Hugging Face's logo

EleutherAI
/
gpt-neox-20b

Text Generation
Transformers
PyTorch
Safetensors
English
gpt_neox
causal-lm
text-generation-inference
Inference Endpoints
Model card Files Community
25
stellaathena olivierdehaene HF staff commited on
Commit
007b5cb
•
1 Parent(s): 3523781

Adding `safetensors` variant of this model (#13)

Browse files

- Adding `safetensors` variant of this model (a7da0652a69c0d33d6bd860fa98508c066e651f4)


Co-authored-by: Olivier Dehaene <[email protected]>

Files changed (48) hide show
  1. .gitattributes +46 -0
  2. model-00001-of-00046.safetensors +3 -0
  3. model-00002-of-00046.safetensors +3 -0
  4. model-00003-of-00046.safetensors +3 -0
  5. model-00004-of-00046.safetensors +3 -0
  6. model-00005-of-00046.safetensors +3 -0
  7. model-00006-of-00046.safetensors +3 -0
  8. model-00007-of-00046.safetensors +3 -0
  9. model-00008-of-00046.safetensors +3 -0
  10. model-00009-of-00046.safetensors +3 -0
  11. model-00010-of-00046.safetensors +3 -0
  12. model-00011-of-00046.safetensors +3 -0
  13. model-00012-of-00046.safetensors +3 -0
  14. model-00013-of-00046.safetensors +3 -0
  15. model-00014-of-00046.safetensors +3 -0
  16. model-00015-of-00046.safetensors +3 -0
  17. model-00016-of-00046.safetensors +3 -0
  18. model-00017-of-00046.safetensors +3 -0
  19. model-00018-of-00046.safetensors +3 -0
  20. model-00019-of-00046.safetensors +3 -0
  21. model-00020-of-00046.safetensors +3 -0
  22. model-00021-of-00046.safetensors +3 -0
  23. model-00022-of-00046.safetensors +3 -0
  24. model-00023-of-00046.safetensors +3 -0
  25. model-00024-of-00046.safetensors +3 -0
  26. model-00025-of-00046.safetensors +3 -0
  27. model-00026-of-00046.safetensors +3 -0
  28. model-00027-of-00046.safetensors +3 -0
  29. model-00028-of-00046.safetensors +3 -0
  30. model-00029-of-00046.safetensors +3 -0
  31. model-00030-of-00046.safetensors +3 -0
  32. model-00031-of-00046.safetensors +3 -0
  33. model-00032-of-00046.safetensors +3 -0
  34. model-00033-of-00046.safetensors +3 -0
  35. model-00034-of-00046.safetensors +3 -0
  36. model-00035-of-00046.safetensors +3 -0
  37. model-00036-of-00046.safetensors +3 -0
  38. model-00037-of-00046.safetensors +3 -0
  39. model-00038-of-00046.safetensors +3 -0
  40. model-00039-of-00046.safetensors +3 -0
  41. model-00040-of-00046.safetensors +3 -0
  42. model-00041-of-00046.safetensors +3 -0
  43. model-00042-of-00046.safetensors +3 -0
  44. model-00043-of-00046.safetensors +3 -0
  45. model-00044-of-00046.safetensors +3 -0
  46. model-00045-of-00046.safetensors +3 -0
  47. model-00046-of-00046.safetensors +3 -0
  48. model.safetensors.index.json +671 -0
.gitattributes CHANGED
@@ -26,3 +26,49 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
26
  *.zip filter=lfs diff=lfs merge=lfs -text
27
  *.zstandard filter=lfs diff=lfs merge=lfs -text
28
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  *.zip filter=lfs diff=lfs merge=lfs -text
27
  *.zstandard filter=lfs diff=lfs merge=lfs -text
28
  *tfevents* filter=lfs diff=lfs merge=lfs -text
29
+ model-00010-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
30
+ model-00012-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
31
+ model-00015-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
32
+ model-00031-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
33
+ model-00029-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
34
+ model-00005-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
35
+ model-00037-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
36
+ model-00025-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
37
+ model-00027-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ model-00018-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
39
+ model-00044-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
40
+ model-00021-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
41
+ model-00017-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
42
+ model-00023-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
43
+ model-00040-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
44
+ model-00034-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
45
+ model-00046-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
46
+ model-00022-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
47
+ model-00033-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
48
+ model-00035-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
49
+ model-00002-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
50
+ model-00020-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
51
+ model-00026-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
52
+ model-00042-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
53
+ model-00013-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
54
+ model-00019-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
55
+ model-00008-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
56
+ model-00016-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
57
+ model-00014-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
58
+ model-00030-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
59
+ model-00028-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
60
+ model-00045-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
61
+ model-00024-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
62
+ model-00009-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
63
+ model-00036-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
64
+ model-00039-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
65
+ model-00006-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
66
+ model-00011-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
67
+ model-00007-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
68
+ model-00032-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
69
+ model-00041-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
70
+ model-00001-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
71
+ model-00043-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
72
+ model-00038-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
73
+ model-00004-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
74
+ model-00003-of-00046.safetensors filter=lfs diff=lfs merge=lfs -text
model-00001-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a2fc18ab96693eac02e833bf7373c78fcd4b12ae5f01651e9b75fd854dbcf1
3
+ size 925992334
model-00002-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb326a6fc1840dabfa3a30c57c306f89f57e5f0917a351c8d045e79539a6bb1b
3
+ size 910325486
model-00003-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95effe91209682aff2935db6cbb84ff1d64083b468699cc2ccdc164343582814
3
+ size 910325486
model-00004-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ac9466a9c1f3f954a678c5dc3dea2c883f54ae199fa70e5e221b1fe8c93dca
3
+ size 910325486
model-00005-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6613a915480e7fa00853c0ead97ff165073e9098eb28cdb3b0f52a5b30e3ac
3
+ size 910325486
model-00006-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cddbc8a13a7797a58f4e34a23276cb67ea3b411e6f6a0d571809ae323ab64985
3
+ size 910325486
model-00007-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097ac87764658bb0d2a1fc15424b7bcfbb039a5f6fa7f8dd6c31dd7e5f41609c
3
+ size 910325486
model-00008-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47ec7084cea6c8444ece2ad3baf03907b708c4b203d69aac285b6888834b14c8
3
+ size 910325486
model-00009-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01fdfabdb95d133ebbb1c604a03c30b8da1e69cfe0b6f7a0a6d4efa9ca3fc7a6
3
+ size 910325486
model-00010-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd3060ee2fbf970c8076a7e3280fbe02face84a973231011b617a7c95fb454a
3
+ size 910325486
model-00011-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd1a57dfabafd6a99705ece673301e6bb682f8e01e67034e52f497f1bc5b922e
3
+ size 910325491
model-00012-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85e72751dffa26e549de07479f6df2e3bbbd3de0ec744d3868ba6b0944057fe
3
+ size 910325501
model-00013-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:179423abc852fc930d0e6e2e794afd930960146214a3e28eb6442a055b915c95
3
+ size 910325501
model-00014-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dcc73bab4328c069f81436d1b5d900fc40420a27b13a484b0a3be817ffebdb2
3
+ size 910325501
model-00015-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df6529dfc089ea0f68cae3de062d83e412fc88d0b2ff824acfdb1bbcc570cb7
3
+ size 910325501
model-00016-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b1a3727b4800e51ddadbfbcbc77a62d6e6ddf47479106220270ca2e3008b793
3
+ size 910325501
model-00017-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5860f6ef89f5377550a0b547ecbc6612a615d181869d47fa184ec37f84b98e5f
3
+ size 910325501
