FrostAura commited on
Commit
0eee5f4
1 Parent(s): 2201472

[DEV]: Initial commit of base model prior to fine-tuning.

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. merges.txt +0 -0
  2. pytorch_model-00001-of-00046.bin +3 -0
  3. pytorch_model-00002-of-00046.bin +3 -0
  4. pytorch_model-00003-of-00046.bin +3 -0
  5. pytorch_model-00004-of-00046.bin +3 -0
  6. pytorch_model-00005-of-00046.bin +3 -0
  7. pytorch_model-00006-of-00046.bin +3 -0
  8. pytorch_model-00007-of-00046.bin +3 -0
  9. pytorch_model-00008-of-00046.bin +3 -0
  10. pytorch_model-00009-of-00046.bin +3 -0
  11. pytorch_model-00010-of-00046.bin +3 -0
  12. pytorch_model-00011-of-00046.bin +3 -0
  13. pytorch_model-00012-of-00046.bin +3 -0
  14. pytorch_model-00013-of-00046.bin +3 -0
  15. pytorch_model-00014-of-00046.bin +3 -0
  16. pytorch_model-00015-of-00046.bin +3 -0
  17. pytorch_model-00016-of-00046.bin +3 -0
  18. pytorch_model-00017-of-00046.bin +3 -0
  19. pytorch_model-00018-of-00046.bin +3 -0
  20. pytorch_model-00019-of-00046.bin +3 -0
  21. pytorch_model-00020-of-00046.bin +3 -0
  22. pytorch_model-00021-of-00046.bin +3 -0
  23. pytorch_model-00022-of-00046.bin +3 -0
  24. pytorch_model-00023-of-00046.bin +3 -0
  25. pytorch_model-00024-of-00046.bin +3 -0
  26. pytorch_model-00025-of-00046.bin +3 -0
  27. pytorch_model-00026-of-00046.bin +3 -0
  28. pytorch_model-00027-of-00046.bin +3 -0
  29. pytorch_model-00028-of-00046.bin +3 -0
  30. pytorch_model-00029-of-00046.bin +3 -0
  31. pytorch_model-00030-of-00046.bin +3 -0
  32. pytorch_model-00031-of-00046.bin +3 -0
  33. pytorch_model-00032-of-00046.bin +3 -0
  34. pytorch_model-00033-of-00046.bin +3 -0
  35. pytorch_model-00034-of-00046.bin +3 -0
  36. pytorch_model-00035-of-00046.bin +3 -0
  37. pytorch_model-00036-of-00046.bin +3 -0
  38. pytorch_model-00037-of-00046.bin +3 -0
  39. pytorch_model-00038-of-00046.bin +3 -0
  40. pytorch_model-00039-of-00046.bin +3 -0
  41. pytorch_model-00040-of-00046.bin +3 -0
  42. pytorch_model-00041-of-00046.bin +3 -0
  43. pytorch_model-00042-of-00046.bin +3 -0
  44. pytorch_model-00043-of-00046.bin +3 -0
  45. pytorch_model-00044-of-00046.bin +3 -0
  46. pytorch_model-00045-of-00046.bin +3 -0
  47. pytorch_model-00046-of-00046.bin +3 -0
  48. pytorch_model.bin.index.json +671 -0
  49. special_tokens_map.json +1 -0
  50. tokenizer.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a6926dd4e27c801194ab9b697e6b739d4312cbd7d081ee020f5ca75607743c
3
+ size 925994625
pytorch_model-00002-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96a36c8efc68a1d6c5de03b8c78625422edbf3a0b3d7c88650a8cd409ebbd73
3
+ size 910328184
pytorch_model-00003-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582e2bbbbd7c8b91de2c8fe2b292610e6b5a74966a7e2398645a38dbda2ed71f
3
+ size 910328184
pytorch_model-00004-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dad2df6d880f4a64ee2c530c0b51c6be4600f2463fa69d06d668b18904e3d5a3
3
+ size 910328184
pytorch_model-00005-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd1111e7f207d4a7720a8723cf5d2c2dabb77e509a57ce41a28ee630b0e8353
3
+ size 910328184
pytorch_model-00006-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7de215cb446cb678dc7e4e7df5b18cc16b79fdf08e41a2738491ff9cc57e37a
3
+ size 910328184
pytorch_model-00007-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b30b05245b1ad580dd2d304a760fd93bb80cd6e67e3e497b0140abb23c8f84
3
+ size 910328184
pytorch_model-00008-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b0850c82bc82ada8e092e7bd9a782737391faa8a844c32f1d206c9d5cc1665
3
+ size 910328184
pytorch_model-00009-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b9c1d811efc0361c8607bd3a52f0474478b5871bbf70746af8dc8cc7b7569d
3
+ size 910328184
pytorch_model-00010-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343cfe1a395d55c148034e13cb3a0470baa68e4d0711412a2d6ad22574e2e9ea
3
+ size 910328184
pytorch_model-00011-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089530ad755e6ec58b10d4a977b960bff4ade4346c0b0b9ebf2063cde42af0fd
3
+ size 910328184
pytorch_model-00012-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7040b3aadd06bfc8b4175f8273d86f22a8eb7c7b1a5cd9991c2678290b610a36
3
+ size 910328184
pytorch_model-00013-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d7a789188146fc4368c0f4b1574dd7933ec8cc4ecb809aebca90a70c0fca91
3
+ size 910328184
pytorch_model-00014-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba306de96a20abccb2e99048614debd63557228c3f9787ca7d6cc445397a9c2
3
+ size 910328184
pytorch_model-00015-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5105b09e42b2eacaf1985ce37811913dca02446169cff6ece20cbf8cd6803a78
3
+ size 910328184
pytorch_model-00016-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c5345d12c491aede73bd79dcda8093badddd1ab393413de1be377aed044c34
3
+ size 910328184
pytorch_model-00017-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a3f74f1e0ce412f6b06c172b068fd9dcefbfdff60a1e3242d1a56a58441e8a
3
+ size 910328184
pytorch_model-00018-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c17a90b84c957246da45835e6b88cc496430e24af18f74d5219cebfb6ca89bf5
3
+ size 910328184
pytorch_model-00019-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0eab7c8271f3b267eb84cc90d0e6667a40060fc5c751f0bbe7edd2c2f1e32f
3
+ size 910328184
pytorch_model-00020-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a3e63161295d36203577c2226e217dffdbf3bbbb99f883ff64e11e7b2cb1fb9
3
+ size 910328184
pytorch_model-00021-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:260f41230c97ce26e787650aa225cc65d381b4e17485cbf6e2cef31e99d0f2dc
3
+ size 910328184
pytorch_model-00022-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43392e9228f83d32455920c0517f3f288049340236fc9cb7d660f61de0705d6d
3
+ size 910328184
pytorch_model-00023-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11fb9cefd82632103450852c85eef713d9dfdd0c14451c84a909e3b335db5ddc
3
+ size 910328184
pytorch_model-00024-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff5af200c2682206e7076337820a576ad125f97cad398513c73c0febac61eb7
3
+ size 910328184
pytorch_model-00025-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e38d80739d11771d6d2ac50574f5c7c5a980da47dd204ff320af548e3305aed3
3
+ size 910328184
pytorch_model-00026-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead5458cf979a9e311e1d1187605caa0d630b39f2bce616f1a7e43b70a565915
3
+ size 910328184
pytorch_model-00027-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34cfb1757f7e4fbc933fe56d442f297fe64763ee95576da09e1a9e6718e7de22
3
+ size 910328184
pytorch_model-00028-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4090aa141fb5d6a00cefc15d5f55cee135db352ebcca1ce6829da65acdefacbc
3
+ size 910328184
pytorch_model-00029-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b81d9a2491ff2054b2e502207e96009308259b25da2efab9e3073ae3fef9fb
3
+ size 910328184
pytorch_model-00030-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaab6b1b9b16640dedca882c7eba8a3991a769462fc267215499241bc48d3732
3
+ size 910328184
pytorch_model-00031-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad862519bb27c0417b0ee46b9ffa47a7b7c219034a254881e054cc79b7d3b2a
3
+ size 910328184
pytorch_model-00032-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23752ed93b429d111dc4d75759731887cddb9f1a6717190778e22f37d6c1ef8d
3
+ size 910328184
pytorch_model-00033-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0842b355f997dc12d5c9c90297936919ed2b1223fd8fd5f00afbfcd28db979
3
+ size 910328184
pytorch_model-00034-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7275a1541dd2a22297f878bdb5dff0cd41c327e61445e8ba6fd7f4b8ed51b6f9
3
+ size 910328184
pytorch_model-00035-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b1e3ead65e8867953b00685531c42b3968fb317eb21286a4489f2d33c9424f
3
+ size 910328184
