch_model-00022-of-00025.bin",
614
+ "decoder.layers.42.self_attn.v_proj.bias": "pytorch_model-00022-of-00025.bin",
615
+ "decoder.layers.42.self_attn.v_proj.weight": "pytorch_model-00022-of-00025.bin",
616
+ "decoder.layers.42.self_attn_layer_norm.bias": "pytorch_model-00022-of-00025.bin",
617
+ "decoder.layers.42.self_attn_layer_norm.weight": "pytorch_model-00022-of-00025.bin",
618
+ "decoder.layers.43.fc1.bias": "pytorch_model-00023-of-00025.bin",
619
+ "decoder.layers.43.fc1.weight": "pytorch_model-00023-of-00025.bin",
620
+ "decoder.layers.43.fc2.bias": "pytorch_model-00023-of-00025.bin",
621
+ "decoder.layers.43.fc2.weight": "pytorch_model-00023-of-00025.bin",
622
+ "decoder.layers.43.final_layer_norm.bias": "pytorch_model-00023-of-00025.bin",
623
+ "decoder.layers.43.final_layer_norm.weight": "pytorch_model-00023-of-00025.bin",
624
+ "decoder.layers.43.self_attn.k_proj.bias": "pytorch_model-00022-of-00025.bin",
625
+ "decoder.layers.43.self_attn.k_proj.weight": "pytorch_model-00022-of-00025.bin",
626
+ "decoder.layers.43.self_attn.out_proj.bias": "pytorch_model-00022-of-00025.bin",
627
+ "decoder.layers.43.self_attn.out_proj.weight": "pytorch_model-00022-of-00025.bin",
628
+ "decoder.layers.43.self_attn.q_proj.bias": "pytorch_model-00022-of-00025.bin",
629
+ "decoder.layers.43.self_attn.q_proj.weight": "pytorch_model-00022-of-00025.bin",
630
+ "decoder.layers.43.self_attn.v_proj.bias": "pytorch_model-00022-of-00025.bin",
631
+ "decoder.layers.43.self_attn.v_proj.weight": "pytorch_model-00022-of-00025.bin",
632
+ "decoder.layers.43.self_attn_layer_norm.bias": "pytorch_model-00022-of-00025.bin",
633
+ "decoder.layers.43.self_attn_layer_norm.weight": "pytorch_model-00022-of-00025.bin",
634
+ "decoder.layers.44.fc1.bias": "pytorch_model-00023-of-00025.bin",
635
+ "decoder.layers.44.fc1.weight": "pytorch_model-00023-of-00025.bin",
636
+ "decoder.layers.44.fc2.bias": "pytorch_model-00023-of-00025.bin",
637
+ "decoder.layers.44.fc2.weight": "pytorch_model-00023-of-00025.bin",
638
+ "decoder.layers.44.final_layer_norm.bias": "pytorch_model-00023-of-00025.bin",
639
+ "decoder.layers.44.final_layer_norm.weight": "pytorch_model-00023-of-00025.bin",
640
+ "decoder.layers.44.self_attn.k_proj.bias": "pytorch_model-00023-of-00025.bin",
641
+ "decoder.layers.44.self_attn.k_proj.weight": "pytorch_model-00023-of-00025.bin",
642
+ "decoder.layers.44.self_attn.out_proj.bias": "pytorch_model-00023-of-00025.bin",
643
+ "decoder.layers.44.self_attn.out_proj.weight": "pytorch_model-00023-of-00025.bin",
644
+ "decoder.layers.44.self_attn.q_proj.bias": "pytorch_model-00023-of-00025.bin",
645
+ "decoder.layers.44.self_attn.q_proj.weight": "pytorch_model-00023-of-00025.bin",
646
+ "decoder.layers.44.self_attn.v_proj.bias": "pytorch_model-00023-of-00025.bin",
647
+ "decoder.layers.44.self_attn.v_proj.weight": "pytorch_model-00023-of-00025.bin",
648
+ "decoder.layers.44.self_attn_layer_norm.bias": "pytorch_model-00023-of-00025.bin",
649
+ "decoder.layers.44.self_attn_layer_norm.weight": "pytorch_model-00023-of-00025.bin",
650
+ "decoder.layers.45.fc1.bias": "pytorch_model-00024-of-00025.bin",
651
+ "decoder.layers.45.fc1.weight": "pytorch_model-00024-of-00025.bin",
652
+ "decoder.layers.45.fc2.bias": "pytorch_model-00024-of-00025.bin",
653
+ "decoder.layers.45.fc2.weight": "pytorch_model-00024-of-00025.bin",
654
+ "decoder.layers.45.final_layer_norm.bias": "pytorch_model-00024-of-00025.bin",
655
+ "decoder.layers.45.final_layer_norm.weight": "pytorch_model-00024-of-00025.bin",
656
+ "decoder.layers.45.self_attn.k_proj.bias": "pytorch_model-00023-of-00025.bin",
657
+ "decoder.layers.45.self_attn.k_proj.weight": "pytorch_model-00023-of-00025.bin",
658
+ "decoder.layers.45.self_attn.out_proj.bias": "pytorch_model-00023-of-00025.bin",
659
+ "decoder.layers.45.self_attn.out_proj.weight": "pytorch_model-00023-of-00025.bin",
660
+ "decoder.layers.45.self_attn.q_proj.bias": "pytorch_model-00023-of-00025.bin",
661
+ "decoder.layers.45.self_attn.q_proj.weight": "pytorch_model-00023-of-00025.bin",
662
+ "decoder.layers.45.self_attn.v_proj.bias": "pytorch_model-00023-of-00025.bin",
663
+ "decoder.layers.45.self_attn.v_proj.weight": "pytorch_model-00023-of-00025.bin",
664
+ "decoder.layers.45.self_attn_layer_norm.bias": "pytorch_model-00023-of-00025.bin",
665
+ "decoder.layers.45.self_attn_layer_norm.weight": "pytorch_model-00023-of-00025.bin",
666
+ "decoder.layers.46.fc1.bias": "pytorch_model-00024-of-00025.bin",
667
+ "decoder.layers.46.fc1.weight": "pytorch_model-00024-of-00025.bin",
668
+ "decoder.layers.46.fc2.bias": "pytorch_model-00024-of-00025.bin",
669
+ "decoder.layers.46.fc2.weight": "pytorch_model-00024-of-00025.bin",
670
+ "decoder.layers.46.final_layer_norm.bias": "pytorch_model-00024-of-00025.bin",
671
+ "decoder.layers.46.final_layer_norm.weight": "pytorch_model-00024-of-00025.bin",
672
+ "decoder.layers.46.self_attn.k_proj.bias": "pytorch_model-00024-of-00025.bin",
673
+ "decoder.layers.46.self_attn.k_proj.weight": "pytorch_model-00024-of-00025.bin",
674
+ "decoder.layers.46.self_attn.out_proj.bias": "pytorch_model-00024-of-00025.bin",
675
+ "decoder.layers.46.self_attn.out_proj.weight": "pytorch_model-00024-of-00025.bin",
676
+ "decoder.layers.46.self_attn.q_proj.bias": "pytorch_model-00024-of-00025.bin",
677
+ "decoder.layers.46.self_attn.q_proj.weight": "pytorch_model-00024-of-00025.bin",
678
+ "decoder.layers.46.self_attn.v_proj.bias": "pytorch_model-00024-of-00025.bin",
679
+ "decoder.layers.46.self_attn.v_proj.weight": "pytorch_model-00024-of-00025.bin",
680
+ "decoder.layers.46.self_attn_layer_norm.bias": "pytorch_model-00024-of-00025.bin",
681
+ "decoder.layers.46.self_attn_layer_norm.weight": "pytorch_model-00024-of-00025.bin",
682
+ "decoder.layers.47.fc1.bias": "pytorch_model-00025-of-00025.bin",
683
+ "decoder.layers.47.fc1.weight": "pytorch_model-00025-of-00025.bin",
684
+ "decoder.layers.47.fc2.bias": "pytorch_model-00025-of-00025.bin",
685
+ "decoder.layers.47.fc2.weight": "pytorch_model-00025-of-00025.bin",
686
+ "decoder.layers.47.final_layer_norm.bias": "pytorch_model-00025-of-00025.bin",
687
+ "decoder.layers.47.final_layer_norm.weight": "pytorch_model-00025-of-00025.bin",
688
+ "decoder.layers.47.self_attn.k_proj.bias": "pytorch_model-00024-of-00025.bin",
689
+ "decoder.layers.47.self_attn.k_proj.weight": "pytorch_model-00024-of-00025.bin",
690
+ "decoder.layers.47.self_attn.out_proj.bias": "pytorch_model-00024-of-00025.bin",
691
+ "decoder.layers.47.self_attn.out_proj.weight": "pytorch_model-00024-of-00025.bin",
692
+ "decoder.layers.47.self_attn.q_proj.bias": "pytorch_model-00024-of-00025.bin",
693
+ "decoder.layers.47.self_attn.q_proj.weight": "pytorch_model-00024-of-00025.bin",
694
+ "decoder.layers.47.self_attn.v_proj.bias": "pytorch_model-00024-of-00025.bin",
695
+ "decoder.layers.47.self_attn.v_proj.weight": "pytorch_model-00024-of-00025.bin",
696
+ "decoder.layers.47.self_attn_layer_norm.bias": "pytorch_model-00024-of-00025.bin",
697
+ "decoder.layers.47.self_attn_layer_norm.weight": "pytorch_model-00024-of-00025.bin",
698
+ "decoder.layers.5.fc1.bias": "pytorch_model-00004-of-00025.bin",
699
+ "decoder.layers.5.fc1.weight": "pytorch_model-00004-of-00025.bin",
700
+ "decoder.layers.5.fc2.bias": "pytorch_model-00004-of-00025.bin",
701
+ "decoder.layers.5.fc2.weight": "pytorch_model-00004-of-00025.bin",
702
+ "decoder.layers.5.final_layer_norm.bias": "pytorch_model-00004-of-00025.bin",
703
+ "decoder.layers.5.final_layer_norm.weight": "pytorch_model-00004-of-00025.bin",
704
+ "decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00025.bin",
705
+ "decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00025.bin",
706
+ "decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00025.bin",
707
+ "decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00025.bin",
708
+ "decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00025.bin",
709
+ "decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00025.bin",
710
+ "decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00025.bin",
711
+ "decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00025.bin",
712
+ "decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00003-of-00025.bin",
713
+ "decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00003-of-00025.bin",
714
+ "decoder.layers.6.fc1.bias": "pytorch_model-00004-of-00025.bin",
715
+ "decoder.layers.6.fc1.weight": "pytorch_model-00004-of-00025.bin",
716
+ "decoder.layers.6.fc2.bias": "pytorch_model-00004-of-00025.bin",
717
+ "decoder.layers.6.fc2.weight": "pytorch_model-00004-of-00025.bin",
718
+ "decoder.layers.6.final_layer_norm.bias": "pytorch_model-00004-of-00025.bin",
719
+ "decoder.layers.6.final_layer_norm.weight": "pytorch_model-00004-of-00025.bin",
720
+ "decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00004-of-00025.bin",
721
+ "decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00025.bin",
722
+ "decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00004-of-00025.bin",
723
+ "decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00004-of-00025.bin",
724
+ "decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00004-of-00025.bin",
725
+ "decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00025.bin",
726
+ "decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00004-of-00025.bin",
727
+ "decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00025.bin",
728
+ "decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00004-of-00025.bin",
729
+ "decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00004-of-00025.bin",
730
+ "decoder.layers.7.fc1.bias": "pytorch_model-00005-of-00025.bin",
731
+ "decoder.layers.7.fc1.weight": "pytorch_model-00005-of-00025.bin",
732
+ "decoder.layers.7.fc2.bias": "pytorch_model-00005-of-00025.bin",
733
+ "decoder.layers.7.fc2.weight": "pytorch_model-00005-of-00025.bin",
734
+ "decoder.layers.7.final_layer_norm.bias": "pytorch_model-00005-of-00025.bin",
735
+ "decoder.layers.7.final_layer_norm.weight": "pytorch_model-00005-of-00025.bin",
736
+ "decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00004-of-00025.bin",
737
+ "decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00025.bin",
738
+ "decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00004-of-00025.bin",
739
+ "decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00004-of-00025.bin",
740
+ "decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00004-of-00025.bin",
741
+ "decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00025.bin",
742
+ "decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00004-of-00025.bin",
743
+ "decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00025.bin",
744
+ "decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00004-of-00025.bin",
745
+ "decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00004-of-00025.bin",
746
+ "decoder.layers.8.fc1.bias": "pytorch_model-00005-of-00025.bin",
747
+ "decoder.layers.8.fc1.weight": "pytorch_model-00005-of-00025.bin",
748
+ "decoder.layers.8.fc2.bias": "pytorch_model-00005-of-00025.bin",
749
+ "decoder.layers.8.fc2.weight": "pytorch_model-00005-of-00025.bin",
750
+ "decoder.layers.8.final_layer_norm.bias": "pytorch_model-00005-of-00025.bin",
751
+ "decoder.layers.8.final_layer_norm.weight": "pytorch_model-00005-of-00025.bin",
752
+ "decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00005-of-00025.bin",
753
+ "decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00005-of-00025.bin",
754
+ "decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00005-of-00025.bin",
755
+ "decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00005-of-00025.bin",
756
+ "decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00005-of-00025.bin",
757
+ "decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00005-of-00025.bin",
758
+ "decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00005-of-00025.bin",
759
+ "decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00005-of-00025.bin",
760
+ "decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00005-of-00025.bin",
761
+ "decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00005-of-00025.bin",
762
+ "decoder.layers.9.fc1.bias": "pytorch_model-00006-of-00025.bin",
763
+ "decoder.layers.9.fc1.weight": "pytorch_model-00006-of-00025.bin",
764
+ "decoder.layers.9.fc2.bias": "pytorch_model-00006-of-00025.bin",
765
+ "decoder.layers.9.fc2.weight": "pytorch_model-00006-of-00025.bin",
766
+ "decoder.layers.9.final_layer_norm.bias": "pytorch_model-00006-of-00025.bin",
767
+ "decoder.layers.9.final_layer_norm.weight": "pytorch_model-00006-of-00025.bin",
768
+ "decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00005-of-00025.bin",
769
+ "decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00025.bin",
770
+ "decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00005-of-00025.bin",
771
+ "decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00005-of-00025.bin",
772
+ "decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00005-of-00025.bin",
773
+ "decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00025.bin",
774
+ "decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00005-of-00025.bin",
775
+ "decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00025.bin",
776
+ "decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00005-of-00025.bin",
777
+ "decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00005-of-00025.bin"
778
+ }
779
+ }