model-00018-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d8b2094835d04506fa677dfb0d1d44c8af7104613717e8a24a69330f9979bc
3
+ size 910325501
model-00019-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06cd4a326cd54d565d2d17385d927eaadad57ffaaad0dcb963379132c5006e70
3
+ size 910325501
model-00020-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d192a4a220ba4bfe5d76fb681e28901a51164f59fdc9b84e3ad32c6678426c8
3
+ size 910325501
model-00021-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c8388deca5726d11c07810017aaf178d36454df375b45fd4ab6db20b0fcddc
3
+ size 910325501
model-00022-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd821f6f05df926a12879560660278d6e32d33b84adf289f7f72a2daebfee9a2
3
+ size 910325501
model-00023-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ac34fc590ebb62ea8374213873e8ecf1209687c279742f993357045704a05d
3
+ size 910325501
model-00024-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:506b22eebc595a64dc2da52758130f63e544c75cdf93a5060c380bdf224b8043
3
+ size 910325501
model-00025-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed055bbd7cd16e384b0ac9499192df8c33dee0109d503008d813ea077209d2f
3
+ size 910325501
model-00026-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25b6edd4b9d50c7e6ea35b38ce52fa9e8849ebdafb92d718726549aad431a71
3
+ size 910325501
model-00027-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9c0cf13f55dc236b4cd5039df3eb49c521e371074ccaa901a71ce7462ec4a6
3
+ size 910325501
model-00028-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793c91ab150af3a3c6176abbc3cd54a20137527f150bcdce6b6f01e1b27bd1f4
3
+ size 910325501
model-00029-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b1bcc99c22204bcf88b44fc212cdc9aa3de8138b3ef767cc1342620e4cea15
3
+ size 910325501
model-00030-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf342ac358e299f553f15b35fb6f30a657c5e697237d60bd79c917d885e7bbda
3
+ size 910325501
model-00031-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713341d88368000cfab1ebe8ab47121f4e79bd67418cfd3f4372110547678473
3
+ size 910325501
model-00032-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d26e8d4c5811c42d8172eb0624f941b747fdfa22add2f42c6d2eb93be137db43
3
+ size 910325501
model-00033-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757880b98e70fb826e27333f580194ccd85e99e40b19c993cfb1c4a6c2b21b3c
3
+ size 910325501
model-00034-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808c213e7e6e0bcae8cf4d6ddde3bcec96f7f73f57d7958ba05e0b06dbc7a0ab
3
+ size 910325501
model-00035-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11113c4a99b37f86bd8054a23b922710350ffb6ef9969921be87647c554812dc
3
+ size 910325501
model-00036-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5649b0348af719ae73c2c7312d1abcc5e1924805a69dd300a7f1d54bc04654
3
+ size 910325501
model-00037-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaf2e9c33501b372547d5da9a60fedf689f225b22091ec1856b94337f3226784
3
+ size 910325501
model-00038-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a815e95afd13b93ab246b32d6fe75af72fb35a52336f47961d027a135e8266e7
3
+ size 910325501
model-00039-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbcc362c5028e969f2d0907d183130e47cfe269dbe8815a60751140a8e1d4cca
3
+ size 910325501
model-00040-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a24e2b3a2befb91162ac54e201dd49a8acd282980c8b8997753a6cf1fe17c27
3
+ size 910325501
model-00041-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e26c19107464eeb3acf15578402c4d51c56df2721c939ad09f5b4465356fc3
3
+ size 910325501
model-00042-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7172ff989ec0219a3d764d55751c9551e64d4d3451ea285988725aae7bb96da3
3
+ size 910325501
model-00043-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0266b06e509f6b6566961d8131b9cea3fe4706ade362d8cafef4c8d532efc064
3
+ size 910325501
model-00044-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae11994b83961d8e5f634e4ca93561f66ea8db1a36151501de3a03ddf9a86df
3
+ size 910325501
model-00045-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ae0ac80dd9dd8a5dbef6000ae7051fe9609557c1262bf31585896ba06d7325
3
+ size 604066469
model-00046-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01499aa37fdaace2112368ea52cccd955d6a0efbf4f4a2934129f789db79a87f
3
+ size 619708541
model.safetensors.index.json ADDED
@@ -0,0 +1,671 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 41293685880
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00046-of-00046.safetensors",
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00046.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00045-of-00046.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00045-of-00046.safetensors",
10
+ "gpt_neox.layers.0.attention.bias": "model-00001-of-00046.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00046.safetensors",
12
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00046.safetensors",
13
+ "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00046.safetensors",
14
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00046.safetensors",
15
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00046.safetensors",
16
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00046.safetensors",
17
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00046.safetensors",
18
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00046.safetensors",
19
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00002-of-00046.safetensors",
20
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00002-of-00046.safetensors",
21
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00002-of-00046.safetensors",
22
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00002-of-00046.safetensors",
23
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00046.safetensors",
24
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00046.safetensors",
25
+ "gpt_neox.layers.1.attention.bias": "model-00002-of-00046.safetensors",
26
+ "gpt_neox.layers.1.attention.dense.bias": "model-00002-of-00046.safetensors",
27
+ "gpt_neox.layers.1.attention.dense.weight": "model-00002-of-00046.safetensors",
28
+ "gpt_neox.layers.1.attention.masked_bias": "model-00002-of-00046.safetensors",
29
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00002-of-00046.safetensors",
30
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00002-of-00046.safetensors",
31
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00002-of-00046.safetensors",
32
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00002-of-00046.safetensors",
33
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00002-of-00046.safetensors",
34
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00003-of-00046.safetensors",
35
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00003-of-00046.safetensors",
36
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00003-of-00046.safetensors",
37
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00003-of-00046.safetensors",
38
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00002-of-00046.safetensors",
39
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00002-of-00046.safetensors",
40
+ "gpt_neox.layers.10.attention.bias": "model-00011-of-00046.safetensors",
41
+ "gpt_neox.layers.10.attention.dense.bias": "model-00011-of-00046.safetensors",
42
+ "gpt_neox.layers.10.attention.dense.weight": "model-00011-of-00046.safetensors",
43
+ "gpt_neox.layers.10.attention.masked_bias": "model-00011-of-00046.safetensors",
44
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00011-of-00046.safetensors",
45
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00011-of-00046.safetensors",
46
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00011-of-00046.safetensors",
47
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00011-of-00046.safetensors",
48
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00011-of-00046.safetensors",
49
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00012-of-00046.safetensors",
50
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00012-of-00046.safetensors",
51
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00012-of-00046.safetensors",
52
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00012-of-00046.safetensors",
53
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00011-of-00046.safetensors",
54
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00011-of-00046.safetensors",
55
+ "gpt_neox.layers.11.attention.bias": "model-00012-of-00046.safetensors",
56
+ "gpt_neox.layers.11.attention.dense.bias": "model-00012-of-00046.safetensors",
57
+ "gpt_neox.layers.11.attention.dense.weight": "model-00012-of-00046.safetensors",
58
+ "gpt_neox.layers.11.attention.masked_bias": "model-00012-of-00046.safetensors",
59
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00012-of-00046.safetensors",
60
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00012-of-00046.safetensors",