pytorch_model-00036-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92801ef5b1dd5f959f94b79233c461343319bd7fd881cc5d1642cd97675352b4
3
+ size 910328184
pytorch_model-00037-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080b0ab69fdc85af7f0fac13bf89d402980ee1e93812545e6ec85253040fc9ea
3
+ size 910328184
pytorch_model-00038-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:603b045908ca1044109a3c13da7ce8f9f633a015b7717adc2ca72db186beb58e
3
+ size 910328184
pytorch_model-00039-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9823f13162ca5b21532930863497d82a79788a2842c77d0538a36b8d86ec9573
3
+ size 910328184
pytorch_model-00040-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a231cae597ce6e732429e9f589d2b1face5755df083b999eb2688481757cb4af
3
+ size 910328184
pytorch_model-00041-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc909def52bbd51a6b6bb34f29bad67383a5ce0a5947a2fc26a9afcf5f705471
3
+ size 910328184
pytorch_model-00042-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac94d1b42f8ffd9b34121a797dc8371e405d3b4bbc1ad8003560da82a13205a
3
+ size 910328184
pytorch_model-00043-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36259a4252eae0d31d14513bb6b1e9e408aa416abda2347f397b333ae4ee0a41
3
+ size 910328184
pytorch_model-00044-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c40045b5342d2e4643cea8b7db300f529064df796a08f38b4b7df08ca67f96
3
+ size 910328184
pytorch_model-00045-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7baf394716643e2873b74cc823f39cc563ad1cdaa918b4b91cc7f1b42d7b68b
3
+ size 604067735
pytorch_model-00046-of-00046.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925dc7a0c53a3487686cea905b52f2117d14fb3ff18e8fe1b544895a9c69fce4
3
+ size 619709163
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,671 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 41293685880
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "pytorch_model-00046-of-00046.bin",
7
+ "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00046.bin",
8
+ "gpt_neox.final_layer_norm.bias": "pytorch_model-00045-of-00046.bin",
9
+ "gpt_neox.final_layer_norm.weight": "pytorch_model-00045-of-00046.bin",
10
+ "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00046.bin",
11
+ "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00046.bin",
12
+ "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00046.bin",
13
+ "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00046.bin",
14
+ "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00046.bin",
15
+ "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00046.bin",
16
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00046.bin",
17
+ "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00046.bin",
18
+ "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00046.bin",
19
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00046.bin",
20
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00046.bin",
21
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00046.bin",
22
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00046.bin",
23
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00046.bin",
24
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00046.bin",
25
+ "gpt_neox.layers.1.attention.bias": "pytorch_model-00002-of-00046.bin",
26
+ "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00002-of-00046.bin",
27
+ "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00002-of-00046.bin",
28
+ "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00002-of-00046.bin",
29
+ "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00002-of-00046.bin",
30
+ "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00002-of-00046.bin",
31
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00046.bin",
32
+ "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00002-of-00046.bin",
33
+ "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00046.bin",
34
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00046.bin",
35
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00046.bin",
36
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00046.bin",
37
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00046.bin",
38
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00002-of-00046.bin",
39
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00046.bin",
40
+ "gpt_neox.layers.10.attention.bias": "pytorch_model-00011-of-00046.bin",
41
+ "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00011-of-00046.bin",
42
+ "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00011-of-00046.bin",
43
+ "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00011-of-00046.bin",
44
+ "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00011-of-00046.bin",
45
+ "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00011-of-00046.bin",
46
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00011-of-00046.bin",
47
+ "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00011-of-00046.bin",
48
+ "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00011-of-00046.bin",
49
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00046.bin",
50
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00046.bin",
51
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00046.bin",
52
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00046.bin",
53
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00011-of-00046.bin",
54
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00011-of-00046.bin",
55
+ "gpt_neox.layers.11.attention.bias": "pytorch_model-00012-of-00046.bin",
56
+ "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00012-of-00046.bin",
57
+ "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00012-of-00046.bin",
58
+ "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00012-of-00046.bin",
59
+ "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00012-of-00046.bin",
60
+ "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00012-of-00046.bin",
61
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00012-of-00046.bin",
62
+ "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00012-of-00046.bin",
63
+ "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00012-of-00046.bin",
64
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00046.bin",
65
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00046.bin",
66
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00046.bin",
67
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00046.bin",
68
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00012-of-00046.bin",
69
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00012-of-00046.bin",
70
+ "gpt_neox.layers.12.attention.bias": "pytorch_model-00013-of-00046.bin",
71
+ "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00013-of-00046.bin",
72
+ "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00013-of-00046.bin",
73
+ "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00013-of-00046.bin",
74
+ "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00013-of-00046.bin",
75
+ "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00013-of-00046.bin",
76
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00013-of-00046.bin",
77
+ "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00013-of-00046.bin",
78
+ "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00013-of-00046.bin",
79
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00046.bin",
80
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00046.bin",
81
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00046.bin",
82
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00046.bin",
83
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00013-of-00046.bin",
84
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00013-of-00046.bin",
85
+ "gpt_neox.layers.13.attention.bias": "pytorch_model-00014-of-00046.bin",
86