61
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00012-of-00046.safetensors",
62
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00012-of-00046.safetensors",
63
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00012-of-00046.safetensors",
64
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00013-of-00046.safetensors",
65
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00013-of-00046.safetensors",
66
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00013-of-00046.safetensors",
67
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00013-of-00046.safetensors",
68
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00012-of-00046.safetensors",
69
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00012-of-00046.safetensors",
70
+ "gpt_neox.layers.12.attention.bias": "model-00013-of-00046.safetensors",
71
+ "gpt_neox.layers.12.attention.dense.bias": "model-00013-of-00046.safetensors",
72
+ "gpt_neox.layers.12.attention.dense.weight": "model-00013-of-00046.safetensors",
73
+ "gpt_neox.layers.12.attention.masked_bias": "model-00013-of-00046.safetensors",
74
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00013-of-00046.safetensors",
75
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00013-of-00046.safetensors",
76
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00013-of-00046.safetensors",
77
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00013-of-00046.safetensors",
78
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00013-of-00046.safetensors",
79
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00014-of-00046.safetensors",
80
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00014-of-00046.safetensors",
81
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00014-of-00046.safetensors",
82
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00014-of-00046.safetensors",
83
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00013-of-00046.safetensors",
84
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00013-of-00046.safetensors",
85
+ "gpt_neox.layers.13.attention.bias": "model-00014-of-00046.safetensors",
86
+ "gpt_neox.layers.13.attention.dense.bias": "model-00014-of-00046.safetensors",
87
+ "gpt_neox.layers.13.attention.dense.weight": "model-00014-of-00046.safetensors",
88
+ "gpt_neox.layers.13.attention.masked_bias": "model-00014-of-00046.safetensors",
89
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00014-of-00046.safetensors",
90
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00014-of-00046.safetensors",
91
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00014-of-00046.safetensors",
92
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00014-of-00046.safetensors",
93
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00014-of-00046.safetensors",
94
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00015-of-00046.safetensors",
95
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00015-of-00046.safetensors",
96
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00015-of-00046.safetensors",
97
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00015-of-00046.safetensors",
98
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00014-of-00046.safetensors",
99
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00014-of-00046.safetensors",
100
+ "gpt_neox.layers.14.attention.bias": "model-00015-of-00046.safetensors",
101
+ "gpt_neox.layers.14.attention.dense.bias": "model-00015-of-00046.safetensors",
102
+ "gpt_neox.layers.14.attention.dense.weight": "model-00015-of-00046.safetensors",
103
+ "gpt_neox.layers.14.attention.masked_bias": "model-00015-of-00046.safetensors",
104
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00015-of-00046.safetensors",
105
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00015-of-00046.safetensors",
106
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00015-of-00046.safetensors",
107
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00015-of-00046.safetensors",
108
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00015-of-00046.safetensors",
109
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00016-of-00046.safetensors",
110
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00016-of-00046.safetensors",
111
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00016-of-00046.safetensors",
112
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00016-of-00046.safetensors",
113
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00015-of-00046.safetensors",
114
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00015-of-00046.safetensors",
115
+ "gpt_neox.layers.15.attention.bias": "model-00016-of-00046.safetensors",
116
+ "gpt_neox.layers.15.attention.dense.bias": "model-00016-of-00046.safetensors",
117
+ "gpt_neox.layers.15.attention.dense.weight": "model-00016-of-00046.safetensors",
118
+ "gpt_neox.layers.15.attention.masked_bias": "model-00016-of-00046.safetensors",
119
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00016-of-00046.safetensors",
120
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00016-of-00046.safetensors",
121
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00016-of-00046.safetensors",
122
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00016-of-00046.safetensors",
123
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00016-of-00046.safetensors",
124
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00017-of-00046.safetensors",
125
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00017-of-00046.safetensors",
126
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00017-of-00046.safetensors",
127
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00017-of-00046.safetensors",
128
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00016-of-00046.safetensors",
129
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00016-of-00046.safetensors",
130
+ "gpt_neox.layers.16.attention.bias": "model-00017-of-00046.safetensors",
131
+ "gpt_neox.layers.16.attention.dense.bias": "model-00017-of-00046.safetensors",
132
+ "gpt_neox.layers.16.attention.dense.weight": "model-00017-of-00046.safetensors",
133
+ "gpt_neox.layers.16.attention.masked_bias": "model-00017-of-00046.safetensors",
134
+ "gpt_neox.layers.16.attention.query_key_value.bias": "model-00017-of-00046.safetensors",
135
+ "gpt_neox.layers.16.attention.query_key_value.weight": "model-00017-of-00046.safetensors",
136
+ "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00017-of-00046.safetensors",
137
+ "gpt_neox.layers.16.input_layernorm.bias": "model-00017-of-00046.safetensors",
138
+ "gpt_neox.layers.16.input_layernorm.weight": "model-00017-of-00046.safetensors",
139
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00018-of-00046.safetensors",
140
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00018-of-00046.safetensors",
141
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00018-of-00046.safetensors",
142
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00018-of-00046.safetensors",
143
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00017-of-00046.safetensors",
144
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00017-of-00046.safetensors",
145
+ "gpt_neox.layers.17.attention.bias": "model-00018-of-00046.safetensors",
146
+ "gpt_neox.layers.17.attention.dense.bias": "model-00018-of-00046.safetensors",
147
+ "gpt_neox.layers.17.attention.dense.weight": "model-00018-of-00046.safetensors",
148
+ "gpt_neox.layers.17.attention.masked_bias": "model-00018-of-00046.safetensors",
149
+ "gpt_neox.layers.17.attention.query_key_value.bias": "model-00018-of-00046.safetensors",
150
+ "gpt_neox.layers.17.attention.query_key_value.weight": "model-00018-of-00046.safetensors",
151
+ "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00018-of-00046.safetensors",
152
+ "gpt_neox.layers.17.input_layernorm.bias": "model-00018-of-00046.safetensors",
153
+ "gpt_neox.layers.17.input_layernorm.weight": "model-00018-of-00046.safetensors",
154
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00019-of-00046.safetensors",
155
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00019-of-00046.safetensors",
156
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00019-of-00046.safetensors",
157
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00019-of-00046.safetensors",
158
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00018-of-00046.safetensors",
159
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00018-of-00046.safetensors",
160
+ "gpt_neox.layers.18.attention.bias": "model-00019-of-00046.safetensors",
161
+ "gpt_neox.layers.18.attention.dense.bias": "model-00019-of-00046.safetensors",
162
+ "gpt_neox.layers.18.attention.dense.weight": "model-00019-of-00046.safetensors",
163
+ "gpt_neox.layers.18.attention.masked_bias": "model-00019-of-00046.safetensors",
164
+ "gpt_neox.layers.18.attention.query_key_value.bias": "model-00019-of-00046.safetensors",
165
+ "gpt_neox.layers.18.attention.query_key_value.weight": "model-00019-of-00046.safetensors",
166
+ "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00019-of-00046.safetensors",
167
+ "gpt_neox.layers.18.input_layernorm.bias": "model-00019-of-00046.safetensors",
168
+ "gpt_neox.layers.18.input_layernorm.weight": "model-00019-of-00046.safetensors",
169
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00020-of-00046.safetensors",
170
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00020-of-00046.safetensors",
171
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00020-of-00046.safetensors",
172
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00020-of-00046.safetensors",
173
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00019-of-00046.safetensors",
174
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00019-of-00046.safetensors",
175
+ "gpt_neox.layers.19.attention.bias": "model-00020-of-00046.safetensors",
176
+ "gpt_neox.layers.19.attention.dense.bias": "model-00020-of-00046.safetensors",
177
+ "gpt_neox.layers.19.attention.dense.weight": "model-00020-of-00046.safetensors",
178
+ "gpt_neox.layers.19.attention.masked_bias": "model-00020-of-00046.safetensors",
179
+ "gpt_neox.layers.19.attention.query_key_value.bias": "model-00020-of-00046.safetensors",
180
+ "gpt_neox.layers.19.attention.query_key_value.weight": "model-00020-of-00046.safetensors",
181
+ "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00020-of-00046.safetensors",
182
+ "gpt_neox.layers.19.input_layernorm.bias": "model-00020-of-00046.safetensors",
183
+ "gpt_neox.layers.19.input_layernorm.weight": "model-00020-of-00046.safetensors",
184
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00021-of-00046.safetensors",
185
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00021-of-00046.safetensors",
186
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00021-of-00046.safetensors",
187
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00021-of-00046.safetensors",
188
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00020-of-00046.safetensors",
189
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00020-of-00046.safetensors",
190
+ "gpt_neox.layers.2.attention.bias": "model-00003-of-00046.safetensors",
191
+ "gpt_neox.layers.2.attention.dense.bias": "model-00003-of-00046.safetensors",
192
+ "gpt_neox.layers.2.attention.dense.weight": "model-00003-of-00046.safetensors",
193
+ "gpt_neox.layers.2.attention.masked_bias": "model-00003-of-00046.safetensors",
194
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00003-of-00046.safetensors",
195
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00003-of-00046.safetensors",
196
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00003-of-00046.safetensors",
197
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00003-of-00046.safetensors",
198
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00003-of-00046.safetensors",
199
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00004-of-00046.safetensors",
200
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00004-of-00046.safetensors",
201
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00004-of-00046.safetensors",
202
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00004-of-00046.safetensors",
203
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00003-of-00046.safetensors",
204
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00003-of-00046.safetensors",
205
+ "gpt_neox.layers.20.attention.bias": "model-00021-of-00046.safetensors",
206
+ "gpt_neox.layers.20.attention.dense.bias": "model-00021-of-00046.safetensors",
207
+ "gpt_neox.layers.20.attention.dense.weight": "model-00021-of-00046.safetensors",
208
+ "gpt_neox.layers.20.attention.masked_bias": "model-00021-of-00046.safetensors",
209
+ "gpt_neox.layers.20.attention.query_key_value.bias": "model-00021-of-00046.safetensors",
210
+ "gpt_neox.layers.20.attention.query_key_value.weight": "model-00021-of-00046.safetensors",
211
+ "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00021-of-00046.safetensors",
212
+ "gpt_neox.layers.20.input_layernorm.bias": "model-00021-of-00046.safetensors",
213
+ "gpt_neox.layers.20.input_layernorm.weight": "model-00021-of-00046.safetensors",
214
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00022-of-00046.safetensors",
215
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00022-of-00046.safetensors",
216
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00022-of-00046.safetensors",
217
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00022-of-00046.safetensors",
218
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00021-of-00046.safetensors",
219
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00021-of-00046.safetensors",
220
+ "gpt_neox.layers.21.attention.bias": "model-00022-of-00046.safetensors",
221
+ "gpt_neox.layers.21.attention.dense.bias": "model-00022-of-00046.safetensors",
222
+ "gpt_neox.layers.21.attention.dense.weight": "model-00022-of-00046.safetensors",
223
+ "gpt_neox.layers.21.attention.masked_bias": "model-00022-of-00046.safetensors",
224
+ "gpt_neox.layers.21.attention.query_key_value.bias": "model-00022-of-00046.safetensors",
225
+ "gpt_neox.layers.21.attention.query_key_value.weight": "model-00022-of-00046.safetensors",
226
+ "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00022-of-00046.safetensors",
227
+ "gpt_neox.layers.21.input_layernorm.bias": "model-00022-of-00046.safetensors",
228
+ "gpt_neox.layers.21.input_layernorm.weight": "model-00022-of-00046.safetensors",
229
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00023-of-00046.safetensors",
230
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00023-of-00046.safetensors",
231
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00023-of-00046.safetensors",
232
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00023-of-00046.safetensors",
233
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00022-of-00046.safetensors",
234
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00022-of-00046.safetensors",
235
+ "gpt_neox.layers.22.attention.bias": "model-00023-of-00046.safetensors",
236
+ "gpt_neox.layers.22.attention.dense.bias": "model-00023-of-00046.safetensors",
237
+ "gpt_neox.layers.22.attention.dense.weight": "model-00023-of-00046.safetensors",
238
+ "gpt_neox.layers.22.attention.masked_bias": "model-00023-of-00046.safetensors",
239
+ "gpt_neox.layers.22.attention.query_key_value.bias": "model-00023-of-00046.safetensors",
240
+ "gpt_neox.layers.22.attention.query_key_value.weight": "model-00023-of-00046.safetensors",
241
+ "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00023-of-00046.safetensors",
242
+ "gpt_neox.layers.22.input_layernorm.bias": "model-00023-of-00046.safetensors",
243
+ "gpt_neox.layers.22.input_layernorm.weight": "model-00023-of-00046.safetensors",
244
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00024-of-00046.safetensors",
245
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00024-of-00046.safetensors",
246
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00024-of-00046.safetensors",
247
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00024-of-00046.safetensors",
248
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00023-of-00046.safetensors",
249
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00023-of-00046.safetensors",
250
+ "gpt_neox.layers.23.attention.bias": "model-00024-of-00046.safetensors",
251
+ "gpt_neox.layers.23.attention.dense.bias": "model-00024-of-00046.safetensors",
252
+ "gpt_neox.layers.23.attention.dense.weight": "model-00024-of-00046.safetensors",
253
+ "gpt_neox.layers.23.attention.masked_bias": "model-00024-of-00046.safetensors",
254
+ "gpt_neox.layers.23.attention.query_key_value.bias": "model-00024-of-00046.safetensors",
255
+ "gpt_neox.layers.23.attention.query_key_value.weight": "model-00024-of-00046.safetensors",
256
+ "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00024-of-00046.safetensors",
257
+ "gpt_neox.layers.23.input_layernorm.bias": "model-00024-of-00046.safetensors",
258
+ "gpt_neox.layers.23.input_layernorm.weight": "model-00024-of-00046.safetensors",
259
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00025-of-00046.safetensors",
260
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00025-of-00046.safetensors",
261
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00025-of-00046.safetensors",
262
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00025-of-00046.safetensors",
263
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00024-of-00046.safetensors",
264
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00024-of-00046.safetensors",
265
+ "gpt_neox.layers.24.attention.bias": "model-00025-of-00046.safetensors",
266
+ "gpt_neox.layers.24.attention.dense.bias": "model-00025-of-00046.safetensors",