+ "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00014-of-00046.bin",
87
+ "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00014-of-00046.bin",
88
+ "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00014-of-00046.bin",
89
+ "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00014-of-00046.bin",
90
+ "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00014-of-00046.bin",
91
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00014-of-00046.bin",
92
+ "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00014-of-00046.bin",
93
+ "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00014-of-00046.bin",
94
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00015-of-00046.bin",
95
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00046.bin",
96
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00015-of-00046.bin",
97
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00046.bin",
98
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00014-of-00046.bin",
99
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00014-of-00046.bin",
100
+ "gpt_neox.layers.14.attention.bias": "pytorch_model-00015-of-00046.bin",
101
+ "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00015-of-00046.bin",
102
+ "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00015-of-00046.bin",
103
+ "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00015-of-00046.bin",
104
+ "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00015-of-00046.bin",
105
+ "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00015-of-00046.bin",
106
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00015-of-00046.bin",
107
+ "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00015-of-00046.bin",
108
+ "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00015-of-00046.bin",
109
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00016-of-00046.bin",
110
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00046.bin",
111
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00016-of-00046.bin",
112
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00046.bin",
113
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00015-of-00046.bin",
114
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00015-of-00046.bin",
115
+ "gpt_neox.layers.15.attention.bias": "pytorch_model-00016-of-00046.bin",
116
+ "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00016-of-00046.bin",
117
+ "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00016-of-00046.bin",
118
+ "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00016-of-00046.bin",
119
+ "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00016-of-00046.bin",
120
+ "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00016-of-00046.bin",
121
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00016-of-00046.bin",
122
+ "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00016-of-00046.bin",
123
+ "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00016-of-00046.bin",
124
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00017-of-00046.bin",
125
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00046.bin",
126
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00017-of-00046.bin",
127
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00046.bin",
128
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00016-of-00046.bin",
129
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00016-of-00046.bin",
130
+ "gpt_neox.layers.16.attention.bias": "pytorch_model-00017-of-00046.bin",
131
+ "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00017-of-00046.bin",
132
+ "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00017-of-00046.bin",
133
+ "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00017-of-00046.bin",
134
+ "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00017-of-00046.bin",
135
+ "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00017-of-00046.bin",
136
+ "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00017-of-00046.bin",
137
+ "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00017-of-00046.bin",
138
+ "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00017-of-00046.bin",
139
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00018-of-00046.bin",
140
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00046.bin",
141
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00018-of-00046.bin",
142
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00046.bin",
143
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00017-of-00046.bin",
144
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00017-of-00046.bin",
145
+ "gpt_neox.layers.17.attention.bias": "pytorch_model-00018-of-00046.bin",
146
+ "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00018-of-00046.bin",
147
+ "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00018-of-00046.bin",
148
+ "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00018-of-00046.bin",
149
+ "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00018-of-00046.bin",
150
+ "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00018-of-00046.bin",
151
+ "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00018-of-00046.bin",
152
+ "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00018-of-00046.bin",
153
+ "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00018-of-00046.bin",
154
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00019-of-00046.bin",
155
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00046.bin",
156
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00019-of-00046.bin",
157
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00046.bin",
158
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00018-of-00046.bin",
159
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00018-of-00046.bin",
160
+ "gpt_neox.layers.18.attention.bias": "pytorch_model-00019-of-00046.bin",
161
+ "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00019-of-00046.bin",
162
+ "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00019-of-00046.bin",
163
+ "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00019-of-00046.bin",
164
+ "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00019-of-00046.bin",
165
+ "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00019-of-00046.bin",
166
+ "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00019-of-00046.bin",
167
+ "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00019-of-00046.bin",
168
+ "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00019-of-00046.bin",
169
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00020-of-00046.bin",
170
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00046.bin",
171
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00020-of-00046.bin",
172
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00020-of-00046.bin",
173
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00019-of-00046.bin",
174
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00019-of-00046.bin",
175
+ "gpt_neox.layers.19.attention.bias": "pytorch_model-00020-of-00046.bin",
176
+ "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00020-of-00046.bin",
177
+ "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00020-of-00046.bin",
178
+ "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00020-of-00046.bin",
179
+ "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00020-of-00046.bin",
180
+ "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00020-of-00046.bin",
181
+ "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00020-of-00046.bin",
182
+ "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00020-of-00046.bin",
183
+ "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00020-of-00046.bin",
184
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00021-of-00046.bin",
185
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00046.bin",
186
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00021-of-00046.bin",
187
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00046.bin",
188
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00020-of-00046.bin",
189
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00020-of-00046.bin",
190
+ "gpt_neox.layers.2.attention.bias": "pytorch_model-00003-of-00046.bin",
191
+ "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00003-of-00046.bin",
192
+ "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00003-of-00046.bin",
193
+ "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00003-of-00046.bin",
194
+ "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00003-of-00046.bin",
195
+ "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00003-of-00046.bin",
196
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00046.bin",
197
+ "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00003-of-00046.bin",
198
+ "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00046.bin",
199
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00046.bin",
200
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00046.bin",
201
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00046.bin",
202
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00046.bin",
203
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00003-of-00046.bin",
204
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00046.bin",
205
+ "gpt_neox.layers.20.attention.bias": "pytorch_model-00021-of-00046.bin",
206
+ "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00021-of-00046.bin",
207
+ "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00021-of-00046.bin",
208
+ "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00021-of-00046.bin",
209
+ "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00021-of-00046.bin",
210
+ "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00021-of-00046.bin",
211
+ "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00021-of-00046.bin",
212
+ "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00021-of-00046.bin",
213
+ "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00021-of-00046.bin",
214
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00022-of-00046.bin",
215
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00046.bin",
216
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00022-of-00046.bin",
217
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00046.bin",
218
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00021-of-00046.bin",
219
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00021-of-00046.bin",
220
+ "gpt_neox.layers.21.attention.bias": "pytorch_model-00022-of-00046.bin",
221
+ "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00022-of-00046.bin",
222
+ "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00022-of-00046.bin",
223
+ "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00022-of-00046.bin",
224
+ "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00022-of-00046.bin",
225
+ "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00022-of-00046.bin",
226
+ "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00022-of-00046.bin",
227
+ "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00022-of-00046.bin",
228
+ "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00022-of-00046.bin",
229
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00023-of-00046.bin",
230
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00023-of-00046.bin",
231
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00023-of-00046.bin",
232
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00046.bin",
233
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00022-of-00046.bin",
234
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00022-of-00046.bin",
235
+ "gpt_neox.layers.22.attention.bias": "pytorch_model-00023-of-00046.bin",
236
+ "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00023-of-00046.bin",
237
+ "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00023-of-00046.bin",
238
+ "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00023-of-00046.bin",
239
+ "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00023-of-00046.bin",
240
+ "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00023-of-00046.bin",
241
+ "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00023-of-00046.bin",
242
+ "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00023-of-00046.bin",
243
+ "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00023-of-00046.bin",
244
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00024-of-00046.bin",
245
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00046.bin",
246
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00024-of-00046.bin",
247
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00024-of-00046.bin",
248
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00023-of-00046.bin",
249
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00023-of-00046.bin",
250
+ "gpt_neox.layers.23.attention.bias": "pytorch_model-00024-of-00046.bin",
251
+ "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00024-of-00046.bin",
252
+ "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00024-of-00046.bin",
253
+ "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00024-of-00046.bin",
254
+ "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00024-of-00046.bin",
255
+ "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00024-of-00046.bin",
256
+ "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00024-of-00046.bin",
257
+ "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00024-of-00046.bin",
258
+ "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00024-of-00046.bin",
259
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00025-of-00046.bin",
260
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00046.bin",
261
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00025-of-00046.bin",
262
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00046.bin",
263
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00024-of-00046.bin",
264
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00024-of-00046.bin",
265
+ "gpt_neox.layers.24.attention.bias": "pytorch_model-00025-of-00046.bin",
266
+ "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00025-of-00046.bin",
267
+ "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00025-of-00046.bin",
268
+ "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00025-of-00046.bin",
269
+ "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00025-of-00046.bin",
270
+ "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00025-of-00046.bin",
271
+ "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00025-of-00046.bin",
272
+ "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00025-of-00046.bin",
273
+ "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00025-of-00046.bin",
274
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00026-of-00046.bin",
275
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00046.bin",
276
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00026-of-00046.bin",
277
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00046.bin",
278
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00025-of-00046.bin",
279
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00025-of-00046.bin",
280
+ "gpt_neox.layers.25.attention.bias": "pytorch_model-00026-of-00046.bin",
281
+ "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00026-of-00046.bin",
282
+ "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00026-of-00046.bin",
283
+ "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00026-of-00046.bin",
284
+ "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00026-of-00046.bin",
285
+ "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00026-of-00046.bin",
286