267
+ "gpt_neox.layers.24.attention.dense.weight": "model-00025-of-00046.safetensors",
268
+ "gpt_neox.layers.24.attention.masked_bias": "model-00025-of-00046.safetensors",
269
+ "gpt_neox.layers.24.attention.query_key_value.bias": "model-00025-of-00046.safetensors",
270
+ "gpt_neox.layers.24.attention.query_key_value.weight": "model-00025-of-00046.safetensors",
271
+ "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00025-of-00046.safetensors",
272
+ "gpt_neox.layers.24.input_layernorm.bias": "model-00025-of-00046.safetensors",
273
+ "gpt_neox.layers.24.input_layernorm.weight": "model-00025-of-00046.safetensors",
274
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00026-of-00046.safetensors",
275
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00026-of-00046.safetensors",
276
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00026-of-00046.safetensors",
277
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00026-of-00046.safetensors",
278
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00025-of-00046.safetensors",
279
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00025-of-00046.safetensors",
280
+ "gpt_neox.layers.25.attention.bias": "model-00026-of-00046.safetensors",
281
+ "gpt_neox.layers.25.attention.dense.bias": "model-00026-of-00046.safetensors",
282
+ "gpt_neox.layers.25.attention.dense.weight": "model-00026-of-00046.safetensors",
283
+ "gpt_neox.layers.25.attention.masked_bias": "model-00026-of-00046.safetensors",
284
+ "gpt_neox.layers.25.attention.query_key_value.bias": "model-00026-of-00046.safetensors",
285
+ "gpt_neox.layers.25.attention.query_key_value.weight": "model-00026-of-00046.safetensors",
286
+ "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00026-of-00046.safetensors",
287
+ "gpt_neox.layers.25.input_layernorm.bias": "model-00026-of-00046.safetensors",
288
+ "gpt_neox.layers.25.input_layernorm.weight": "model-00026-of-00046.safetensors",
289
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00027-of-00046.safetensors",
290
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00027-of-00046.safetensors",
291
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00027-of-00046.safetensors",
292
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00027-of-00046.safetensors",
293
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00026-of-00046.safetensors",
294
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00026-of-00046.safetensors",
295
+ "gpt_neox.layers.26.attention.bias": "model-00027-of-00046.safetensors",
296
+ "gpt_neox.layers.26.attention.dense.bias": "model-00027-of-00046.safetensors",
297
+ "gpt_neox.layers.26.attention.dense.weight": "model-00027-of-00046.safetensors",
298
+ "gpt_neox.layers.26.attention.masked_bias": "model-00027-of-00046.safetensors",
299
+ "gpt_neox.layers.26.attention.query_key_value.bias": "model-00027-of-00046.safetensors",
300
+ "gpt_neox.layers.26.attention.query_key_value.weight": "model-00027-of-00046.safetensors",
301
+ "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00027-of-00046.safetensors",
302
+ "gpt_neox.layers.26.input_layernorm.bias": "model-00027-of-00046.safetensors",
303
+ "gpt_neox.layers.26.input_layernorm.weight": "model-00027-of-00046.safetensors",
304
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00028-of-00046.safetensors",
305
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00028-of-00046.safetensors",
306
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00028-of-00046.safetensors",
307
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00028-of-00046.safetensors",
308
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00027-of-00046.safetensors",
309
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00027-of-00046.safetensors",
310
+ "gpt_neox.layers.27.attention.bias": "model-00028-of-00046.safetensors",
311
+ "gpt_neox.layers.27.attention.dense.bias": "model-00028-of-00046.safetensors",
312
+ "gpt_neox.layers.27.attention.dense.weight": "model-00028-of-00046.safetensors",
313
+ "gpt_neox.layers.27.attention.masked_bias": "model-00028-of-00046.safetensors",
314
+ "gpt_neox.layers.27.attention.query_key_value.bias": "model-00028-of-00046.safetensors",
315
+ "gpt_neox.layers.27.attention.query_key_value.weight": "model-00028-of-00046.safetensors",
316
+ "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00028-of-00046.safetensors",
317
+ "gpt_neox.layers.27.input_layernorm.bias": "model-00028-of-00046.safetensors",
318
+ "gpt_neox.layers.27.input_layernorm.weight": "model-00028-of-00046.safetensors",
319
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00029-of-00046.safetensors",
320
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00029-of-00046.safetensors",
321
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00029-of-00046.safetensors",
322
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00029-of-00046.safetensors",
323
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00028-of-00046.safetensors",
324
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00028-of-00046.safetensors",
325
+ "gpt_neox.layers.28.attention.bias": "model-00029-of-00046.safetensors",
326
+ "gpt_neox.layers.28.attention.dense.bias": "model-00029-of-00046.safetensors",
327
+ "gpt_neox.layers.28.attention.dense.weight": "model-00029-of-00046.safetensors",
328
+ "gpt_neox.layers.28.attention.masked_bias": "model-00029-of-00046.safetensors",
329
+ "gpt_neox.layers.28.attention.query_key_value.bias": "model-00029-of-00046.safetensors",
330
+ "gpt_neox.layers.28.attention.query_key_value.weight": "model-00029-of-00046.safetensors",
331
+ "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00029-of-00046.safetensors",
332
+ "gpt_neox.layers.28.input_layernorm.bias": "model-00029-of-00046.safetensors",
333
+ "gpt_neox.layers.28.input_layernorm.weight": "model-00029-of-00046.safetensors",
334
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00030-of-00046.safetensors",
335
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00030-of-00046.safetensors",
336
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00030-of-00046.safetensors",
337
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00030-of-00046.safetensors",
338
+ "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00029-of-00046.safetensors",
339
+ "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00029-of-00046.safetensors",
340
+ "gpt_neox.layers.29.attention.bias": "model-00030-of-00046.safetensors",
341
+ "gpt_neox.layers.29.attention.dense.bias": "model-00030-of-00046.safetensors",
342
+ "gpt_neox.layers.29.attention.dense.weight": "model-00030-of-00046.safetensors",
343
+ "gpt_neox.layers.29.attention.masked_bias": "model-00030-of-00046.safetensors",
344
+ "gpt_neox.layers.29.attention.query_key_value.bias": "model-00030-of-00046.safetensors",
345
+ "gpt_neox.layers.29.attention.query_key_value.weight": "model-00030-of-00046.safetensors",
346
+ "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00030-of-00046.safetensors",
347
+ "gpt_neox.layers.29.input_layernorm.bias": "model-00030-of-00046.safetensors",
348
+ "gpt_neox.layers.29.input_layernorm.weight": "model-00030-of-00046.safetensors",
349
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00031-of-00046.safetensors",
350
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00031-of-00046.safetensors",
351
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00031-of-00046.safetensors",
352
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00031-of-00046.safetensors",
353
+ "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00030-of-00046.safetensors",
354
+ "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00030-of-00046.safetensors",
355
+ "gpt_neox.layers.3.attention.bias": "model-00004-of-00046.safetensors",
356
+ "gpt_neox.layers.3.attention.dense.bias": "model-00004-of-00046.safetensors",
357
+ "gpt_neox.layers.3.attention.dense.weight": "model-00004-of-00046.safetensors",
358
+ "gpt_neox.layers.3.attention.masked_bias": "model-00004-of-00046.safetensors",
359
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00004-of-00046.safetensors",
360
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00004-of-00046.safetensors",
361
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00004-of-00046.safetensors",
362
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00004-of-00046.safetensors",
363
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00004-of-00046.safetensors",
364
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00005-of-00046.safetensors",
365
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00005-of-00046.safetensors",
366
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00005-of-00046.safetensors",
367
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00005-of-00046.safetensors",
368
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00004-of-00046.safetensors",
369
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00004-of-00046.safetensors",
370
+ "gpt_neox.layers.30.attention.bias": "model-00031-of-00046.safetensors",
371
+ "gpt_neox.layers.30.attention.dense.bias": "model-00031-of-00046.safetensors",
372
+ "gpt_neox.layers.30.attention.dense.weight": "model-00031-of-00046.safetensors",
373
+ "gpt_neox.layers.30.attention.masked_bias": "model-00031-of-00046.safetensors",
374
+ "gpt_neox.layers.30.attention.query_key_value.bias": "model-00031-of-00046.safetensors",
375
+ "gpt_neox.layers.30.attention.query_key_value.weight": "model-00031-of-00046.safetensors",
376
+ "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00031-of-00046.safetensors",
377
+ "gpt_neox.layers.30.input_layernorm.bias": "model-00031-of-00046.safetensors",
378
+ "gpt_neox.layers.30.input_layernorm.weight": "model-00031-of-00046.safetensors",
379
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00032-of-00046.safetensors",
380
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00032-of-00046.safetensors",
381
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00032-of-00046.safetensors",
382
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00032-of-00046.safetensors",
383
+ "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00031-of-00046.safetensors",
384
+ "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00031-of-00046.safetensors",
385
+ "gpt_neox.layers.31.attention.bias": "model-00032-of-00046.safetensors",
386
+ "gpt_neox.layers.31.attention.dense.bias": "model-00032-of-00046.safetensors",
387
+ "gpt_neox.layers.31.attention.dense.weight": "model-00032-of-00046.safetensors",
388
+ "gpt_neox.layers.31.attention.masked_bias": "model-00032-of-00046.safetensors",
389
+ "gpt_neox.layers.31.attention.query_key_value.bias": "model-00032-of-00046.safetensors",
390
+ "gpt_neox.layers.31.attention.query_key_value.weight": "model-00032-of-00046.safetensors",
391
+ "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00032-of-00046.safetensors",
392
+ "gpt_neox.layers.31.input_layernorm.bias": "model-00032-of-00046.safetensors",
393
+ "gpt_neox.layers.31.input_layernorm.weight": "model-00032-of-00046.safetensors",
394
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00033-of-00046.safetensors",
395
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00033-of-00046.safetensors",
396
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00033-of-00046.safetensors",
397
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00033-of-00046.safetensors",
398
+ "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00032-of-00046.safetensors",
399
+ "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00032-of-00046.safetensors",
400
+ "gpt_neox.layers.32.attention.bias": "model-00033-of-00046.safetensors",
401
+ "gpt_neox.layers.32.attention.dense.bias": "model-00033-of-00046.safetensors",
402
+ "gpt_neox.layers.32.attention.dense.weight": "model-00033-of-00046.safetensors",
403
+ "gpt_neox.layers.32.attention.masked_bias": "model-00033-of-00046.safetensors",
404
+ "gpt_neox.layers.32.attention.query_key_value.bias": "model-00033-of-00046.safetensors",
405
+ "gpt_neox.layers.32.attention.query_key_value.weight": "model-00033-of-00046.safetensors",
406
+ "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "model-00033-of-00046.safetensors",
407
+ "gpt_neox.layers.32.input_layernorm.bias": "model-00033-of-00046.safetensors",
408
+ "gpt_neox.layers.32.input_layernorm.weight": "model-00033-of-00046.safetensors",
409
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00034-of-00046.safetensors",
410
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00034-of-00046.safetensors",
411
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00034-of-00046.safetensors",
412
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00034-of-00046.safetensors",
413
+ "gpt_neox.layers.32.post_attention_layernorm.bias": "model-00033-of-00046.safetensors",
414
+ "gpt_neox.layers.32.post_attention_layernorm.weight": "model-00033-of-00046.safetensors",
415
+ "gpt_neox.layers.33.attention.bias": "model-00034-of-00046.safetensors",
416
+ "gpt_neox.layers.33.attention.dense.bias": "model-00034-of-00046.safetensors",
417
+ "gpt_neox.layers.33.attention.dense.weight": "model-00034-of-00046.safetensors",
418
+ "gpt_neox.layers.33.attention.masked_bias": "model-00034-of-00046.safetensors",
419
+ "gpt_neox.layers.33.attention.query_key_value.bias": "model-00034-of-00046.safetensors",
420
+ "gpt_neox.layers.33.attention.query_key_value.weight": "model-00034-of-00046.safetensors",
421
+ "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "model-00034-of-00046.safetensors",
422
+ "gpt_neox.layers.33.input_layernorm.bias": "model-00034-of-00046.safetensors",
423
+ "gpt_neox.layers.33.input_layernorm.weight": "model-00034-of-00046.safetensors",
424
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00035-of-00046.safetensors",
425
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00035-of-00046.safetensors",
426
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00035-of-00046.safetensors",
427
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00035-of-00046.safetensors",
428
+ "gpt_neox.layers.33.post_attention_layernorm.bias": "model-00034-of-00046.safetensors",
429
+ "gpt_neox.layers.33.post_attention_layernorm.weight": "model-00034-of-00046.safetensors",
430
+ "gpt_neox.layers.34.attention.bias": "model-00035-of-00046.safetensors",
431
+ "gpt_neox.layers.34.attention.dense.bias": "model-00035-of-00046.safetensors",
432
+ "gpt_neox.layers.34.attention.dense.weight": "model-00035-of-00046.safetensors",
433
+ "gpt_neox.layers.34.attention.masked_bias": "model-00035-of-00046.safetensors",
434
+ "gpt_neox.layers.34.attention.query_key_value.bias": "model-00035-of-00046.safetensors",
435
+ "gpt_neox.layers.34.attention.query_key_value.weight": "model-00035-of-00046.safetensors",
436
+ "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "model-00035-of-00046.safetensors",
437
+ "gpt_neox.layers.34.input_layernorm.bias": "model-00035-of-00046.safetensors",
438
+ "gpt_neox.layers.34.input_layernorm.weight": "model-00035-of-00046.safetensors",
439
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "model-00036-of-00046.safetensors",
440
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "model-00036-of-00046.safetensors",
441
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "model-00036-of-00046.safetensors",
442
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "model-00036-of-00046.safetensors",
443
+ "gpt_neox.layers.34.post_attention_layernorm.bias": "model-00035-of-00046.safetensors",
444
+ "gpt_neox.layers.34.post_attention_layernorm.weight": "model-00035-of-00046.safetensors",
445
+ "gpt_neox.layers.35.attention.bias": "model-00036-of-00046.safetensors",
446
+ "gpt_neox.layers.35.attention.dense.bias": "model-00036-of-00046.safetensors",
447
+ "gpt_neox.layers.35.attention.dense.weight": "model-00036-of-00046.safetensors",
448
+ "gpt_neox.layers.35.attention.masked_bias": "model-00036-of-00046.safetensors",
449
+ "gpt_neox.layers.35.attention.query_key_value.bias": "model-00036-of-00046.safetensors",
450
+ "gpt_neox.layers.35.attention.query_key_value.weight": "model-00036-of-00046.safetensors",
451
+ "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "model-00036-of-00046.safetensors",
452
+ "gpt_neox.layers.35.input_layernorm.bias": "model-00036-of-00046.safetensors",
453
+ "gpt_neox.layers.35.input_layernorm.weight": "model-00036-of-00046.safetensors",
454
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "model-00037-of-00046.safetensors",
455
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "model-00037-of-00046.safetensors",
456
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "model-00037-of-00046.safetensors",
457
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "model-00037-of-00046.safetensors",
458
+ "gpt_neox.layers.35.post_attention_layernorm.bias": "model-00036-of-00046.safetensors",
459
+ "gpt_neox.layers.35.post_attention_layernorm.weight": "model-00036-of-00046.safetensors",
460
+ "gpt_neox.layers.36.attention.bias": "model-00037-of-00046.safetensors",
461
+ "gpt_neox.layers.36.attention.dense.bias": "model-00037-of-00046.safetensors",
462
+ "gpt_neox.layers.36.attention.dense.weight": "model-00037-of-00046.safetensors",
463
+ "gpt_neox.layers.36.attention.masked_bias": "model-00037-of-00046.safetensors",
464
+ "gpt_neox.layers.36.attention.query_key_value.bias": "model-00037-of-00046.safetensors",
465
+ "gpt_neox.layers.36.attention.query_key_value.weight": "model-00037-of-00046.safetensors",
466
+ "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "model-00037-of-00046.safetensors",
467
+ "gpt_neox.layers.36.input_layernorm.bias": "model-00037-of-00046.safetensors",
468