+ "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00026-of-00046.bin",
287
+ "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00026-of-00046.bin",
288
+ "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00026-of-00046.bin",
289
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00027-of-00046.bin",
290
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00027-of-00046.bin",
291
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00027-of-00046.bin",
292
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00046.bin",
293
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00026-of-00046.bin",
294
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00026-of-00046.bin",
295
+ "gpt_neox.layers.26.attention.bias": "pytorch_model-00027-of-00046.bin",
296
+ "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00027-of-00046.bin",
297
+ "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00027-of-00046.bin",
298
+ "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00027-of-00046.bin",
299
+ "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00027-of-00046.bin",
300
+ "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00027-of-00046.bin",
301
+ "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00027-of-00046.bin",
302
+ "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00027-of-00046.bin",
303
+ "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00027-of-00046.bin",
304
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00028-of-00046.bin",
305
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00046.bin",
306
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00028-of-00046.bin",
307
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00028-of-00046.bin",
308
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00027-of-00046.bin",
309
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00027-of-00046.bin",
310
+ "gpt_neox.layers.27.attention.bias": "pytorch_model-00028-of-00046.bin",
311
+ "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00028-of-00046.bin",
312
+ "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00028-of-00046.bin",
313
+ "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00028-of-00046.bin",
314
+ "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00028-of-00046.bin",
315
+ "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00028-of-00046.bin",
316
+ "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00028-of-00046.bin",
317
+ "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00028-of-00046.bin",
318
+ "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00028-of-00046.bin",
319
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00029-of-00046.bin",
320
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00046.bin",
321
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00029-of-00046.bin",
322
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00046.bin",
323
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00028-of-00046.bin",
324
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00028-of-00046.bin",
325
+ "gpt_neox.layers.28.attention.bias": "pytorch_model-00029-of-00046.bin",
326
+ "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00029-of-00046.bin",
327
+ "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00029-of-00046.bin",
328
+ "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00029-of-00046.bin",
329
+ "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00029-of-00046.bin",
330
+ "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00029-of-00046.bin",
331
+ "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00029-of-00046.bin",
332
+ "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00029-of-00046.bin",
333
+ "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00029-of-00046.bin",
334
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00030-of-00046.bin",
335
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00046.bin",
336
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00030-of-00046.bin",
337
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00046.bin",
338
+ "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00029-of-00046.bin",
339
+ "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00029-of-00046.bin",
340
+ "gpt_neox.layers.29.attention.bias": "pytorch_model-00030-of-00046.bin",
341
+ "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00030-of-00046.bin",
342
+ "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00030-of-00046.bin",
343
+ "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00030-of-00046.bin",
344
+ "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00030-of-00046.bin",
345
+ "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00030-of-00046.bin",
346
+ "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00030-of-00046.bin",
347
+ "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00030-of-00046.bin",
348
+ "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00030-of-00046.bin",
349
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00031-of-00046.bin",
350
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00031-of-00046.bin",
351
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00031-of-00046.bin",
352
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00031-of-00046.bin",
353
+ "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00030-of-00046.bin",
354
+ "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00030-of-00046.bin",
355
+ "gpt_neox.layers.3.attention.bias": "pytorch_model-00004-of-00046.bin",
356
+ "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00004-of-00046.bin",
357
+ "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00004-of-00046.bin",
358
+ "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00004-of-00046.bin",
359
+ "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00004-of-00046.bin",
360
+ "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00004-of-00046.bin",
361
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00046.bin",
362
+ "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00004-of-00046.bin",
363
+ "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00046.bin",
364
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00046.bin",
365
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00046.bin",
366
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00046.bin",
367
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00046.bin",
368
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00004-of-00046.bin",
369
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00046.bin",
370
+ "gpt_neox.layers.30.attention.bias": "pytorch_model-00031-of-00046.bin",
371
+ "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00031-of-00046.bin",
372
+ "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00031-of-00046.bin",
373
+ "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00031-of-00046.bin",
374
+ "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00031-of-00046.bin",
375
+ "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00031-of-00046.bin",
376
+ "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00031-of-00046.bin",
377
+ "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00031-of-00046.bin",
378
+ "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00031-of-00046.bin",
379
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00032-of-00046.bin",
380
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00032-of-00046.bin",
381
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00032-of-00046.bin",
382
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00032-of-00046.bin",
383
+ "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00031-of-00046.bin",
384
+ "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00031-of-00046.bin",
385
+ "gpt_neox.layers.31.attention.bias": "pytorch_model-00032-of-00046.bin",
386
+ "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00032-of-00046.bin",
387
+ "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00032-of-00046.bin",
388
+ "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00032-of-00046.bin",
389
+ "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00032-of-00046.bin",
390
+ "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00032-of-00046.bin",
391
+ "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00032-of-00046.bin",
392
+ "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00032-of-00046.bin",
393
+ "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00032-of-00046.bin",
394
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00033-of-00046.bin",
395
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00033-of-00046.bin",
396
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00033-of-00046.bin",
397
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00033-of-00046.bin",
398
+ "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00032-of-00046.bin",
399
+ "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00032-of-00046.bin",
400
+ "gpt_neox.layers.32.attention.bias": "pytorch_model-00033-of-00046.bin",
401
+ "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00033-of-00046.bin",
402
+ "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00033-of-00046.bin",
403
+ "gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00033-of-00046.bin",
404
+ "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00033-of-00046.bin",
405
+ "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00033-of-00046.bin",
406
+ "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00033-of-00046.bin",
407
+ "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00033-of-00046.bin",
408
+ "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00033-of-00046.bin",
409
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00034-of-00046.bin",
410
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00034-of-00046.bin",
411
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00034-of-00046.bin",
412
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00034-of-00046.bin",
413
+ "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00033-of-00046.bin",
414
+ "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00033-of-00046.bin",
415
+ "gpt_neox.layers.33.attention.bias": "pytorch_model-00034-of-00046.bin",
416
+ "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00034-of-00046.bin",
417
+ "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00034-of-00046.bin",
418
+ "gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00034-of-00046.bin",
419
+ "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00034-of-00046.bin",
420
+ "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00034-of-00046.bin",
421
+ "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00034-of-00046.bin",
422
+ "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00034-of-00046.bin",
423
+ "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00034-of-00046.bin",
424
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00035-of-00046.bin",
425
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00035-of-00046.bin",
426
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00035-of-00046.bin",
427
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00035-of-00046.bin",
428
+ "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00034-of-00046.bin",
429
+ "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00034-of-00046.bin",
430
+ "gpt_neox.layers.34.attention.bias": "pytorch_model-00035-of-00046.bin",
431
+ "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00035-of-00046.bin",
432
+ "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00035-of-00046.bin",
433
+ "gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00035-of-00046.bin",
434
+ "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00035-of-00046.bin",
435
+ "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00035-of-00046.bin",
436
+ "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00035-of-00046.bin",
437
+ "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00035-of-00046.bin",
438
+ "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00035-of-00046.bin",
439
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00036-of-00046.bin",
440
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00036-of-00046.bin",
441
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00036-of-00046.bin",
442
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00036-of-00046.bin",
443
+ "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00035-of-00046.bin",
444
+ "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00035-of-00046.bin",
445
+ "gpt_neox.layers.35.attention.bias": "pytorch_model-00036-of-00046.bin",
446
+ "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00036-of-00046.bin",
447
+ "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00036-of-00046.bin",
448
+ "gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00036-of-00046.bin",
449
+ "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00036-of-00046.bin",
450
+ "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00036-of-00046.bin",
451
+ "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00036-of-00046.bin",
452
+ "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00036-of-00046.bin",
453
+ "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00036-of-00046.bin",
454
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00037-of-00046.bin",
455
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00037-of-00046.bin",
456
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00037-of-00046.bin",
457
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00037-of-00046.bin",
458
+ "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00036-of-00046.bin",
459
+ "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00036-of-00046.bin",
460
+ "gpt_neox.layers.36.attention.bias": "pytorch_model-00037-of-00046.bin",
461
+ "gpt_neox.layers.36.attention.dense.bias": "pytorch_model-00037-of-00046.bin",
462
+ "gpt_neox.layers.36.attention.dense.weight": "pytorch_model-00037-of-00046.bin",
463
+ "gpt_neox.layers.36.attention.masked_bias": "pytorch_model-00037-of-00046.bin",
464
+ "gpt_neox.layers.36.attention.query_key_value.bias": "pytorch_model-00037-of-00046.bin",
465
+ "gpt_neox.layers.36.attention.query_key_value.weight": "pytorch_model-00037-of-00046.bin",
466
+ "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "pytorch_model-00037-of-00046.bin",
467
+ "gpt_neox.layers.36.input_layernorm.bias": "pytorch_model-00037-of-00046.bin",
468
+ "gpt_neox.layers.36.input_layernorm.weight": "pytorch_model-00037-of-00046.bin",
469
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00038-of-00046.bin",
470
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00038-of-00046.bin",
471
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00038-of-00046.bin",
472
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00038-of-00046.bin",
473
+ "gpt_neox.layers.36.post_attention_layernorm.bias": "pytorch_model-00037-of-00046.bin",
474
+ "gpt_neox.layers.36.post_attention_layernorm.weight": "pytorch_model-00037-of-00046.bin",
475
+ "gpt_neox.layers.37.attention.bias": "pytorch_model-00038-of-00046.bin",
476
+ "gpt_neox.layers.37.attention.dense.bias": "pytorch_model-00038-of-00046.bin",
477
+ "gpt_neox.layers.37.attention.dense.weight": "pytorch_model-00038-of-00046.bin",
478
+ "gpt_neox.layers.37.attention.masked_bias": "pytorch_model-00038-of-00046.bin",
479
+ "gpt_neox.layers.37.attention.query_key_value.bias": "pytorch_model-00038-of-00046.bin",
480
+ "gpt_neox.layers.37.attention.query_key_value.weight": "pytorch_model-00038-of-00046.bin",
481