+ "gpt_neox.layers.36.input_layernorm.weight": "model-00037-of-00046.safetensors",
469
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "model-00038-of-00046.safetensors",
470
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "model-00038-of-00046.safetensors",
471
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "model-00038-of-00046.safetensors",
472
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "model-00038-of-00046.safetensors",
473
+ "gpt_neox.layers.36.post_attention_layernorm.bias": "model-00037-of-00046.safetensors",
474
+ "gpt_neox.layers.36.post_attention_layernorm.weight": "model-00037-of-00046.safetensors",
475
+ "gpt_neox.layers.37.attention.bias": "model-00038-of-00046.safetensors",
476
+ "gpt_neox.layers.37.attention.dense.bias": "model-00038-of-00046.safetensors",
477
+ "gpt_neox.layers.37.attention.dense.weight": "model-00038-of-00046.safetensors",
478
+ "gpt_neox.layers.37.attention.masked_bias": "model-00038-of-00046.safetensors",
479
+ "gpt_neox.layers.37.attention.query_key_value.bias": "model-00038-of-00046.safetensors",
480
+ "gpt_neox.layers.37.attention.query_key_value.weight": "model-00038-of-00046.safetensors",
481
+ "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "model-00038-of-00046.safetensors",
482
+ "gpt_neox.layers.37.input_layernorm.bias": "model-00038-of-00046.safetensors",
483
+ "gpt_neox.layers.37.input_layernorm.weight": "model-00038-of-00046.safetensors",
484
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "model-00039-of-00046.safetensors",
485
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "model-00039-of-00046.safetensors",
486
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "model-00039-of-00046.safetensors",
487
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "model-00039-of-00046.safetensors",
488
+ "gpt_neox.layers.37.post_attention_layernorm.bias": "model-00038-of-00046.safetensors",
489
+ "gpt_neox.layers.37.post_attention_layernorm.weight": "model-00038-of-00046.safetensors",
490
+ "gpt_neox.layers.38.attention.bias": "model-00039-of-00046.safetensors",
491
+ "gpt_neox.layers.38.attention.dense.bias": "model-00039-of-00046.safetensors",
492
+ "gpt_neox.layers.38.attention.dense.weight": "model-00039-of-00046.safetensors",
493
+ "gpt_neox.layers.38.attention.masked_bias": "model-00039-of-00046.safetensors",
494
+ "gpt_neox.layers.38.attention.query_key_value.bias": "model-00039-of-00046.safetensors",
495
+ "gpt_neox.layers.38.attention.query_key_value.weight": "model-00039-of-00046.safetensors",
496
+ "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "model-00039-of-00046.safetensors",
497
+ "gpt_neox.layers.38.input_layernorm.bias": "model-00039-of-00046.safetensors",
498
+ "gpt_neox.layers.38.input_layernorm.weight": "model-00039-of-00046.safetensors",
499
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "model-00040-of-00046.safetensors",
500
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "model-00040-of-00046.safetensors",
501
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "model-00040-of-00046.safetensors",
502
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "model-00040-of-00046.safetensors",
503
+ "gpt_neox.layers.38.post_attention_layernorm.bias": "model-00039-of-00046.safetensors",
504
+ "gpt_neox.layers.38.post_attention_layernorm.weight": "model-00039-of-00046.safetensors",
505
+ "gpt_neox.layers.39.attention.bias": "model-00040-of-00046.safetensors",
506
+ "gpt_neox.layers.39.attention.dense.bias": "model-00040-of-00046.safetensors",
507
+ "gpt_neox.layers.39.attention.dense.weight": "model-00040-of-00046.safetensors",
508
+ "gpt_neox.layers.39.attention.masked_bias": "model-00040-of-00046.safetensors",
509
+ "gpt_neox.layers.39.attention.query_key_value.bias": "model-00040-of-00046.safetensors",
510
+ "gpt_neox.layers.39.attention.query_key_value.weight": "model-00040-of-00046.safetensors",
511
+ "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "model-00040-of-00046.safetensors",
512
+ "gpt_neox.layers.39.input_layernorm.bias": "model-00040-of-00046.safetensors",
513
+ "gpt_neox.layers.39.input_layernorm.weight": "model-00040-of-00046.safetensors",
514
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "model-00041-of-00046.safetensors",
515
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "model-00041-of-00046.safetensors",
516
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "model-00041-of-00046.safetensors",
517
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "model-00041-of-00046.safetensors",
518
+ "gpt_neox.layers.39.post_attention_layernorm.bias": "model-00040-of-00046.safetensors",
519
+ "gpt_neox.layers.39.post_attention_layernorm.weight": "model-00040-of-00046.safetensors",
520
+ "gpt_neox.layers.4.attention.bias": "model-00005-of-00046.safetensors",
521
+ "gpt_neox.layers.4.attention.dense.bias": "model-00005-of-00046.safetensors",
522
+ "gpt_neox.layers.4.attention.dense.weight": "model-00005-of-00046.safetensors",
523
+ "gpt_neox.layers.4.attention.masked_bias": "model-00005-of-00046.safetensors",
524
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00005-of-00046.safetensors",
525
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00005-of-00046.safetensors",
526
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00005-of-00046.safetensors",
527
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00005-of-00046.safetensors",
528
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00005-of-00046.safetensors",
529
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00006-of-00046.safetensors",
530
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00006-of-00046.safetensors",
531
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00006-of-00046.safetensors",
532
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00006-of-00046.safetensors",
533
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00005-of-00046.safetensors",
534
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00005-of-00046.safetensors",
535
+ "gpt_neox.layers.40.attention.bias": "model-00041-of-00046.safetensors",
536
+ "gpt_neox.layers.40.attention.dense.bias": "model-00041-of-00046.safetensors",
537
+ "gpt_neox.layers.40.attention.dense.weight": "model-00041-of-00046.safetensors",
538
+ "gpt_neox.layers.40.attention.masked_bias": "model-00041-of-00046.safetensors",
539
+ "gpt_neox.layers.40.attention.query_key_value.bias": "model-00041-of-00046.safetensors",
540
+ "gpt_neox.layers.40.attention.query_key_value.weight": "model-00041-of-00046.safetensors",
541
+ "gpt_neox.layers.40.attention.rotary_emb.inv_freq": "model-00041-of-00046.safetensors",
542
+ "gpt_neox.layers.40.input_layernorm.bias": "model-00041-of-00046.safetensors",
543
+ "gpt_neox.layers.40.input_layernorm.weight": "model-00041-of-00046.safetensors",
544
+ "gpt_neox.layers.40.mlp.dense_4h_to_h.bias": "model-00042-of-00046.safetensors",
545
+ "gpt_neox.layers.40.mlp.dense_4h_to_h.weight": "model-00042-of-00046.safetensors",
546
+ "gpt_neox.layers.40.mlp.dense_h_to_4h.bias": "model-00042-of-00046.safetensors",
547
+ "gpt_neox.layers.40.mlp.dense_h_to_4h.weight": "model-00042-of-00046.safetensors",
548
+ "gpt_neox.layers.40.post_attention_layernorm.bias": "model-00041-of-00046.safetensors",
549
+ "gpt_neox.layers.40.post_attention_layernorm.weight": "model-00041-of-00046.safetensors",
550
+ "gpt_neox.layers.41.attention.bias": "model-00042-of-00046.safetensors",
551
+ "gpt_neox.layers.41.attention.dense.bias": "model-00042-of-00046.safetensors",
552
+ "gpt_neox.layers.41.attention.dense.weight": "model-00042-of-00046.safetensors",
553
+ "gpt_neox.layers.41.attention.masked_bias": "model-00042-of-00046.safetensors",
554
+ "gpt_neox.layers.41.attention.query_key_value.bias": "model-00042-of-00046.safetensors",
555
+ "gpt_neox.layers.41.attention.query_key_value.weight": "model-00042-of-00046.safetensors",
556
+ "gpt_neox.layers.41.attention.rotary_emb.inv_freq": "model-00042-of-00046.safetensors",
557
+ "gpt_neox.layers.41.input_layernorm.bias": "model-00042-of-00046.safetensors",
558
+ "gpt_neox.layers.41.input_layernorm.weight": "model-00042-of-00046.safetensors",
559
+ "gpt_neox.layers.41.mlp.dense_4h_to_h.bias": "model-00043-of-00046.safetensors",
560
+ "gpt_neox.layers.41.mlp.dense_4h_to_h.weight": "model-00043-of-00046.safetensors",
561
+ "gpt_neox.layers.41.mlp.dense_h_to_4h.bias": "model-00043-of-00046.safetensors",
562
+ "gpt_neox.layers.41.mlp.dense_h_to_4h.weight": "model-00043-of-00046.safetensors",
563
+ "gpt_neox.layers.41.post_attention_layernorm.bias": "model-00042-of-00046.safetensors",
564
+ "gpt_neox.layers.41.post_attention_layernorm.weight": "model-00042-of-00046.safetensors",
565
+ "gpt_neox.layers.42.attention.bias": "model-00043-of-00046.safetensors",
566
+ "gpt_neox.layers.42.attention.dense.bias": "model-00043-of-00046.safetensors",
567
+ "gpt_neox.layers.42.attention.dense.weight": "model-00043-of-00046.safetensors",
568
+ "gpt_neox.layers.42.attention.masked_bias": "model-00043-of-00046.safetensors",
569
+ "gpt_neox.layers.42.attention.query_key_value.bias": "model-00043-of-00046.safetensors",
570
+ "gpt_neox.layers.42.attention.query_key_value.weight": "model-00043-of-00046.safetensors",
571
+ "gpt_neox.layers.42.attention.rotary_emb.inv_freq": "model-00043-of-00046.safetensors",
572
+ "gpt_neox.layers.42.input_layernorm.bias": "model-00043-of-00046.safetensors",
573
+ "gpt_neox.layers.42.input_layernorm.weight": "model-00043-of-00046.safetensors",
574
+ "gpt_neox.layers.42.mlp.dense_4h_to_h.bias": "model-00044-of-00046.safetensors",
575
+ "gpt_neox.layers.42.mlp.dense_4h_to_h.weight": "model-00044-of-00046.safetensors",
576
+ "gpt_neox.layers.42.mlp.dense_h_to_4h.bias": "model-00044-of-00046.safetensors",
577
+ "gpt_neox.layers.42.mlp.dense_h_to_4h.weight": "model-00044-of-00046.safetensors",
578
+ "gpt_neox.layers.42.post_attention_layernorm.bias": "model-00043-of-00046.safetensors",
579
+ "gpt_neox.layers.42.post_attention_layernorm.weight": "model-00043-of-00046.safetensors",
580
+ "gpt_neox.layers.43.attention.bias": "model-00044-of-00046.safetensors",
581
+ "gpt_neox.layers.43.attention.dense.bias": "model-00044-of-00046.safetensors",
582
+ "gpt_neox.layers.43.attention.dense.weight": "model-00044-of-00046.safetensors",
583
+ "gpt_neox.layers.43.attention.masked_bias": "model-00044-of-00046.safetensors",
584
+ "gpt_neox.layers.43.attention.query_key_value.bias": "model-00044-of-00046.safetensors",
585
+ "gpt_neox.layers.43.attention.query_key_value.weight": "model-00044-of-00046.safetensors",
586
+ "gpt_neox.layers.43.attention.rotary_emb.inv_freq": "model-00044-of-00046.safetensors",
587
+ "gpt_neox.layers.43.input_layernorm.bias": "model-00044-of-00046.safetensors",
588
+ "gpt_neox.layers.43.input_layernorm.weight": "model-00044-of-00046.safetensors",
589
+ "gpt_neox.layers.43.mlp.dense_4h_to_h.bias": "model-00045-of-00046.safetensors",
590
+ "gpt_neox.layers.43.mlp.dense_4h_to_h.weight": "model-00045-of-00046.safetensors",
591
+ "gpt_neox.layers.43.mlp.dense_h_to_4h.bias": "model-00045-of-00046.safetensors",
592
+ "gpt_neox.layers.43.mlp.dense_h_to_4h.weight": "model-00045-of-00046.safetensors",
593
+ "gpt_neox.layers.43.post_attention_layernorm.bias": "model-00044-of-00046.safetensors",
594
+ "gpt_neox.layers.43.post_attention_layernorm.weight": "model-00044-of-00046.safetensors",
595
+ "gpt_neox.layers.5.attention.bias": "model-00006-of-00046.safetensors",
596
+ "gpt_neox.layers.5.attention.dense.bias": "model-00006-of-00046.safetensors",
597
+ "gpt_neox.layers.5.attention.dense.weight": "model-00006-of-00046.safetensors",
598
+ "gpt_neox.layers.5.attention.masked_bias": "model-00006-of-00046.safetensors",
599
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00006-of-00046.safetensors",
600
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00006-of-00046.safetensors",
601
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00006-of-00046.safetensors",
602
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00006-of-00046.safetensors",
603
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00006-of-00046.safetensors",
604
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00007-of-00046.safetensors",
605
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00007-of-00046.safetensors",
606
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00007-of-00046.safetensors",
607
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00007-of-00046.safetensors",
608
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00006-of-00046.safetensors",
609
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00006-of-00046.safetensors",
610
+ "gpt_neox.layers.6.attention.bias": "model-00007-of-00046.safetensors",
611
+ "gpt_neox.layers.6.attention.dense.bias": "model-00007-of-00046.safetensors",
612
+ "gpt_neox.layers.6.attention.dense.weight": "model-00007-of-00046.safetensors",
613
+ "gpt_neox.layers.6.attention.masked_bias": "model-00007-of-00046.safetensors",
614
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00007-of-00046.safetensors",
615
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00007-of-00046.safetensors",
616
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00007-of-00046.safetensors",
617
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00007-of-00046.safetensors",
618
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00007-of-00046.safetensors",
619
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00008-of-00046.safetensors",
620
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00008-of-00046.safetensors",
621
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00008-of-00046.safetensors",
622
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00008-of-00046.safetensors",
623
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00007-of-00046.safetensors",
624
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00007-of-00046.safetensors",
625
+ "gpt_neox.layers.7.attention.bias": "model-00008-of-00046.safetensors",
626
+ "gpt_neox.layers.7.attention.dense.bias": "model-00008-of-00046.safetensors",
627
+ "gpt_neox.layers.7.attention.dense.weight": "model-00008-of-00046.safetensors",
628
+ "gpt_neox.layers.7.attention.masked_bias": "model-00008-of-00046.safetensors",
629
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00008-of-00046.safetensors",
630
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00008-of-00046.safetensors",
631
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00008-of-00046.safetensors",
632
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00008-of-00046.safetensors",
633
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00008-of-00046.safetensors",
634
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00009-of-00046.safetensors",
635
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00009-of-00046.safetensors",
636
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00009-of-00046.safetensors",
637
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00009-of-00046.safetensors",
638
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00008-of-00046.safetensors",
639
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00008-of-00046.safetensors",
640
+ "gpt_neox.layers.8.attention.bias": "model-00009-of-00046.safetensors",
641
+ "gpt_neox.layers.8.attention.dense.bias": "model-00009-of-00046.safetensors",
642
+ "gpt_neox.layers.8.attention.dense.weight": "model-00009-of-00046.safetensors",
643
+ "gpt_neox.layers.8.attention.masked_bias": "model-00009-of-00046.safetensors",
644
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00009-of-00046.safetensors",
645
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00009-of-00046.safetensors",
646
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00009-of-00046.safetensors",
647
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00009-of-00046.safetensors",
648
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00009-of-00046.safetensors",
649
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00010-of-00046.safetensors",
650
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00010-of-00046.safetensors",
651
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00010-of-00046.safetensors",
652
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00010-of-00046.safetensors",
653
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00009-of-00046.safetensors",
654
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00009-of-00046.safetensors",
655
+ "gpt_neox.layers.9.attention.bias": "model-00010-of-00046.safetensors",
656
+ "gpt_neox.layers.9.attention.dense.bias": "model-00010-of-00046.safetensors",
657
+ "gpt_neox.layers.9.attention.dense.weight": "model-00010-of-00046.safetensors",
658
+ "gpt_neox.layers.9.attention.masked_bias": "model-00010-of-00046.safetensors",
659
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00010-of-00046.safetensors",
660
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00010-of-00046.safetensors",
661
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00010-of-00046.safetensors",
662
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00010-of-00046.safetensors",
663
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00010-of-00046.safetensors",
664
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00011-of-00046.safetensors",
665
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00011-of-00046.safetensors",
666
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00011-of-00046.safetensors",
667
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00011-of-00046.safetensors",
668
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00010-of-00046.safetensors",
669
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00010-of-00046.safetensors"
670
+ }
671
+ }