+ "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "pytorch_model-00038-of-00046.bin",
482
+ "gpt_neox.layers.37.input_layernorm.bias": "pytorch_model-00038-of-00046.bin",
483
+ "gpt_neox.layers.37.input_layernorm.weight": "pytorch_model-00038-of-00046.bin",
484
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00039-of-00046.bin",
485
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00039-of-00046.bin",
486
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00039-of-00046.bin",
487
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00039-of-00046.bin",
488
+ "gpt_neox.layers.37.post_attention_layernorm.bias": "pytorch_model-00038-of-00046.bin",
489
+ "gpt_neox.layers.37.post_attention_layernorm.weight": "pytorch_model-00038-of-00046.bin",
490
+ "gpt_neox.layers.38.attention.bias": "pytorch_model-00039-of-00046.bin",
491
+ "gpt_neox.layers.38.attention.dense.bias": "pytorch_model-00039-of-00046.bin",
492
+ "gpt_neox.layers.38.attention.dense.weight": "pytorch_model-00039-of-00046.bin",
493
+ "gpt_neox.layers.38.attention.masked_bias": "pytorch_model-00039-of-00046.bin",
494
+ "gpt_neox.layers.38.attention.query_key_value.bias": "pytorch_model-00039-of-00046.bin",
495
+ "gpt_neox.layers.38.attention.query_key_value.weight": "pytorch_model-00039-of-00046.bin",
496
+ "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "pytorch_model-00039-of-00046.bin",
497
+ "gpt_neox.layers.38.input_layernorm.bias": "pytorch_model-00039-of-00046.bin",
498
+ "gpt_neox.layers.38.input_layernorm.weight": "pytorch_model-00039-of-00046.bin",
499
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00040-of-00046.bin",
500
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00040-of-00046.bin",
501
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00040-of-00046.bin",
502
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00040-of-00046.bin",
503
+ "gpt_neox.layers.38.post_attention_layernorm.bias": "pytorch_model-00039-of-00046.bin",
504
+ "gpt_neox.layers.38.post_attention_layernorm.weight": "pytorch_model-00039-of-00046.bin",
505
+ "gpt_neox.layers.39.attention.bias": "pytorch_model-00040-of-00046.bin",
506
+ "gpt_neox.layers.39.attention.dense.bias": "pytorch_model-00040-of-00046.bin",
507
+ "gpt_neox.layers.39.attention.dense.weight": "pytorch_model-00040-of-00046.bin",
508
+ "gpt_neox.layers.39.attention.masked_bias": "pytorch_model-00040-of-00046.bin",
509
+ "gpt_neox.layers.39.attention.query_key_value.bias": "pytorch_model-00040-of-00046.bin",
510
+ "gpt_neox.layers.39.attention.query_key_value.weight": "pytorch_model-00040-of-00046.bin",
511
+ "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "pytorch_model-00040-of-00046.bin",
512
+ "gpt_neox.layers.39.input_layernorm.bias": "pytorch_model-00040-of-00046.bin",
513
+ "gpt_neox.layers.39.input_layernorm.weight": "pytorch_model-00040-of-00046.bin",
514
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00041-of-00046.bin",
515
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00041-of-00046.bin",
516
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00041-of-00046.bin",
517
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00041-of-00046.bin",
518
+ "gpt_neox.layers.39.post_attention_layernorm.bias": "pytorch_model-00040-of-00046.bin",
519
+ "gpt_neox.layers.39.post_attention_layernorm.weight": "pytorch_model-00040-of-00046.bin",
520
+ "gpt_neox.layers.4.attention.bias": "pytorch_model-00005-of-00046.bin",
521
+ "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00005-of-00046.bin",
522
+ "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00005-of-00046.bin",
523
+ "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00005-of-00046.bin",
524
+ "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00005-of-00046.bin",
525
+ "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00005-of-00046.bin",
526
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00046.bin",
527
+ "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00005-of-00046.bin",
528
+ "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00005-of-00046.bin",
529
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00046.bin",
530
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00046.bin",
531
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00046.bin",
532
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00046.bin",
533
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00005-of-00046.bin",
534
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00005-of-00046.bin",
535
+ "gpt_neox.layers.40.attention.bias": "pytorch_model-00041-of-00046.bin",
536
+ "gpt_neox.layers.40.attention.dense.bias": "pytorch_model-00041-of-00046.bin",
537
+ "gpt_neox.layers.40.attention.dense.weight": "pytorch_model-00041-of-00046.bin",
538
+ "gpt_neox.layers.40.attention.masked_bias": "pytorch_model-00041-of-00046.bin",
539
+ "gpt_neox.layers.40.attention.query_key_value.bias": "pytorch_model-00041-of-00046.bin",
540
+ "gpt_neox.layers.40.attention.query_key_value.weight": "pytorch_model-00041-of-00046.bin",
541
+ "gpt_neox.layers.40.attention.rotary_emb.inv_freq": "pytorch_model-00041-of-00046.bin",
542
+ "gpt_neox.layers.40.input_layernorm.bias": "pytorch_model-00041-of-00046.bin",
543
+ "gpt_neox.layers.40.input_layernorm.weight": "pytorch_model-00041-of-00046.bin",
544
+ "gpt_neox.layers.40.mlp.dense_4h_to_h.bias": "pytorch_model-00042-of-00046.bin",
545
+ "gpt_neox.layers.40.mlp.dense_4h_to_h.weight": "pytorch_model-00042-of-00046.bin",
546
+ "gpt_neox.layers.40.mlp.dense_h_to_4h.bias": "pytorch_model-00042-of-00046.bin",
547
+ "gpt_neox.layers.40.mlp.dense_h_to_4h.weight": "pytorch_model-00042-of-00046.bin",
548
+ "gpt_neox.layers.40.post_attention_layernorm.bias": "pytorch_model-00041-of-00046.bin",
549
+ "gpt_neox.layers.40.post_attention_layernorm.weight": "pytorch_model-00041-of-00046.bin",
550
+ "gpt_neox.layers.41.attention.bias": "pytorch_model-00042-of-00046.bin",
551
+ "gpt_neox.layers.41.attention.dense.bias": "pytorch_model-00042-of-00046.bin",
552
+ "gpt_neox.layers.41.attention.dense.weight": "pytorch_model-00042-of-00046.bin",
553
+ "gpt_neox.layers.41.attention.masked_bias": "pytorch_model-00042-of-00046.bin",
554
+ "gpt_neox.layers.41.attention.query_key_value.bias": "pytorch_model-00042-of-00046.bin",
555
+ "gpt_neox.layers.41.attention.query_key_value.weight": "pytorch_model-00042-of-00046.bin",
556
+ "gpt_neox.layers.41.attention.rotary_emb.inv_freq": "pytorch_model-00042-of-00046.bin",
557
+ "gpt_neox.layers.41.input_layernorm.bias": "pytorch_model-00042-of-00046.bin",
558
+ "gpt_neox.layers.41.input_layernorm.weight": "pytorch_model-00042-of-00046.bin",
559
+ "gpt_neox.layers.41.mlp.dense_4h_to_h.bias": "pytorch_model-00043-of-00046.bin",
560
+ "gpt_neox.layers.41.mlp.dense_4h_to_h.weight": "pytorch_model-00043-of-00046.bin",
561
+ "gpt_neox.layers.41.mlp.dense_h_to_4h.bias": "pytorch_model-00043-of-00046.bin",
562
+ "gpt_neox.layers.41.mlp.dense_h_to_4h.weight": "pytorch_model-00043-of-00046.bin",
563
+ "gpt_neox.layers.41.post_attention_layernorm.bias": "pytorch_model-00042-of-00046.bin",
564
+ "gpt_neox.layers.41.post_attention_layernorm.weight": "pytorch_model-00042-of-00046.bin",
565
+ "gpt_neox.layers.42.attention.bias": "pytorch_model-00043-of-00046.bin",
566
+ "gpt_neox.layers.42.attention.dense.bias": "pytorch_model-00043-of-00046.bin",
567
+ "gpt_neox.layers.42.attention.dense.weight": "pytorch_model-00043-of-00046.bin",
568
+ "gpt_neox.layers.42.attention.masked_bias": "pytorch_model-00043-of-00046.bin",
569
+ "gpt_neox.layers.42.attention.query_key_value.bias": "pytorch_model-00043-of-00046.bin",
570
+ "gpt_neox.layers.42.attention.query_key_value.weight": "pytorch_model-00043-of-00046.bin",
571
+ "gpt_neox.layers.42.attention.rotary_emb.inv_freq": "pytorch_model-00043-of-00046.bin",
572
+ "gpt_neox.layers.42.input_layernorm.bias": "pytorch_model-00043-of-00046.bin",
573
+ "gpt_neox.layers.42.input_layernorm.weight": "pytorch_model-00043-of-00046.bin",
574
+ "gpt_neox.layers.42.mlp.dense_4h_to_h.bias": "pytorch_model-00044-of-00046.bin",
575
+ "gpt_neox.layers.42.mlp.dense_4h_to_h.weight": "pytorch_model-00044-of-00046.bin",
576
+ "gpt_neox.layers.42.mlp.dense_h_to_4h.bias": "pytorch_model-00044-of-00046.bin",
577
+ "gpt_neox.layers.42.mlp.dense_h_to_4h.weight": "pytorch_model-00044-of-00046.bin",
578
+ "gpt_neox.layers.42.post_attention_layernorm.bias": "pytorch_model-00043-of-00046.bin",
579
+ "gpt_neox.layers.42.post_attention_layernorm.weight": "pytorch_model-00043-of-00046.bin",
580
+ "gpt_neox.layers.43.attention.bias": "pytorch_model-00044-of-00046.bin",
581
+ "gpt_neox.layers.43.attention.dense.bias": "pytorch_model-00044-of-00046.bin",
582
+ "gpt_neox.layers.43.attention.dense.weight": "pytorch_model-00044-of-00046.bin",
583
+ "gpt_neox.layers.43.attention.masked_bias": "pytorch_model-00044-of-00046.bin",
584
+ "gpt_neox.layers.43.attention.query_key_value.bias": "pytorch_model-00044-of-00046.bin",
585
+ "gpt_neox.layers.43.attention.query_key_value.weight": "pytorch_model-00044-of-00046.bin",
586
+ "gpt_neox.layers.43.attention.rotary_emb.inv_freq": "pytorch_model-00044-of-00046.bin",
587
+ "gpt_neox.layers.43.input_layernorm.bias": "pytorch_model-00044-of-00046.bin",
588
+ "gpt_neox.layers.43.input_layernorm.weight": "pytorch_model-00044-of-00046.bin",
589
+ "gpt_neox.layers.43.mlp.dense_4h_to_h.bias": "pytorch_model-00045-of-00046.bin",
590
+ "gpt_neox.layers.43.mlp.dense_4h_to_h.weight": "pytorch_model-00045-of-00046.bin",
591
+ "gpt_neox.layers.43.mlp.dense_h_to_4h.bias": "pytorch_model-00045-of-00046.bin",
592
+ "gpt_neox.layers.43.mlp.dense_h_to_4h.weight": "pytorch_model-00045-of-00046.bin",
593
+ "gpt_neox.layers.43.post_attention_layernorm.bias": "pytorch_model-00044-of-00046.bin",
594
+ "gpt_neox.layers.43.post_attention_layernorm.weight": "pytorch_model-00044-of-00046.bin",
595
+ "gpt_neox.layers.5.attention.bias": "pytorch_model-00006-of-00046.bin",
596
+ "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00006-of-00046.bin",
597
+ "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00006-of-00046.bin",
598
+ "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00006-of-00046.bin",
599
+ "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00006-of-00046.bin",
600
+ "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00006-of-00046.bin",
601
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00046.bin",
602
+ "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00006-of-00046.bin",
603
+ "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00006-of-00046.bin",
604
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00046.bin",
605
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00046.bin",
606
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00046.bin",
607
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00046.bin",
608
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00006-of-00046.bin",
609
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00006-of-00046.bin",
610
+ "gpt_neox.layers.6.attention.bias": "pytorch_model-00007-of-00046.bin",
611
+ "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00007-of-00046.bin",
612
+ "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00007-of-00046.bin",
613
+ "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00007-of-00046.bin",
614
+ "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00007-of-00046.bin",
615
+ "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00007-of-00046.bin",
616
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00046.bin",
617
+ "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00007-of-00046.bin",
618
+ "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00007-of-00046.bin",
619
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00046.bin",
620
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00046.bin",
621
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00046.bin",
622
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00046.bin",
623
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00007-of-00046.bin",
624
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00007-of-00046.bin",
625
+ "gpt_neox.layers.7.attention.bias": "pytorch_model-00008-of-00046.bin",
626
+ "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00008-of-00046.bin",
627
+ "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00008-of-00046.bin",
628
+ "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00008-of-00046.bin",
629
+ "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00008-of-00046.bin",
630
+ "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00008-of-00046.bin",
631
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00046.bin",
632
+ "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00008-of-00046.bin",
633
+ "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00008-of-00046.bin",
634
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00046.bin",
635
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00046.bin",
636
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00046.bin",
637
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00046.bin",
638
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00008-of-00046.bin",
639
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00008-of-00046.bin",
640
+ "gpt_neox.layers.8.attention.bias": "pytorch_model-00009-of-00046.bin",
641
+ "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00009-of-00046.bin",
642
+ "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00009-of-00046.bin",
643
+ "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00009-of-00046.bin",
644
+ "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00009-of-00046.bin",
645
+ "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00009-of-00046.bin",
646
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00009-of-00046.bin",
647
+ "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00009-of-00046.bin",
648
+ "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00009-of-00046.bin",
649
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00046.bin",
650
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00046.bin",
651
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00046.bin",
652
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00046.bin",
653
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00009-of-00046.bin",
654
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00009-of-00046.bin",
655
+ "gpt_neox.layers.9.attention.bias": "pytorch_model-00010-of-00046.bin",
656
+ "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00010-of-00046.bin",
657
+ "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00010-of-00046.bin",
658
+ "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00010-of-00046.bin",
659
+ "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00010-of-00046.bin",
660
+ "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00010-of-00046.bin",
661
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00010-of-00046.bin",
662
+ "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00010-of-00046.bin",
663
+ "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00010-of-00046.bin",
664
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00046.bin",
665
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00046.bin",
666
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00046.bin",
667
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00046.bin",
668
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00010-of-00046.bin",
669
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00010-of-00046.bin"
670
+ }
671
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff