kolinko commited on
Commit
a873fea
·
1 Parent(s): cd665a4

initial commit

Browse files
Files changed (33) hide show
  1. buckets-FP16-00001-of-00032.safetensors +3 -0
  2. buckets-FP16-00002-of-00032.safetensors +3 -0
  3. buckets-FP16-00003-of-00032.safetensors +3 -0
  4. buckets-FP16-00004-of-00032.safetensors +3 -0
  5. buckets-FP16-00005-of-00032.safetensors +3 -0
  6. buckets-FP16-00006-of-00032.safetensors +3 -0
  7. buckets-FP16-00007-of-00032.safetensors +3 -0
  8. buckets-FP16-00008-of-00032.safetensors +3 -0
  9. buckets-FP16-00009-of-00032.safetensors +3 -0
  10. buckets-FP16-00010-of-00032.safetensors +3 -0
  11. buckets-FP16-00011-of-00032.safetensors +3 -0
  12. buckets-FP16-00012-of-00032.safetensors +3 -0
  13. buckets-FP16-00013-of-00032.safetensors +3 -0
  14. buckets-FP16-00014-of-00032.safetensors +3 -0
  15. buckets-FP16-00015-of-00032.safetensors +3 -0
  16. buckets-FP16-00016-of-00032.safetensors +3 -0
  17. buckets-FP16-00017-of-00032.safetensors +3 -0
  18. buckets-FP16-00018-of-00032.safetensors +3 -0
  19. buckets-FP16-00019-of-00032.safetensors +3 -0
  20. buckets-FP16-00020-of-00032.safetensors +3 -0
  21. buckets-FP16-00021-of-00032.safetensors +3 -0
  22. buckets-FP16-00022-of-00032.safetensors +3 -0
  23. buckets-FP16-00023-of-00032.safetensors +3 -0
  24. buckets-FP16-00024-of-00032.safetensors +3 -0
  25. buckets-FP16-00025-of-00032.safetensors +3 -0
  26. buckets-FP16-00026-of-00032.safetensors +3 -0
  27. buckets-FP16-00027-of-00032.safetensors +3 -0
  28. buckets-FP16-00028-of-00032.safetensors +3 -0
  29. buckets-FP16-00029-of-00032.safetensors +3 -0
  30. buckets-FP16-00030-of-00032.safetensors +3 -0
  31. buckets-FP16-00031-of-00032.safetensors +3 -0
  32. buckets-FP16-00032-of-00032.safetensors +3 -0
  33. buckets-FP16.safetensors.index.json +871 -0
buckets-FP16-00001-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8598cc7aaf83e9ed4bc6085468be03cb857b04a30d2a7d5d6b028ff46da7dacf
3
+ size 1049447580
buckets-FP16-00002-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f29a1da019768c723eb157bc047eb3386542bf82826de21115a8af8fc93a0a8
3
+ size 525151132
buckets-FP16-00003-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:610177344ba44d20881ba6545b09dc3352889571b345b761eca80c6a22e8a383
3
+ size 525151134
buckets-FP16-00004-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0650694e056ab77ed82ab8140cd9d9a0f7c659bb8cf280100bf5895f280a79d6
3
+ size 525151138
buckets-FP16-00005-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f97fb8ec49ad6e7e2e8c5657634a2fbd0e1b1f0c3dcc1606fe30f13b94efe78e
3
+ size 525151086
buckets-FP16-00006-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152852b42d84f072a2bcb1a9e492d35eab985d20cc3bb73dd6594ebf92c849d0
3
+ size 525151104
buckets-FP16-00007-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2b0c90b1408c1811d22868e9eed819be5855018242d30e8aa83d54aa1c53bd
3
+ size 525151126
buckets-FP16-00008-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dfccfd742c888ea9dc43337afe0159c747fdf23f67aefd3c39d3fbb92815800
3
+ size 525151108
buckets-FP16-00009-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11574b18c32f09ffccad086c8f06e9cf78ed970f7533b9066c2736905e6ea2d
3
+ size 525151112
buckets-FP16-00010-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe5f533ae2187fa2aeeebedb6a8f0d764ed2151989ead97a53f61f19fd2b091
3
+ size 525151106
buckets-FP16-00011-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb729e3937758d35a704f6001bc888b1034de2a93b22e6e347ede2d520986143
3
+ size 525151139
buckets-FP16-00012-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f95f2cd1a8956f8a483c5714eb036b3c2089530db18533f79fd2377a6041cb
3
+ size 525151165
buckets-FP16-00013-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7329b47836cf1b48239a4fa8e3773b65b2827d94617babafbe0de6fbf5c9926
3
+ size 525151139
buckets-FP16-00014-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66badfe9545e172e1d8d1ac05e8a0a3edc0f491549a91371ccefc34716bd4932
3
+ size 525151127
buckets-FP16-00015-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7450ff32780c28f17bf9ba8e1598db78622cd6ec3337d0f283e249bdca753ea
3
+ size 525151129
buckets-FP16-00016-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:320d3d84907af71774716b231075993dca0e24039881db2c011bda123708245d
3
+ size 525151131
buckets-FP16-00017-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8bdfb80cf8cb66997e03825bf82432fd20efe85606b139bf370fed730762ca5
3
+ size 525151155
buckets-FP16-00018-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5925e4f7d9d6113c9b3192979b33b7dbc6d05ad543e551ac33eb0d88b971d7a
3
+ size 525151153
buckets-FP16-00019-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46b5c839423724934c5f06bdc9d05148ddcad9389731e423cfb25d6fca6550d
3
+ size 525151121
buckets-FP16-00020-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3cc78b92b2fc0951b2ecc27d972c734b760035906aa6eaca0f0288d441f11d6
3
+ size 525151125
buckets-FP16-00021-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb241ceaf617baeb4675b3cba4765815d04256bd72dc9dd0f27d524c94b6287f
3
+ size 525151141
buckets-FP16-00022-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1127824500672194f3fd2e83a48f5bc50a6140073203c05f977afbba1ba54889
3
+ size 525151143
buckets-FP16-00023-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:092f2b6149420e77a09b1122e6f74d251b6146461e4881cb8c615936241e2093
3
+ size 525151143
buckets-FP16-00024-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d021e1cdc18dc64432ed314c9bbf56c2fe01dac02143b241cce7d9227f4d27
3
+ size 525151165
buckets-FP16-00025-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c70a1643257b0cf5757eb8cab8ea35d7d656500f6ccb41547af10d74c396ab
3
+ size 525151153
buckets-FP16-00026-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6a718fa5a3ea01c54725c5047ed7a7b66799dfaa29e1b7d7e2008381f790c2
3
+ size 525151165
buckets-FP16-00027-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c840838d3a0cc6c38ffafdf103f62a63f050c6b469eec0a08d7f899e580c3386
3
+ size 525151147
buckets-FP16-00028-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecfbe579beda6b7f4e8707928fa3cc7d4d07e170db904f24ce7bd96fdcbbed65
3
+ size 525151147
buckets-FP16-00029-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf2754dcfd209b3363942bec6155d04698d1d0a9e0b138df65821b73427da0e
3
+ size 525151143
buckets-FP16-00030-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:305aa8d83a8a3a35ec43b93813e031dbd573142517d58f4c4d62a12204ad889c
3
+ size 525151125
buckets-FP16-00031-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f9f96234a50d68f29ee40fd5ac0dd4babfb832e802dbcf26e1b04d9535faf1
3
+ size 525151165
buckets-FP16-00032-of-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dae431c5dc1006bc9fb2dbd004f99b53baff3a91facfbef16cd4efd2f52e25d4
3
+ size 525151139
buckets-FP16.safetensors.index.json ADDED
@@ -0,0 +1,871 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map" : {
3
+ "layers.24.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00025-of-00032.safetensors",
4
+ "layers.16.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00017-of-00032.safetensors",
5
+ "layers.24.attention.wv.bucket.stats" : "buckets-FP16-00025-of-00032.safetensors",
6
+ "layers.16.attention.wo.probes" : "buckets-FP16-00017-of-00032.safetensors",
7
+ "layers.27.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00028-of-00032.safetensors",
8
+ "layers.28.attention.wo.buckets" : "buckets-FP16-00029-of-00032.safetensors",
9
+ "layers.1.attention.wq.buckets" : "buckets-FP16-00002-of-00032.safetensors",
10
+ "layers.22.feed_forward.experts.0.w2.probes" : "buckets-FP16-00023-of-00032.safetensors",
11
+ "layers.8.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00009-of-00032.safetensors",
12
+ "layers.6.attention.wq.buckets" : "buckets-FP16-00007-of-00032.safetensors",
13
+ "layers.17.attention.wv.core" : "buckets-FP16-00018-of-00032.safetensors",
14
+ "layers.0.attention.wq.core" : "buckets-FP16-00001-of-00032.safetensors",
15
+ "layers.18.attention.wq.core" : "buckets-FP16-00019-of-00032.safetensors",
16
+ "layers.15.attention.wo.core" : "buckets-FP16-00016-of-00032.safetensors",
17
+ "layers.19.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00020-of-00032.safetensors",
18
+ "layers.1.feed_forward.experts.0.w1.probes" : "buckets-FP16-00002-of-00032.safetensors",
19
+ "layers.12.attention_norm" : "buckets-FP16-00013-of-00032.safetensors",
20
+ "layers.13.attention.wq.core" : "buckets-FP16-00014-of-00032.safetensors",
21
+ "layers.6.attention.wo.buckets" : "buckets-FP16-00007-of-00032.safetensors",
22
+ "layers.22.attention.wo.buckets" : "buckets-FP16-00023-of-00032.safetensors",
23
+ "layers.20.attention.wv.bucket.stats" : "buckets-FP16-00021-of-00032.safetensors",
24
+ "layers.14.attention.wo.probes" : "buckets-FP16-00015-of-00032.safetensors",
25
+ "layers.28.attention.wq.core" : "buckets-FP16-00029-of-00032.safetensors",
26
+ "layers.19.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00020-of-00032.safetensors",
27
+ "layers.6.attention.wv.buckets" : "buckets-FP16-00007-of-00032.safetensors",
28
+ "layers.2.attention.wq.buckets" : "buckets-FP16-00003-of-00032.safetensors",
29
+ "layers.26.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00027-of-00032.safetensors",
30
+ "layers.5.attention.wv.core" : "buckets-FP16-00006-of-00032.safetensors",
31
+ "layers.0.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00001-of-00032.safetensors",
32
+ "layers.24.attention.wq.bucket.stats" : "buckets-FP16-00025-of-00032.safetensors",
33
+ "layers.19.attention.wv.bucket.stats" : "buckets-FP16-00020-of-00032.safetensors",
34
+ "layers.30.attention.wo.bucket.stats" : "buckets-FP16-00031-of-00032.safetensors",
35
+ "layers.3.attention.wk.buckets" : "buckets-FP16-00004-of-00032.safetensors",
36
+ "layers.13.attention.wq.buckets" : "buckets-FP16-00014-of-00032.safetensors",
37
+ "layers.16.attention.wq.bucket.stats" : "buckets-FP16-00017-of-00032.safetensors",
38
+ "layers.20.attention.wo.bucket.stats" : "buckets-FP16-00021-of-00032.safetensors",
39
+ "layers.16.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00017-of-00032.safetensors",
40
+ "layers.19.attention.wo.buckets" : "buckets-FP16-00020-of-00032.safetensors",
41
+ "layers.6.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00007-of-00032.safetensors",
42
+ "layers.17.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00018-of-00032.safetensors",
43
+ "layers.31.attention.wk.buckets" : "buckets-FP16-00032-of-00032.safetensors",
44
+ "layers.17.attention_norm" : "buckets-FP16-00018-of-00032.safetensors",
45
+ "layers.24.attention.wk.bucket.stats" : "buckets-FP16-00025-of-00032.safetensors",
46
+ "layers.23.attention.wo.bucket.stats" : "buckets-FP16-00024-of-00032.safetensors",
47
+ "layers.1.attention.wo.probes" : "buckets-FP16-00002-of-00032.safetensors",
48
+ "layers.19.attention.wv.probes" : "buckets-FP16-00020-of-00032.safetensors",
49
+ "layers.31.ffn_norm" : "buckets-FP16-00032-of-00032.safetensors",
50
+ "layers.25.feed_forward.experts.0.w3.probes" : "buckets-FP16-00026-of-00032.safetensors",
51
+ "layers.10.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00011-of-00032.safetensors",
52
+ "layers.29.attention.wo.bucket.stats" : "buckets-FP16-00030-of-00032.safetensors",
53
+ "layers.9.attention.wo.bucket.stats" : "buckets-FP16-00010-of-00032.safetensors",
54
+ "layers.11.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00012-of-00032.safetensors",
55
+ "layers.10.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00011-of-00032.safetensors",
56
+ "layers.27.attention.wq.buckets" : "buckets-FP16-00028-of-00032.safetensors",
57
+ "layers.1.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00002-of-00032.safetensors",
58
+ "layers.22.attention.wq.bucket.stats" : "buckets-FP16-00023-of-00032.safetensors",
59
+ "layers.25.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00026-of-00032.safetensors",
60
+ "layers.27.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00028-of-00032.safetensors",
61
+ "layers.23.attention.wo.buckets" : "buckets-FP16-00024-of-00032.safetensors",
62
+ "layers.13.attention.wq.probes" : "buckets-FP16-00014-of-00032.safetensors",
63
+ "layers.18.attention.wv.probes" : "buckets-FP16-00019-of-00032.safetensors",
64
+ "layers.14.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00015-of-00032.safetensors",
65
+ "layers.8.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00009-of-00032.safetensors",
66
+ "layers.14.attention.wo.buckets" : "buckets-FP16-00015-of-00032.safetensors",
67
+ "layers.9.attention.wo.buckets" : "buckets-FP16-00010-of-00032.safetensors",
68
+ "layers.13.attention.wo.buckets" : "buckets-FP16-00014-of-00032.safetensors",
69
+ "layers.18.attention.wk.buckets" : "buckets-FP16-00019-of-00032.safetensors",
70
+ "layers.15.attention.wv.buckets" : "buckets-FP16-00016-of-00032.safetensors",
71
+ "layers.25.attention.wk.core" : "buckets-FP16-00026-of-00032.safetensors",
72
+ "layers.21.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00022-of-00032.safetensors",
73
+ "layers.25.attention.wk.bucket.stats" : "buckets-FP16-00026-of-00032.safetensors",
74
+ "layers.2.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00003-of-00032.safetensors",
75
+ "layers.28.attention.wo.core" : "buckets-FP16-00029-of-00032.safetensors",
76
+ "layers.7.attention.wo.buckets" : "buckets-FP16-00008-of-00032.safetensors",
77
+ "layers.21.feed_forward.experts.0.w3.probes" : "buckets-FP16-00022-of-00032.safetensors",
78
+ "layers.7.attention.wo.core" : "buckets-FP16-00008-of-00032.safetensors",
79
+ "layers.5.ffn_norm" : "buckets-FP16-00006-of-00032.safetensors",
80
+ "layers.29.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00030-of-00032.safetensors",
81
+ "layers.25.attention.wo.bucket.stats" : "buckets-FP16-00026-of-00032.safetensors",
82
+ "layers.2.attention.wq.core" : "buckets-FP16-00003-of-00032.safetensors",
83
+ "layers.28.attention.wq.probes" : "buckets-FP16-00029-of-00032.safetensors",
84
+ "layers.4.attention.wo.buckets" : "buckets-FP16-00005-of-00032.safetensors",
85
+ "layers.13.attention.wo.core" : "buckets-FP16-00014-of-00032.safetensors",
86
+ "layers.15.attention.wq.bucket.stats" : "buckets-FP16-00016-of-00032.safetensors",
87
+ "layers.5.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00006-of-00032.safetensors",
88
+ "layers.3.ffn_norm" : "buckets-FP16-00004-of-00032.safetensors",
89
+ "layers.28.attention.wv.bucket.stats" : "buckets-FP16-00029-of-00032.safetensors",
90
+ "layers.10.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00011-of-00032.safetensors",
91
+ "layers.14.feed_forward.experts.0.w2.probes" : "buckets-FP16-00015-of-00032.safetensors",
92
+ "layers.24.attention.wv.probes" : "buckets-FP16-00025-of-00032.safetensors",
93
+ "layers.17.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00018-of-00032.safetensors",
94
+ "layers.8.attention.wk.probes" : "buckets-FP16-00009-of-00032.safetensors",
95
+ "layers.29.attention.wo.buckets" : "buckets-FP16-00030-of-00032.safetensors",
96
+ "layers.9.attention.wq.bucket.stats" : "buckets-FP16-00010-of-00032.safetensors",
97
+ "layers.11.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00012-of-00032.safetensors",
98
+ "layers.20.attention.wq.buckets" : "buckets-FP16-00021-of-00032.safetensors",
99
+ "layers.7.attention.wv.bucket.stats" : "buckets-FP16-00008-of-00032.safetensors",
100
+ "layers.5.attention.wq.core" : "buckets-FP16-00006-of-00032.safetensors",
101
+ "layers.11.attention.wo.core" : "buckets-FP16-00012-of-00032.safetensors",
102
+ "layers.4.attention.wv.buckets" : "buckets-FP16-00005-of-00032.safetensors",
103
+ "layers.6.feed_forward.experts.0.w1.probes" : "buckets-FP16-00007-of-00032.safetensors",
104
+ "layers.6.attention.wo.probes" : "buckets-FP16-00007-of-00032.safetensors",
105
+ "layers.31.feed_forward.experts.0.w2.probes" : "buckets-FP16-00032-of-00032.safetensors",
106
+ "layers.20.attention.wk.buckets" : "buckets-FP16-00021-of-00032.safetensors",
107
+ "layers.12.attention.wv.buckets" : "buckets-FP16-00013-of-00032.safetensors",
108
+ "layers.1.attention.wv.bucket.stats" : "buckets-FP16-00002-of-00032.safetensors",
109
+ "layers.16.attention_norm" : "buckets-FP16-00017-of-00032.safetensors",
110
+ "layers.7.attention.wq.core" : "buckets-FP16-00008-of-00032.safetensors",
111
+ "layers.29.feed_forward.experts.0.w1.probes" : "buckets-FP16-00030-of-00032.safetensors",
112
+ "layers.23.ffn_norm" : "buckets-FP16-00024-of-00032.safetensors",
113
+ "layers.1.attention.wk.bucket.stats" : "buckets-FP16-00002-of-00032.safetensors",
114
+ "layers.10.feed_forward.experts.0.w2.probes" : "buckets-FP16-00011-of-00032.safetensors",
115
+ "layers.23.attention.wk.core" : "buckets-FP16-00024-of-00032.safetensors",
116
+ "layers.17.attention.wv.probes" : "buckets-FP16-00018-of-00032.safetensors",
117
+ "layers.19.attention.wk.buckets" : "buckets-FP16-00020-of-00032.safetensors",
118
+ "layers.20.attention.wq.core" : "buckets-FP16-00021-of-00032.safetensors",
119
+ "layers.20.attention.wo.buckets" : "buckets-FP16-00021-of-00032.safetensors",
120
+ "layers.16.attention.wk.bucket.stats" : "buckets-FP16-00017-of-00032.safetensors",
121
+ "layers.1.attention.wq.bucket.stats" : "buckets-FP16-00002-of-00032.safetensors",
122
+ "layers.11.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00012-of-00032.safetensors",
123
+ "layers.14.attention.wv.buckets" : "buckets-FP16-00015-of-00032.safetensors",
124
+ "layers.13.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00014-of-00032.safetensors",
125
+ "layers.10.attention.wq.probes" : "buckets-FP16-00011-of-00032.safetensors",
126
+ "layers.9.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00010-of-00032.safetensors",
127
+ "layers.12.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00013-of-00032.safetensors",
128
+ "layers.18.attention.wv.bucket.stats" : "buckets-FP16-00019-of-00032.safetensors",
129
+ "layers.31.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00032-of-00032.safetensors",
130
+ "layers.6.attention.wk.buckets" : "buckets-FP16-00007-of-00032.safetensors",
131
+ "layers.30.attention.wv.bucket.stats" : "buckets-FP16-00031-of-00032.safetensors",
132
+ "layers.13.attention.wq.bucket.stats" : "buckets-FP16-00014-of-00032.safetensors",
133
+ "layers.6.attention.wq.core" : "buckets-FP16-00007-of-00032.safetensors",
134
+ "layers.9.attention.wq.core" : "buckets-FP16-00010-of-00032.safetensors",
135
+ "layers.21.attention.wq.bucket.stats" : "buckets-FP16-00022-of-00032.safetensors",
136
+ "layers.21.attention.wo.probes" : "buckets-FP16-00022-of-00032.safetensors",
137
+ "layers.18.attention.wo.probes" : "buckets-FP16-00019-of-00032.safetensors",
138
+ "layers.8.attention.wv.bucket.stats" : "buckets-FP16-00009-of-00032.safetensors",
139
+ "layers.16.attention.wq.probes" : "buckets-FP16-00017-of-00032.safetensors",
140
+ "layers.0.attention_norm" : "buckets-FP16-00001-of-00032.safetensors",
141
+ "layers.20.attention.wv.probes" : "buckets-FP16-00021-of-00032.safetensors",
142
+ "layers.19.attention.wk.core" : "buckets-FP16-00020-of-00032.safetensors",
143
+ "layers.31.feed_forward.experts.0.w3.probes" : "buckets-FP16-00032-of-00032.safetensors",
144
+ "layers.4.attention.wq.bucket.stats" : "buckets-FP16-00005-of-00032.safetensors",
145
+ "layers.19.attention.wq.bucket.stats" : "buckets-FP16-00020-of-00032.safetensors",
146
+ "layers.31.attention.wq.core" : "buckets-FP16-00032-of-00032.safetensors",
147
+ "layers.30.attention.wk.bucket.stats" : "buckets-FP16-00031-of-00032.safetensors",
148
+ "layers.19.attention.wq.core" : "buckets-FP16-00020-of-00032.safetensors",
149
+ "layers.23.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00024-of-00032.safetensors",
150
+ "layers.29.attention.wv.core" : "buckets-FP16-00030-of-00032.safetensors",
151
+ "layers.11.attention.wk.bucket.stats" : "buckets-FP16-00012-of-00032.safetensors",
152
+ "layers.20.attention.wv.core" : "buckets-FP16-00021-of-00032.safetensors",
153
+ "layers.7.feed_forward.experts.0.w2.probes" : "buckets-FP16-00008-of-00032.safetensors",
154
+ "layers.16.attention.wo.core" : "buckets-FP16-00017-of-00032.safetensors",
155
+ "layers.15.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00016-of-00032.safetensors",
156
+ "layers.16.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00017-of-00032.safetensors",
157
+ "layers.21.attention.wk.core" : "buckets-FP16-00022-of-00032.safetensors",
158
+ "layers.25.attention.wv.buckets" : "buckets-FP16-00026-of-00032.safetensors",
159
+ "layers.22.attention_norm" : "buckets-FP16-00023-of-00032.safetensors",
160
+ "layers.3.feed_forward.experts.0.w2.probes" : "buckets-FP16-00004-of-00032.safetensors",
161
+ "layers.6.feed_forward.experts.0.w2.probes" : "buckets-FP16-00007-of-00032.safetensors",
162
+ "layers.7.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00008-of-00032.safetensors",
163
+ "layers.2.attention.wo.bucket.stats" : "buckets-FP16-00003-of-00032.safetensors",
164
+ "layers.11.attention.wq.buckets" : "buckets-FP16-00012-of-00032.safetensors",
165
+ "layers.21.attention_norm" : "buckets-FP16-00022-of-00032.safetensors",
166
+ "layers.15.attention.wk.bucket.stats" : "buckets-FP16-00016-of-00032.safetensors",
167
+ "layers.2.attention.wv.probes" : "buckets-FP16-00003-of-00032.safetensors",
168
+ "layers.2.feed_forward.experts.0.w1.probes" : "buckets-FP16-00003-of-00032.safetensors",
169
+ "layers.10.attention.wo.bucket.stats" : "buckets-FP16-00011-of-00032.safetensors",
170
+ "layers.12.attention.wo.bucket.stats" : "buckets-FP16-00013-of-00032.safetensors",
171
+ "layers.12.ffn_norm" : "buckets-FP16-00013-of-00032.safetensors",
172
+ "layers.3.attention.wq.buckets" : "buckets-FP16-00004-of-00032.safetensors",
173
+ "layers.13.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00014-of-00032.safetensors",
174
+ "layers.28.attention.wv.probes" : "buckets-FP16-00029-of-00032.safetensors",
175
+ "layers.2.attention.wo.core" : "buckets-FP16-00003-of-00032.safetensors",
176
+ "layers.10.attention.wo.core" : "buckets-FP16-00011-of-00032.safetensors",
177
+ "layers.18.attention.wo.bucket.stats" : "buckets-FP16-00019-of-00032.safetensors",
178
+ "layers.9.ffn_norm" : "buckets-FP16-00010-of-00032.safetensors",
179
+ "layers.15.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00016-of-00032.safetensors",
180
+ "layers.26.attention.wk.bucket.stats" : "buckets-FP16-00027-of-00032.safetensors",
181
+ "layers.26.attention.wv.bucket.stats" : "buckets-FP16-00027-of-00032.safetensors",
182
+ "layers.21.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00022-of-00032.safetensors",
183
+ "layers.2.attention.wv.buckets" : "buckets-FP16-00003-of-00032.safetensors",
184
+ "layers.31.attention.wv.probes" : "buckets-FP16-00032-of-00032.safetensors",
185
+ "layers.18.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00019-of-00032.safetensors",
186
+ "layers.4.feed_forward.experts.0.w3.probes" : "buckets-FP16-00005-of-00032.safetensors",
187
+ "layers.27.attention.wk.probes" : "buckets-FP16-00028-of-00032.safetensors",
188
+ "layers.1.attention.wv.core" : "buckets-FP16-00002-of-00032.safetensors",
189
+ "layers.12.feed_forward.experts.0.w3.probes" : "buckets-FP16-00013-of-00032.safetensors",
190
+ "layers.15.attention_norm" : "buckets-FP16-00016-of-00032.safetensors",
191
+ "layers.3.attention.wq.bucket.stats" : "buckets-FP16-00004-of-00032.safetensors",
192
+ "layers.10.attention.wo.buckets" : "buckets-FP16-00011-of-00032.safetensors",
193
+ "layers.11.feed_forward.experts.0.w2.probes" : "buckets-FP16-00012-of-00032.safetensors",
194
+ "layers.14.attention.wq.core" : "buckets-FP16-00015-of-00032.safetensors",
195
+ "layers.13.attention.wv.core" : "buckets-FP16-00014-of-00032.safetensors",
196
+ "layers.14.attention_norm" : "buckets-FP16-00015-of-00032.safetensors",
197
+ "layers.28.attention.wk.bucket.stats" : "buckets-FP16-00029-of-00032.safetensors",
198
+ "layers.1.attention.wk.probes" : "buckets-FP16-00002-of-00032.safetensors",
199
+ "layers.1.attention.wk.core" : "buckets-FP16-00002-of-00032.safetensors",
200
+ "layers.27.attention.wv.bucket.stats" : "buckets-FP16-00028-of-00032.safetensors",
201
+ "layers.0.feed_forward.experts.0.w2.probes" : "buckets-FP16-00001-of-00032.safetensors",
202
+ "layers.4.attention.wo.core" : "buckets-FP16-00005-of-00032.safetensors",
203
+ "layers.3.attention.wq.core" : "buckets-FP16-00004-of-00032.safetensors",
204
+ "layers.15.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00016-of-00032.safetensors",
205
+ "layers.28.attention.wk.probes" : "buckets-FP16-00029-of-00032.safetensors",
206
+ "layers.8.attention.wq.buckets" : "buckets-FP16-00009-of-00032.safetensors",
207
+ "layers.12.attention.wk.core" : "buckets-FP16-00013-of-00032.safetensors",
208
+ "layers.6.attention_norm" : "buckets-FP16-00007-of-00032.safetensors",
209
+ "layers.12.attention.wq.bucket.stats" : "buckets-FP16-00013-of-00032.safetensors",
210
+ "layers.6.attention.wk.probes" : "buckets-FP16-00007-of-00032.safetensors",
211
+ "layers.18.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00019-of-00032.safetensors",
212
+ "layers.14.attention.wk.bucket.stats" : "buckets-FP16-00015-of-00032.safetensors",
213
+ "layers.26.attention.wv.probes" : "buckets-FP16-00027-of-00032.safetensors",
214
+ "layers.27.attention.wo.core" : "buckets-FP16-00028-of-00032.safetensors",
215
+ "layers.17.ffn_norm" : "buckets-FP16-00018-of-00032.safetensors",
216
+ "layers.10.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00011-of-00032.safetensors",
217
+ "layers.0.attention.wv.probes" : "buckets-FP16-00001-of-00032.safetensors",
218
+ "layers.28.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00029-of-00032.safetensors",
219
+ "layers.15.attention.wk.probes" : "buckets-FP16-00016-of-00032.safetensors",
220
+ "layers.15.attention.wq.probes" : "buckets-FP16-00016-of-00032.safetensors",
221
+ "layers.4.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00005-of-00032.safetensors",
222
+ "layers.14.attention.wv.core" : "buckets-FP16-00015-of-00032.safetensors",
223
+ "layers.19.feed_forward.experts.0.w3.probes" : "buckets-FP16-00020-of-00032.safetensors",
224
+ "layers.26.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00027-of-00032.safetensors",
225
+ "layers.0.attention.wq.probes" : "buckets-FP16-00001-of-00032.safetensors",
226
+ "layers.21.feed_forward.experts.0.w1.probes" : "buckets-FP16-00022-of-00032.safetensors",
227
+ "layers.2.feed_forward.experts.0.w2.probes" : "buckets-FP16-00003-of-00032.safetensors",
228
+ "layers.13.attention_norm" : "buckets-FP16-00014-of-00032.safetensors",
229
+ "layers.14.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00015-of-00032.safetensors",
230
+ "layers.12.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00013-of-00032.safetensors",
231
+ "layers.30.feed_forward.experts.0.w1.probes" : "buckets-FP16-00031-of-00032.safetensors",
232
+ "layers.20.attention.wk.probes" : "buckets-FP16-00021-of-00032.safetensors",
233
+ "layers.15.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00016-of-00032.safetensors",
234
+ "layers.18.attention.wk.bucket.stats" : "buckets-FP16-00019-of-00032.safetensors",
235
+ "layers.2.feed_forward.experts.0.w3.probes" : "buckets-FP16-00003-of-00032.safetensors",
236
+ "layers.25.attention.wk.probes" : "buckets-FP16-00026-of-00032.safetensors",
237
+ "layers.10.attention.wq.buckets" : "buckets-FP16-00011-of-00032.safetensors",
238
+ "layers.10.attention.wk.probes" : "buckets-FP16-00011-of-00032.safetensors",
239
+ "layers.30.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00031-of-00032.safetensors",
240
+ "layers.23.attention.wv.bucket.stats" : "buckets-FP16-00024-of-00032.safetensors",
241
+ "layers.28.attention.wk.buckets" : "buckets-FP16-00029-of-00032.safetensors",
242
+ "layers.1.attention.wq.probes" : "buckets-FP16-00002-of-00032.safetensors",
243
+ "layers.9.attention.wv.probes" : "buckets-FP16-00010-of-00032.safetensors",
244
+ "layers.30.attention.wq.probes" : "buckets-FP16-00031-of-00032.safetensors",
245
+ "layers.2.attention.wo.probes" : "buckets-FP16-00003-of-00032.safetensors",
246
+ "layers.26.attention.wo.buckets" : "buckets-FP16-00027-of-00032.safetensors",
247
+ "layers.6.attention.wv.probes" : "buckets-FP16-00007-of-00032.safetensors",
248
+ "layers.24.attention.wv.core" : "buckets-FP16-00025-of-00032.safetensors",
249
+ "layers.21.attention.wq.core" : "buckets-FP16-00022-of-00032.safetensors",
250
+ "layers.14.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00015-of-00032.safetensors",
251
+ "layers.28.ffn_norm" : "buckets-FP16-00029-of-00032.safetensors",
252
+ "layers.17.attention.wo.core" : "buckets-FP16-00018-of-00032.safetensors",
253
+ "layers.29.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00030-of-00032.safetensors",
254
+ "layers.23.attention.wv.core" : "buckets-FP16-00024-of-00032.safetensors",
255
+ "layers.23.attention.wk.bucket.stats" : "buckets-FP16-00024-of-00032.safetensors",
256
+ "layers.7.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00008-of-00032.safetensors",
257
+ "layers.15.feed_forward.experts.0.w3.probes" : "buckets-FP16-00016-of-00032.safetensors",
258
+ "layers.11.ffn_norm" : "buckets-FP16-00012-of-00032.safetensors",
259
+ "layers.6.feed_forward.experts.0.w3.probes" : "buckets-FP16-00007-of-00032.safetensors",
260
+ "layers.9.feed_forward.experts.0.w2.probes" : "buckets-FP16-00010-of-00032.safetensors",
261
+ "layers.23.attention.wo.core" : "buckets-FP16-00024-of-00032.safetensors",
262
+ "layers.5.attention.wo.probes" : "buckets-FP16-00006-of-00032.safetensors",
263
+ "layers.4.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00005-of-00032.safetensors",
264
+ "layers.29.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00030-of-00032.safetensors",
265
+ "layers.3.attention.wv.core" : "buckets-FP16-00004-of-00032.safetensors",
266
+ "layers.15.attention.wv.core" : "buckets-FP16-00016-of-00032.safetensors",
267
+ "layers.10.feed_forward.experts.0.w1.probes" : "buckets-FP16-00011-of-00032.safetensors",
268
+ "layers.0.attention.wk.core" : "buckets-FP16-00001-of-00032.safetensors",
269
+ "layers.31.attention.wk.core" : "buckets-FP16-00032-of-00032.safetensors",
270
+ "layers.12.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00013-of-00032.safetensors",
271
+ "layers.1.attention.wo.core" : "buckets-FP16-00002-of-00032.safetensors",
272
+ "layers.5.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00006-of-00032.safetensors",
273
+ "layers.18.attention.wq.bucket.stats" : "buckets-FP16-00019-of-00032.safetensors",
274
+ "layers.14.attention.wv.bucket.stats" : "buckets-FP16-00015-of-00032.safetensors",
275
+ "layers.26.attention.wq.bucket.stats" : "buckets-FP16-00027-of-00032.safetensors",
276
+ "layers.29.attention.wv.buckets" : "buckets-FP16-00030-of-00032.safetensors",
277
+ "layers.17.attention.wk.probes" : "buckets-FP16-00018-of-00032.safetensors",
278
+ "layers.5.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00006-of-00032.safetensors",
279
+ "layers.16.attention.wk.probes" : "buckets-FP16-00017-of-00032.safetensors",
280
+ "layers.4.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00005-of-00032.safetensors",
281
+ "layers.26.feed_forward.experts.0.w3.probes" : "buckets-FP16-00027-of-00032.safetensors",
282
+ "layers.10.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00011-of-00032.safetensors",
283
+ "layers.9.attention.wo.core" : "buckets-FP16-00010-of-00032.safetensors",
284
+ "layers.6.attention.wv.core" : "buckets-FP16-00007-of-00032.safetensors",
285
+ "layers.24.attention.wq.probes" : "buckets-FP16-00025-of-00032.safetensors",
286
+ "layers.25.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00026-of-00032.safetensors",
287
+ "layers.30.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00031-of-00032.safetensors",
288
+ "layers.8.attention.wv.core" : "buckets-FP16-00009-of-00032.safetensors",
289
+ "layers.21.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00022-of-00032.safetensors",
290
+ "layers.1.ffn_norm" : "buckets-FP16-00002-of-00032.safetensors",
291
+ "layers.22.attention.wq.core" : "buckets-FP16-00023-of-00032.safetensors",
292
+ "layers.14.feed_forward.experts.0.w3.probes" : "buckets-FP16-00015-of-00032.safetensors",
293
+ "layers.31.attention.wq.buckets" : "buckets-FP16-00032-of-00032.safetensors",
294
+ "layers.13.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00014-of-00032.safetensors",
295
+ "layers.8.attention.wk.core" : "buckets-FP16-00009-of-00032.safetensors",
296
+ "layers.31.attention.wq.probes" : "buckets-FP16-00032-of-00032.safetensors",
297
+ "layers.0.attention.wk.probes" : "buckets-FP16-00001-of-00032.safetensors",
298
+ "layers.30.ffn_norm" : "buckets-FP16-00031-of-00032.safetensors",
299
+ "layers.22.feed_forward.experts.0.w1.probes" : "buckets-FP16-00023-of-00032.safetensors",
300
+ "layers.31.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00032-of-00032.safetensors",
301
+ "layers.7.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00008-of-00032.safetensors",
302
+ "layers.7.feed_forward.experts.0.w1.probes" : "buckets-FP16-00008-of-00032.safetensors",
303
+ "layers.7.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00008-of-00032.safetensors",
304
+ "layers.28.attention.wo.probes" : "buckets-FP16-00029-of-00032.safetensors",
305
+ "layers.24.attention.wq.core" : "buckets-FP16-00025-of-00032.safetensors",
306
+ "layers.12.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00013-of-00032.safetensors",
307
+ "layers.28.attention.wq.buckets" : "buckets-FP16-00029-of-00032.safetensors",
308
+ "layers.30.attention.wo.probes" : "buckets-FP16-00031-of-00032.safetensors",
309
+ "layers.9.attention.wq.probes" : "buckets-FP16-00010-of-00032.safetensors",
310
+ "layers.8.feed_forward.experts.0.w3.probes" : "buckets-FP16-00009-of-00032.safetensors",
311
+ "layers.12.attention.wk.bucket.stats" : "buckets-FP16-00013-of-00032.safetensors",
312
+ "layers.27.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00028-of-00032.safetensors",
313
+ "layers.25.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00026-of-00032.safetensors",
314
+ "layers.21.attention.wv.probes" : "buckets-FP16-00022-of-00032.safetensors",
315
+ "layers.20.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00021-of-00032.safetensors",
316
+ "layers.4.attention.wq.buckets" : "buckets-FP16-00005-of-00032.safetensors",
317
+ "layers.20.attention.wk.core" : "buckets-FP16-00021-of-00032.safetensors",
318
+ "layers.29.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00030-of-00032.safetensors",
319
+ "layers.7.attention_norm" : "buckets-FP16-00008-of-00032.safetensors",
320
+ "layers.27.feed_forward.experts.0.w1.probes" : "buckets-FP16-00028-of-00032.safetensors",
321
+ "layers.22.ffn_norm" : "buckets-FP16-00023-of-00032.safetensors",
322
+ "layers.24.feed_forward.experts.0.w3.probes" : "buckets-FP16-00025-of-00032.safetensors",
323
+ "layers.8.attention.wo.probes" : "buckets-FP16-00009-of-00032.safetensors",
324
+ "layers.31.attention.wv.core" : "buckets-FP16-00032-of-00032.safetensors",
325
+ "layers.12.attention.wk.buckets" : "buckets-FP16-00013-of-00032.safetensors",
326
+ "layers.8.attention.wv.buckets" : "buckets-FP16-00009-of-00032.safetensors",
327
+ "layers.29.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00030-of-00032.safetensors",
328
+ "layers.26.feed_forward.experts.0.w1.probes" : "buckets-FP16-00027-of-00032.safetensors",
329
+ "layers.5.attention.wq.bucket.stats" : "buckets-FP16-00006-of-00032.safetensors",
330
+ "layers.3.attention.wk.probes" : "buckets-FP16-00004-of-00032.safetensors",
331
+ "layers.24.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00025-of-00032.safetensors",
332
+ "layers.26.attention.wv.buckets" : "buckets-FP16-00027-of-00032.safetensors",
333
+ "layers.20.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00021-of-00032.safetensors",
334
+ "layers.9.attention.wv.bucket.stats" : "buckets-FP16-00010-of-00032.safetensors",
335
+ "layers.12.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00013-of-00032.safetensors",
336
+ "layers.21.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00022-of-00032.safetensors",
337
+ "layers.0.attention.wv.buckets" : "buckets-FP16-00001-of-00032.safetensors",
338
+ "layers.16.attention.wv.buckets" : "buckets-FP16-00017-of-00032.safetensors",
339
+ "layers.26.attention.wo.core" : "buckets-FP16-00027-of-00032.safetensors",
340
+ "layers.4.attention.wo.bucket.stats" : "buckets-FP16-00005-of-00032.safetensors",
341
+ "layers.10.attention.wq.bucket.stats" : "buckets-FP16-00011-of-00032.safetensors",
342
+ "layers.7.attention.wv.buckets" : "buckets-FP16-00008-of-00032.safetensors",
343
+ "layers.3.feed_forward.experts.0.w3.probes" : "buckets-FP16-00004-of-00032.safetensors",
344
+ "layers.19.attention.wq.probes" : "buckets-FP16-00020-of-00032.safetensors",
345
+ "layers.17.attention.wk.buckets" : "buckets-FP16-00018-of-00032.safetensors",
346
+ "layers.4.attention.wk.buckets" : "buckets-FP16-00005-of-00032.safetensors",
347
+ "layers.7.attention.wk.buckets" : "buckets-FP16-00008-of-00032.safetensors",
348
+ "layers.27.ffn_norm" : "buckets-FP16-00028-of-00032.safetensors",
349
+ "layers.3.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00004-of-00032.safetensors",
350
+ "layers.10.attention.wv.buckets" : "buckets-FP16-00011-of-00032.safetensors",
351
+ "layers.11.attention.wo.buckets" : "buckets-FP16-00012-of-00032.safetensors",
352
+ "layers.20.feed_forward.experts.0.w2.probes" : "buckets-FP16-00021-of-00032.safetensors",
353
+ "layers.2.attention.wo.buckets" : "buckets-FP16-00003-of-00032.safetensors",
354
+ "layers.24.feed_forward.experts.0.w2.probes" : "buckets-FP16-00025-of-00032.safetensors",
355
+ "layers.30.attention.wv.core" : "buckets-FP16-00031-of-00032.safetensors",
356
+ "layers.23.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00024-of-00032.safetensors",
357
+ "layers.15.feed_forward.experts.0.w2.probes" : "buckets-FP16-00016-of-00032.safetensors",
358
+ "layers.1.feed_forward.experts.0.w3.probes" : "buckets-FP16-00002-of-00032.safetensors",
359
+ "layers.24.attention.wk.probes" : "buckets-FP16-00025-of-00032.safetensors",
360
+ "layers.17.attention.wv.bucket.stats" : "buckets-FP16-00018-of-00032.safetensors",
361
+ "layers.4.ffn_norm" : "buckets-FP16-00005-of-00032.safetensors",
362
+ "layers.27.attention.wv.core" : "buckets-FP16-00028-of-00032.safetensors",
363
+ "layers.19.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00020-of-00032.safetensors",
364
+ "layers.3.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00004-of-00032.safetensors",
365
+ "layers.18.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00019-of-00032.safetensors",
366
+ "layers.7.attention.wo.bucket.stats" : "buckets-FP16-00008-of-00032.safetensors",
367
+ "layers.17.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00018-of-00032.safetensors",
368
+ "layers.23.attention.wq.probes" : "buckets-FP16-00024-of-00032.safetensors",
369
+ "layers.18.attention.wv.buckets" : "buckets-FP16-00019-of-00032.safetensors",
370
+ "layers.10.attention.wo.probes" : "buckets-FP16-00011-of-00032.safetensors",
371
+ "layers.5.attention_norm" : "buckets-FP16-00006-of-00032.safetensors",
372
+ "layers.30.attention.wk.probes" : "buckets-FP16-00031-of-00032.safetensors",
373
+ "layers.30.attention_norm" : "buckets-FP16-00031-of-00032.safetensors",
374
+ "layers.26.attention.wo.bucket.stats" : "buckets-FP16-00027-of-00032.safetensors",
375
+ "layers.18.ffn_norm" : "buckets-FP16-00019-of-00032.safetensors",
376
+ "layers.22.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00023-of-00032.safetensors",
377
+ "layers.6.attention.wq.probes" : "buckets-FP16-00007-of-00032.safetensors",
378
+ "layers.4.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00005-of-00032.safetensors",
379
+ "layers.30.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00031-of-00032.safetensors",
380
+ "layers.31.attention.wo.probes" : "buckets-FP16-00032-of-00032.safetensors",
381
+ "layers.5.feed_forward.experts.0.w3.probes" : "buckets-FP16-00006-of-00032.safetensors",
382
+ "layers.6.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00007-of-00032.safetensors",
383
+ "layers.13.attention.wv.probes" : "buckets-FP16-00014-of-00032.safetensors",
384
+ "layers.16.attention.wv.bucket.stats" : "buckets-FP16-00017-of-00032.safetensors",
385
+ "layers.19.attention.wo.bucket.stats" : "buckets-FP16-00020-of-00032.safetensors",
386
+ "layers.1.attention.wo.bucket.stats" : "buckets-FP16-00002-of-00032.safetensors",
387
+ "layers.31.attention.wq.bucket.stats" : "buckets-FP16-00032-of-00032.safetensors",
388
+ "layers.27.attention.wk.core" : "buckets-FP16-00028-of-00032.safetensors",
389
+ "layers.25.attention.wq.bucket.stats" : "buckets-FP16-00026-of-00032.safetensors",
390
+ "layers.15.attention.wv.probes" : "buckets-FP16-00016-of-00032.safetensors",
391
+ "layers.15.attention.wv.bucket.stats" : "buckets-FP16-00016-of-00032.safetensors",
392
+ "layers.6.attention.wv.bucket.stats" : "buckets-FP16-00007-of-00032.safetensors",
393
+ "layers.3.attention.wo.probes" : "buckets-FP16-00004-of-00032.safetensors",
394
+ "layers.5.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00006-of-00032.safetensors",
395
+ "output.core" : "buckets-FP16-00001-of-00032.safetensors",
396
+ "layers.23.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00024-of-00032.safetensors",
397
+ "layers.16.attention.wv.core" : "buckets-FP16-00017-of-00032.safetensors",
398
+ "layers.26.attention.wq.probes" : "buckets-FP16-00027-of-00032.safetensors",
399
+ "layers.17.feed_forward.experts.0.w3.probes" : "buckets-FP16-00018-of-00032.safetensors",
400
+ "layers.26.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00027-of-00032.safetensors",
401
+ "layers.5.attention.wk.probes" : "buckets-FP16-00006-of-00032.safetensors",
402
+ "layers.30.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00031-of-00032.safetensors",
403
+ "layers.11.attention.wo.probes" : "buckets-FP16-00012-of-00032.safetensors",
404
+ "layers.14.attention.wk.buckets" : "buckets-FP16-00015-of-00032.safetensors",
405
+ "layers.16.attention.wq.buckets" : "buckets-FP16-00017-of-00032.safetensors",
406
+ "layers.13.attention.wo.probes" : "buckets-FP16-00014-of-00032.safetensors",
407
+ "model.norm" : "buckets-FP16-00001-of-00032.safetensors",
408
+ "layers.3.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00004-of-00032.safetensors",
409
+ "layers.0.feed_forward.experts.0.w1.probes" : "buckets-FP16-00001-of-00032.safetensors",
410
+ "layers.14.attention.wk.core" : "buckets-FP16-00015-of-00032.safetensors",
411
+ "layers.7.feed_forward.experts.0.w3.probes" : "buckets-FP16-00008-of-00032.safetensors",
412
+ "layers.16.attention.wk.core" : "buckets-FP16-00017-of-00032.safetensors",
413
+ "layers.13.attention.wv.buckets" : "buckets-FP16-00014-of-00032.safetensors",
414
+ "layers.20.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00021-of-00032.safetensors",
415
+ "layers.25.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00026-of-00032.safetensors",
416
+ "layers.27.feed_forward.experts.0.w3.probes" : "buckets-FP16-00028-of-00032.safetensors",
417
+ "layers.21.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00022-of-00032.safetensors",
418
+ "layers.12.feed_forward.experts.0.w1.probes" : "buckets-FP16-00013-of-00032.safetensors",
419
+ "layers.23.attention.wv.probes" : "buckets-FP16-00024-of-00032.safetensors",
420
+ "layers.18.feed_forward.experts.0.w1.probes" : "buckets-FP16-00019-of-00032.safetensors",
421
+ "layers.25.attention_norm" : "buckets-FP16-00026-of-00032.safetensors",
422
+ "layers.26.attention.wq.buckets" : "buckets-FP16-00027-of-00032.safetensors",
423
+ "layers.24.attention.wo.probes" : "buckets-FP16-00025-of-00032.safetensors",
424
+ "layers.12.attention.wk.probes" : "buckets-FP16-00013-of-00032.safetensors",
425
+ "layers.27.attention_norm" : "buckets-FP16-00028-of-00032.safetensors",
426
+ "layers.27.attention.wq.probes" : "buckets-FP16-00028-of-00032.safetensors",
427
+ "layers.28.attention.wq.bucket.stats" : "buckets-FP16-00029-of-00032.safetensors",
428
+ "layers.5.attention.wv.buckets" : "buckets-FP16-00006-of-00032.safetensors",
429
+ "layers.4.attention.wv.core" : "buckets-FP16-00005-of-00032.safetensors",
430
+ "layers.12.attention.wo.buckets" : "buckets-FP16-00013-of-00032.safetensors",
431
+ "layers.21.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00022-of-00032.safetensors",
432
+ "layers.10.ffn_norm" : "buckets-FP16-00011-of-00032.safetensors",
433
+ "layers.8.ffn_norm" : "buckets-FP16-00009-of-00032.safetensors",
434
+ "layers.14.attention.wq.buckets" : "buckets-FP16-00015-of-00032.safetensors",
435
+ "layers.5.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00006-of-00032.safetensors",
436
+ "layers.3.feed_forward.experts.0.w1.probes" : "buckets-FP16-00004-of-00032.safetensors",
437
+ "layers.30.attention.wk.core" : "buckets-FP16-00031-of-00032.safetensors",
438
+ "layers.22.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00023-of-00032.safetensors",
439
+ "layers.8.attention.wo.bucket.stats" : "buckets-FP16-00009-of-00032.safetensors",
440
+ "layers.6.attention.wo.core" : "buckets-FP16-00007-of-00032.safetensors",
441
+ "layers.8.attention.wk.bucket.stats" : "buckets-FP16-00009-of-00032.safetensors",
442
+ "layers.9.feed_forward.experts.0.w3.probes" : "buckets-FP16-00010-of-00032.safetensors",
443
+ "layers.9.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00010-of-00032.safetensors",
444
+ "layers.20.attention.wq.bucket.stats" : "buckets-FP16-00021-of-00032.safetensors",
445
+ "layers.11.attention.wv.buckets" : "buckets-FP16-00012-of-00032.safetensors",
446
+ "layers.27.attention.wo.buckets" : "buckets-FP16-00028-of-00032.safetensors",
447
+ "layers.12.attention.wq.core" : "buckets-FP16-00013-of-00032.safetensors",
448
+ "layers.16.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00017-of-00032.safetensors",
449
+ "layers.20.attention.wk.bucket.stats" : "buckets-FP16-00021-of-00032.safetensors",
450
+ "layers.15.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00016-of-00032.safetensors",
451
+ "layers.17.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00018-of-00032.safetensors",
452
+ "layers.15.attention.wo.probes" : "buckets-FP16-00016-of-00032.safetensors",
453
+ "layers.8.attention.wo.core" : "buckets-FP16-00009-of-00032.safetensors",
454
+ "layers.23.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00024-of-00032.safetensors",
455
+ "layers.14.attention.wq.bucket.stats" : "buckets-FP16-00015-of-00032.safetensors",
456
+ "layers.30.feed_forward.experts.0.w2.probes" : "buckets-FP16-00031-of-00032.safetensors",
457
+ "layers.2.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00003-of-00032.safetensors",
458
+ "layers.12.attention.wq.probes" : "buckets-FP16-00013-of-00032.safetensors",
459
+ "layers.22.attention.wq.buckets" : "buckets-FP16-00023-of-00032.safetensors",
460
+ "layers.25.attention.wq.probes" : "buckets-FP16-00026-of-00032.safetensors",
461
+ "layers.29.attention.wo.core" : "buckets-FP16-00030-of-00032.safetensors",
462
+ "layers.31.attention.wo.buckets" : "buckets-FP16-00032-of-00032.safetensors",
463
+ "layers.0.attention.wo.buckets" : "buckets-FP16-00001-of-00032.safetensors",
464
+ "layers.31.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00032-of-00032.safetensors",
465
+ "layers.3.attention.wk.core" : "buckets-FP16-00004-of-00032.safetensors",
466
+ "layers.30.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00031-of-00032.safetensors",
467
+ "layers.14.attention.wk.probes" : "buckets-FP16-00015-of-00032.safetensors",
468
+ "layers.0.attention.wo.probes" : "buckets-FP16-00001-of-00032.safetensors",
469
+ "layers.25.attention.wv.core" : "buckets-FP16-00026-of-00032.safetensors",
470
+ "layers.8.feed_forward.experts.0.w1.probes" : "buckets-FP16-00009-of-00032.safetensors",
471
+ "layers.23.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00024-of-00032.safetensors",
472
+ "layers.5.attention.wo.bucket.stats" : "buckets-FP16-00006-of-00032.safetensors",
473
+ "layers.8.attention.wq.bucket.stats" : "buckets-FP16-00009-of-00032.safetensors",
474
+ "layers.15.attention.wo.bucket.stats" : "buckets-FP16-00016-of-00032.safetensors",
475
+ "layers.18.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00019-of-00032.safetensors",
476
+ "layers.20.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00021-of-00032.safetensors",
477
+ "layers.2.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00003-of-00032.safetensors",
478
+ "layers.27.attention.wv.probes" : "buckets-FP16-00028-of-00032.safetensors",
479
+ "layers.11.attention.wv.core" : "buckets-FP16-00012-of-00032.safetensors",
480
+ "layers.0.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00001-of-00032.safetensors",
481
+ "layers.29.attention.wq.core" : "buckets-FP16-00030-of-00032.safetensors",
482
+ "layers.4.attention.wv.probes" : "buckets-FP16-00005-of-00032.safetensors",
483
+ "layers.5.attention.wk.buckets" : "buckets-FP16-00006-of-00032.safetensors",
484
+ "layers.28.attention.wv.buckets" : "buckets-FP16-00029-of-00032.safetensors",
485
+ "layers.18.attention.wk.core" : "buckets-FP16-00019-of-00032.safetensors",
486
+ "layers.29.attention.wk.core" : "buckets-FP16-00030-of-00032.safetensors",
487
+ "layers.8.attention.wk.buckets" : "buckets-FP16-00009-of-00032.safetensors",
488
+ "layers.18.feed_forward.experts.0.w3.probes" : "buckets-FP16-00019-of-00032.safetensors",
489
+ "layers.1.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00002-of-00032.safetensors",
490
+ "layers.13.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00014-of-00032.safetensors",
491
+ "layers.22.attention.wk.core" : "buckets-FP16-00023-of-00032.safetensors",
492
+ "layers.0.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00001-of-00032.safetensors",
493
+ "layers.2.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00003-of-00032.safetensors",
494
+ "layers.5.attention.wk.core" : "buckets-FP16-00006-of-00032.safetensors",
495
+ "layers.26.attention.wk.core" : "buckets-FP16-00027-of-00032.safetensors",
496
+ "layers.31.attention.wv.buckets" : "buckets-FP16-00032-of-00032.safetensors",
497
+ "layers.21.attention.wo.buckets" : "buckets-FP16-00022-of-00032.safetensors",
498
+ "layers.11.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00012-of-00032.safetensors",
499
+ "layers.1.feed_forward.experts.0.w2.probes" : "buckets-FP16-00002-of-00032.safetensors",
500
+ "layers.18.attention.wv.core" : "buckets-FP16-00019-of-00032.safetensors",
501
+ "layers.4.feed_forward.experts.0.w2.probes" : "buckets-FP16-00005-of-00032.safetensors",
502
+ "layers.13.attention.wo.bucket.stats" : "buckets-FP16-00014-of-00032.safetensors",
503
+ "layers.30.feed_forward.experts.0.w3.probes" : "buckets-FP16-00031-of-00032.safetensors",
504
+ "layers.28.attention.wv.core" : "buckets-FP16-00029-of-00032.safetensors",
505
+ "layers.14.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00015-of-00032.safetensors",
506
+ "layers.3.attention.wk.bucket.stats" : "buckets-FP16-00004-of-00032.safetensors",
507
+ "layers.10.attention.wk.core" : "buckets-FP16-00011-of-00032.safetensors",
508
+ "layers.27.attention.wq.core" : "buckets-FP16-00028-of-00032.safetensors",
509
+ "layers.16.ffn_norm" : "buckets-FP16-00017-of-00032.safetensors",
510
+ "layers.5.attention.wq.buckets" : "buckets-FP16-00006-of-00032.safetensors",
511
+ "layers.7.attention.wq.bucket.stats" : "buckets-FP16-00008-of-00032.safetensors",
512
+ "layers.28.feed_forward.experts.0.w2.probes" : "buckets-FP16-00029-of-00032.safetensors",
513
+ "layers.19.ffn_norm" : "buckets-FP16-00020-of-00032.safetensors",
514
+ "layers.21.attention.wk.bucket.stats" : "buckets-FP16-00022-of-00032.safetensors",
515
+ "layers.6.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00007-of-00032.safetensors",
516
+ "layers.19.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00020-of-00032.safetensors",
517
+ "layers.17.attention.wk.bucket.stats" : "buckets-FP16-00018-of-00032.safetensors",
518
+ "layers.17.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00018-of-00032.safetensors",
519
+ "layers.29.attention.wq.probes" : "buckets-FP16-00030-of-00032.safetensors",
520
+ "layers.8.attention.wq.core" : "buckets-FP16-00009-of-00032.safetensors",
521
+ "layers.11.attention.wq.bucket.stats" : "buckets-FP16-00012-of-00032.safetensors",
522
+ "layers.5.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00006-of-00032.safetensors",
523
+ "layers.1.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00002-of-00032.safetensors",
524
+ "layers.5.attention.wq.probes" : "buckets-FP16-00006-of-00032.safetensors",
525
+ "layers.19.feed_forward.experts.0.w2.probes" : "buckets-FP16-00020-of-00032.safetensors",
526
+ "layers.0.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00001-of-00032.safetensors",
527
+ "layers.11.attention.wk.core" : "buckets-FP16-00012-of-00032.safetensors",
528
+ "layers.1.attention.wq.core" : "buckets-FP16-00002-of-00032.safetensors",
529
+ "layers.13.attention.wv.bucket.stats" : "buckets-FP16-00014-of-00032.safetensors",
530
+ "layers.23.attention_norm" : "buckets-FP16-00024-of-00032.safetensors",
531
+ "layers.23.feed_forward.experts.0.w2.probes" : "buckets-FP16-00024-of-00032.safetensors",
532
+ "layers.9.attention.wv.buckets" : "buckets-FP16-00010-of-00032.safetensors",
533
+ "layers.9.feed_forward.experts.0.w1.probes" : "buckets-FP16-00010-of-00032.safetensors",
534
+ "layers.2.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00003-of-00032.safetensors",
535
+ "layers.14.attention.wo.bucket.stats" : "buckets-FP16-00015-of-00032.safetensors",
536
+ "layers.25.attention.wk.buckets" : "buckets-FP16-00026-of-00032.safetensors",
537
+ "layers.26.attention_norm" : "buckets-FP16-00027-of-00032.safetensors",
538
+ "layers.18.attention.wo.core" : "buckets-FP16-00019-of-00032.safetensors",
539
+ "layers.5.attention.wv.bucket.stats" : "buckets-FP16-00006-of-00032.safetensors",
540
+ "layers.3.attention.wo.buckets" : "buckets-FP16-00004-of-00032.safetensors",
541
+ "layers.25.feed_forward.experts.0.w1.probes" : "buckets-FP16-00026-of-00032.safetensors",
542
+ "layers.24.attention.wv.buckets" : "buckets-FP16-00025-of-00032.safetensors",
543
+ "layers.26.attention.wk.buckets" : "buckets-FP16-00027-of-00032.safetensors",
544
+ "layers.28.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00029-of-00032.safetensors",
545
+ "layers.31.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00032-of-00032.safetensors",
546
+ "layers.5.feed_forward.experts.0.w2.probes" : "buckets-FP16-00006-of-00032.safetensors",
547
+ "layers.29.attention.wq.bucket.stats" : "buckets-FP16-00030-of-00032.safetensors",
548
+ "layers.26.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00027-of-00032.safetensors",
549
+ "layers.22.attention.wo.core" : "buckets-FP16-00023-of-00032.safetensors",
550
+ "layers.14.attention.wq.probes" : "buckets-FP16-00015-of-00032.safetensors",
551
+ "layers.21.attention.wk.buckets" : "buckets-FP16-00022-of-00032.safetensors",
552
+ "layers.3.attention.wq.probes" : "buckets-FP16-00004-of-00032.safetensors",
553
+ "layers.15.ffn_norm" : "buckets-FP16-00016-of-00032.safetensors",
554
+ "layers.11.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00012-of-00032.safetensors",
555
+ "layers.31.feed_forward.experts.0.w1.probes" : "buckets-FP16-00032-of-00032.safetensors",
556
+ "layers.26.attention.wk.probes" : "buckets-FP16-00027-of-00032.safetensors",
557
+ "layers.20.ffn_norm" : "buckets-FP16-00021-of-00032.safetensors",
558
+ "layers.18.attention.wo.buckets" : "buckets-FP16-00019-of-00032.safetensors",
559
+ "layers.15.attention.wq.core" : "buckets-FP16-00016-of-00032.safetensors",
560
+ "layers.28.attention.wo.bucket.stats" : "buckets-FP16-00029-of-00032.safetensors",
561
+ "layers.24.attention.wo.core" : "buckets-FP16-00025-of-00032.safetensors",
562
+ "layers.6.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00007-of-00032.safetensors",
563
+ "layers.0.attention.wv.bucket.stats" : "buckets-FP16-00001-of-00032.safetensors",
564
+ "layers.27.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00028-of-00032.safetensors",
565
+ "layers.9.attention.wo.probes" : "buckets-FP16-00010-of-00032.safetensors",
566
+ "layers.4.attention.wk.bucket.stats" : "buckets-FP16-00005-of-00032.safetensors",
567
+ "layers.1.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00002-of-00032.safetensors",
568
+ "layers.17.feed_forward.experts.0.w1.probes" : "buckets-FP16-00018-of-00032.safetensors",
569
+ "layers.2.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00003-of-00032.safetensors",
570
+ "layers.22.attention.wo.bucket.stats" : "buckets-FP16-00023-of-00032.safetensors",
571
+ "layers.24.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00025-of-00032.safetensors",
572
+ "layers.25.ffn_norm" : "buckets-FP16-00026-of-00032.safetensors",
573
+ "layers.19.feed_forward.experts.0.w1.probes" : "buckets-FP16-00020-of-00032.safetensors",
574
+ "layers.26.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00027-of-00032.safetensors",
575
+ "layers.16.attention.wv.probes" : "buckets-FP16-00017-of-00032.safetensors",
576
+ "layers.7.attention.wv.core" : "buckets-FP16-00008-of-00032.safetensors",
577
+ "layers.7.ffn_norm" : "buckets-FP16-00008-of-00032.safetensors",
578
+ "layers.17.attention.wo.buckets" : "buckets-FP16-00018-of-00032.safetensors",
579
+ "layers.26.attention.wo.probes" : "buckets-FP16-00027-of-00032.safetensors",
580
+ "layers.20.attention.wo.probes" : "buckets-FP16-00021-of-00032.safetensors",
581
+ "layers.20.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00021-of-00032.safetensors",
582
+ "layers.25.attention.wo.buckets" : "buckets-FP16-00026-of-00032.safetensors",
583
+ "layers.24.attention.wk.buckets" : "buckets-FP16-00025-of-00032.safetensors",
584
+ "layers.14.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00015-of-00032.safetensors",
585
+ "layers.5.attention.wo.buckets" : "buckets-FP16-00006-of-00032.safetensors",
586
+ "layers.27.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00028-of-00032.safetensors",
587
+ "layers.13.feed_forward.experts.0.w1.probes" : "buckets-FP16-00014-of-00032.safetensors",
588
+ "layers.7.attention.wk.core" : "buckets-FP16-00008-of-00032.safetensors",
589
+ "layers.9.attention.wk.buckets" : "buckets-FP16-00010-of-00032.safetensors",
590
+ "layers.10.attention.wv.core" : "buckets-FP16-00011-of-00032.safetensors",
591
+ "layers.27.attention.wv.buckets" : "buckets-FP16-00028-of-00032.safetensors",
592
+ "layers.26.attention.wq.core" : "buckets-FP16-00027-of-00032.safetensors",
593
+ "layers.4.attention.wv.bucket.stats" : "buckets-FP16-00005-of-00032.safetensors",
594
+ "layers.20.attention.wq.probes" : "buckets-FP16-00021-of-00032.safetensors",
595
+ "layers.21.attention.wo.bucket.stats" : "buckets-FP16-00022-of-00032.safetensors",
596
+ "layers.26.attention.wv.core" : "buckets-FP16-00027-of-00032.safetensors",
597
+ "layers.3.attention.wv.bucket.stats" : "buckets-FP16-00004-of-00032.safetensors",
598
+ "layers.18.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00019-of-00032.safetensors",
599
+ "layers.13.attention.wk.core" : "buckets-FP16-00014-of-00032.safetensors",
600
+ "layers.29.feed_forward.experts.0.w3.probes" : "buckets-FP16-00030-of-00032.safetensors",
601
+ "layers.29.attention_norm" : "buckets-FP16-00030-of-00032.safetensors",
602
+ "layers.11.attention_norm" : "buckets-FP16-00012-of-00032.safetensors",
603
+ "layers.28.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00029-of-00032.safetensors",
604
+ "layers.8.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00009-of-00032.safetensors",
605
+ "layers.23.attention.wv.buckets" : "buckets-FP16-00024-of-00032.safetensors",
606
+ "tok_embeddings.core" : "buckets-FP16-00001-of-00032.safetensors",
607
+ "layers.2.attention.wv.bucket.stats" : "buckets-FP16-00003-of-00032.safetensors",
608
+ "layers.14.ffn_norm" : "buckets-FP16-00015-of-00032.safetensors",
609
+ "layers.27.feed_forward.experts.0.w2.probes" : "buckets-FP16-00028-of-00032.safetensors",
610
+ "layers.4.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00005-of-00032.safetensors",
611
+ "layers.8.attention_norm" : "buckets-FP16-00009-of-00032.safetensors",
612
+ "layers.24.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00025-of-00032.safetensors",
613
+ "layers.19.attention.wv.core" : "buckets-FP16-00020-of-00032.safetensors",
614
+ "layers.10.attention.wk.bucket.stats" : "buckets-FP16-00011-of-00032.safetensors",
615
+ "layers.10.attention_norm" : "buckets-FP16-00011-of-00032.safetensors",
616
+ "layers.22.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00023-of-00032.safetensors",
617
+ "layers.27.attention.wo.bucket.stats" : "buckets-FP16-00028-of-00032.safetensors",
618
+ "layers.18.feed_forward.experts.0.w2.probes" : "buckets-FP16-00019-of-00032.safetensors",
619
+ "layers.29.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00030-of-00032.safetensors",
620
+ "layers.26.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00027-of-00032.safetensors",
621
+ "layers.30.attention.wv.probes" : "buckets-FP16-00031-of-00032.safetensors",
622
+ "layers.24.attention.wq.buckets" : "buckets-FP16-00025-of-00032.safetensors",
623
+ "layers.3.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00004-of-00032.safetensors",
624
+ "layers.2.attention.wv.core" : "buckets-FP16-00003-of-00032.safetensors",
625
+ "layers.17.attention.wv.buckets" : "buckets-FP16-00018-of-00032.safetensors",
626
+ "layers.3.attention.wo.bucket.stats" : "buckets-FP16-00004-of-00032.safetensors",
627
+ "layers.14.feed_forward.experts.0.w1.probes" : "buckets-FP16-00015-of-00032.safetensors",
628
+ "layers.22.attention.wv.buckets" : "buckets-FP16-00023-of-00032.safetensors",
629
+ "layers.3.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00004-of-00032.safetensors",
630
+ "layers.19.attention.wq.buckets" : "buckets-FP16-00020-of-00032.safetensors",
631
+ "layers.14.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00015-of-00032.safetensors",
632
+ "layers.19.attention.wo.probes" : "buckets-FP16-00020-of-00032.safetensors",
633
+ "layers.4.attention.wq.core" : "buckets-FP16-00005-of-00032.safetensors",
634
+ "layers.27.attention.wo.probes" : "buckets-FP16-00028-of-00032.safetensors",
635
+ "layers.5.attention.wo.core" : "buckets-FP16-00006-of-00032.safetensors",
636
+ "layers.21.attention.wo.core" : "buckets-FP16-00022-of-00032.safetensors",
637
+ "layers.17.attention.wq.bucket.stats" : "buckets-FP16-00018-of-00032.safetensors",
638
+ "layers.1.attention.wv.probes" : "buckets-FP16-00002-of-00032.safetensors",
639
+ "layers.22.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00023-of-00032.safetensors",
640
+ "layers.12.attention.wo.core" : "buckets-FP16-00013-of-00032.safetensors",
641
+ "layers.12.attention.wq.buckets" : "buckets-FP16-00013-of-00032.safetensors",
642
+ "layers.6.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00007-of-00032.safetensors",
643
+ "layers.9.attention.wq.buckets" : "buckets-FP16-00010-of-00032.safetensors",
644
+ "layers.22.attention.wk.buckets" : "buckets-FP16-00023-of-00032.safetensors",
645
+ "layers.21.attention.wv.buckets" : "buckets-FP16-00022-of-00032.safetensors",
646
+ "layers.8.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00009-of-00032.safetensors",
647
+ "layers.25.attention.wv.probes" : "buckets-FP16-00026-of-00032.safetensors",
648
+ "layers.4.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00005-of-00032.safetensors",
649
+ "layers.15.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00016-of-00032.safetensors",
650
+ "layers.4.attention_norm" : "buckets-FP16-00005-of-00032.safetensors",
651
+ "layers.1.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00002-of-00032.safetensors",
652
+ "layers.25.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00026-of-00032.safetensors",
653
+ "layers.23.attention.wq.buckets" : "buckets-FP16-00024-of-00032.safetensors",
654
+ "layers.30.attention.wv.buckets" : "buckets-FP16-00031-of-00032.safetensors",
655
+ "layers.17.attention.wo.bucket.stats" : "buckets-FP16-00018-of-00032.safetensors",
656
+ "layers.3.attention.wo.core" : "buckets-FP16-00004-of-00032.safetensors",
657
+ "layers.24.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00025-of-00032.safetensors",
658
+ "layers.18.attention.wk.probes" : "buckets-FP16-00019-of-00032.safetensors",
659
+ "layers.5.attention.wv.probes" : "buckets-FP16-00006-of-00032.safetensors",
660
+ "layers.24.attention.wo.buckets" : "buckets-FP16-00025-of-00032.safetensors",
661
+ "layers.0.attention.wk.bucket.stats" : "buckets-FP16-00001-of-00032.safetensors",
662
+ "layers.11.attention.wv.probes" : "buckets-FP16-00012-of-00032.safetensors",
663
+ "layers.30.attention.wo.buckets" : "buckets-FP16-00031-of-00032.safetensors",
664
+ "layers.30.attention.wq.bucket.stats" : "buckets-FP16-00031-of-00032.safetensors",
665
+ "layers.6.ffn_norm" : "buckets-FP16-00007-of-00032.safetensors",
666
+ "layers.24.feed_forward.experts.0.w1.probes" : "buckets-FP16-00025-of-00032.safetensors",
667
+ "layers.28.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00029-of-00032.safetensors",
668
+ "layers.0.feed_forward.experts.0.w3.probes" : "buckets-FP16-00001-of-00032.safetensors",
669
+ "layers.13.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00014-of-00032.safetensors",
670
+ "layers.19.attention.wk.bucket.stats" : "buckets-FP16-00020-of-00032.safetensors",
671
+ "layers.0.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00001-of-00032.safetensors",
672
+ "layers.14.attention.wv.probes" : "buckets-FP16-00015-of-00032.safetensors",
673
+ "layers.27.attention.wk.buckets" : "buckets-FP16-00028-of-00032.safetensors",
674
+ "layers.10.feed_forward.experts.0.w3.probes" : "buckets-FP16-00011-of-00032.safetensors",
675
+ "layers.21.attention.wk.probes" : "buckets-FP16-00022-of-00032.safetensors",
676
+ "layers.19.attention_norm" : "buckets-FP16-00020-of-00032.safetensors",
677
+ "layers.1.attention_norm" : "buckets-FP16-00002-of-00032.safetensors",
678
+ "layers.2.attention.wk.bucket.stats" : "buckets-FP16-00003-of-00032.safetensors",
679
+ "layers.20.attention.wv.buckets" : "buckets-FP16-00021-of-00032.safetensors",
680
+ "layers.25.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00026-of-00032.safetensors",
681
+ "layers.19.attention.wo.core" : "buckets-FP16-00020-of-00032.safetensors",
682
+ "layers.13.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00014-of-00032.safetensors",
683
+ "layers.10.attention.wq.core" : "buckets-FP16-00011-of-00032.safetensors",
684
+ "layers.18.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00019-of-00032.safetensors",
685
+ "layers.12.attention.wo.probes" : "buckets-FP16-00013-of-00032.safetensors",
686
+ "layers.24.attention_norm" : "buckets-FP16-00025-of-00032.safetensors",
687
+ "layers.31.attention.wo.bucket.stats" : "buckets-FP16-00032-of-00032.safetensors",
688
+ "layers.23.attention.wk.probes" : "buckets-FP16-00024-of-00032.safetensors",
689
+ "layers.19.attention.wk.probes" : "buckets-FP16-00020-of-00032.safetensors",
690
+ "layers.16.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00017-of-00032.safetensors",
691
+ "layers.16.feed_forward.experts.0.w3.probes" : "buckets-FP16-00017-of-00032.safetensors",
692
+ "layers.29.attention.wk.probes" : "buckets-FP16-00030-of-00032.safetensors",
693
+ "layers.7.attention.wo.probes" : "buckets-FP16-00008-of-00032.safetensors",
694
+ "layers.20.attention_norm" : "buckets-FP16-00021-of-00032.safetensors",
695
+ "layers.13.attention.wk.probes" : "buckets-FP16-00014-of-00032.safetensors",
696
+ "layers.27.attention.wq.bucket.stats" : "buckets-FP16-00028-of-00032.safetensors",
697
+ "layers.26.ffn_norm" : "buckets-FP16-00027-of-00032.safetensors",
698
+ "layers.22.attention.wo.probes" : "buckets-FP16-00023-of-00032.safetensors",
699
+ "layers.30.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00031-of-00032.safetensors",
700
+ "layers.8.attention.wv.probes" : "buckets-FP16-00009-of-00032.safetensors",
701
+ "layers.15.attention.wk.core" : "buckets-FP16-00016-of-00032.safetensors",
702
+ "layers.17.attention.wq.probes" : "buckets-FP16-00018-of-00032.safetensors",
703
+ "layers.17.attention.wo.probes" : "buckets-FP16-00018-of-00032.safetensors",
704
+ "layers.1.attention.wv.buckets" : "buckets-FP16-00002-of-00032.safetensors",
705
+ "layers.22.attention.wk.probes" : "buckets-FP16-00023-of-00032.safetensors",
706
+ "layers.23.attention.wq.bucket.stats" : "buckets-FP16-00024-of-00032.safetensors",
707
+ "layers.8.attention.wo.buckets" : "buckets-FP16-00009-of-00032.safetensors",
708
+ "layers.8.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00009-of-00032.safetensors",
709
+ "layers.0.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00001-of-00032.safetensors",
710
+ "layers.12.feed_forward.experts.0.w2.probes" : "buckets-FP16-00013-of-00032.safetensors",
711
+ "layers.19.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00020-of-00032.safetensors",
712
+ "layers.21.attention.wq.probes" : "buckets-FP16-00022-of-00032.safetensors",
713
+ "layers.25.attention.wq.core" : "buckets-FP16-00026-of-00032.safetensors",
714
+ "layers.26.feed_forward.experts.0.w2.probes" : "buckets-FP16-00027-of-00032.safetensors",
715
+ "layers.30.attention.wq.buckets" : "buckets-FP16-00031-of-00032.safetensors",
716
+ "layers.13.attention.wk.bucket.stats" : "buckets-FP16-00014-of-00032.safetensors",
717
+ "layers.24.ffn_norm" : "buckets-FP16-00025-of-00032.safetensors",
718
+ "layers.17.attention.wk.core" : "buckets-FP16-00018-of-00032.safetensors",
719
+ "layers.21.attention.wq.buckets" : "buckets-FP16-00022-of-00032.safetensors",
720
+ "layers.16.attention.wq.core" : "buckets-FP16-00017-of-00032.safetensors",
721
+ "layers.20.feed_forward.experts.0.w1.probes" : "buckets-FP16-00021-of-00032.safetensors",
722
+ "layers.22.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00023-of-00032.safetensors",
723
+ "layers.7.attention.wk.bucket.stats" : "buckets-FP16-00008-of-00032.safetensors",
724
+ "layers.16.attention.wo.buckets" : "buckets-FP16-00017-of-00032.safetensors",
725
+ "layers.28.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00029-of-00032.safetensors",
726
+ "layers.28.attention_norm" : "buckets-FP16-00029-of-00032.safetensors",
727
+ "layers.1.attention.wo.buckets" : "buckets-FP16-00002-of-00032.safetensors",
728
+ "layers.11.feed_forward.experts.0.w1.probes" : "buckets-FP16-00012-of-00032.safetensors",
729
+ "layers.22.attention.wq.probes" : "buckets-FP16-00023-of-00032.safetensors",
730
+ "layers.2.attention.wq.probes" : "buckets-FP16-00003-of-00032.safetensors",
731
+ "layers.30.attention.wo.core" : "buckets-FP16-00031-of-00032.safetensors",
732
+ "layers.31.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00032-of-00032.safetensors",
733
+ "layers.0.attention.wq.bucket.stats" : "buckets-FP16-00001-of-00032.safetensors",
734
+ "layers.21.feed_forward.experts.0.w2.probes" : "buckets-FP16-00022-of-00032.safetensors",
735
+ "layers.14.attention.wo.core" : "buckets-FP16-00015-of-00032.safetensors",
736
+ "layers.2.attention.wk.core" : "buckets-FP16-00003-of-00032.safetensors",
737
+ "layers.9.attention.wk.bucket.stats" : "buckets-FP16-00010-of-00032.safetensors",
738
+ "layers.22.feed_forward.experts.0.w3.probes" : "buckets-FP16-00023-of-00032.safetensors",
739
+ "layers.6.attention.wk.core" : "buckets-FP16-00007-of-00032.safetensors",
740
+ "layers.6.attention.wk.bucket.stats" : "buckets-FP16-00007-of-00032.safetensors",
741
+ "layers.13.feed_forward.experts.0.w2.probes" : "buckets-FP16-00014-of-00032.safetensors",
742
+ "layers.25.attention.wq.buckets" : "buckets-FP16-00026-of-00032.safetensors",
743
+ "layers.17.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00018-of-00032.safetensors",
744
+ "layers.11.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00012-of-00032.safetensors",
745
+ "layers.10.attention.wv.bucket.stats" : "buckets-FP16-00011-of-00032.safetensors",
746
+ "layers.0.attention.wq.buckets" : "buckets-FP16-00001-of-00032.safetensors",
747
+ "layers.9.attention.wv.core" : "buckets-FP16-00010-of-00032.safetensors",
748
+ "layers.2.ffn_norm" : "buckets-FP16-00003-of-00032.safetensors",
749
+ "layers.24.attention.wo.bucket.stats" : "buckets-FP16-00025-of-00032.safetensors",
750
+ "layers.3.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00004-of-00032.safetensors",
751
+ "layers.7.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00008-of-00032.safetensors",
752
+ "layers.9.attention_norm" : "buckets-FP16-00010-of-00032.safetensors",
753
+ "layers.16.feed_forward.experts.0.w2.probes" : "buckets-FP16-00017-of-00032.safetensors",
754
+ "layers.22.attention.wv.probes" : "buckets-FP16-00023-of-00032.safetensors",
755
+ "layers.1.attention.wk.buckets" : "buckets-FP16-00002-of-00032.safetensors",
756
+ "layers.18.attention.wq.buckets" : "buckets-FP16-00019-of-00032.safetensors",
757
+ "layers.11.attention.wk.buckets" : "buckets-FP16-00012-of-00032.safetensors",
758
+ "layers.22.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00023-of-00032.safetensors",
759
+ "layers.23.feed_forward.experts.0.w3.probes" : "buckets-FP16-00024-of-00032.safetensors",
760
+ "layers.25.feed_forward.experts.0.w2.probes" : "buckets-FP16-00026-of-00032.safetensors",
761
+ "layers.29.attention.wk.buckets" : "buckets-FP16-00030-of-00032.safetensors",
762
+ "layers.15.attention.wo.buckets" : "buckets-FP16-00016-of-00032.safetensors",
763
+ "layers.29.ffn_norm" : "buckets-FP16-00030-of-00032.safetensors",
764
+ "layers.15.attention.wk.buckets" : "buckets-FP16-00016-of-00032.safetensors",
765
+ "layers.13.ffn_norm" : "buckets-FP16-00014-of-00032.safetensors",
766
+ "layers.7.attention.wv.probes" : "buckets-FP16-00008-of-00032.safetensors",
767
+ "layers.2.attention.wk.probes" : "buckets-FP16-00003-of-00032.safetensors",
768
+ "layers.18.attention.wq.probes" : "buckets-FP16-00019-of-00032.safetensors",
769
+ "layers.0.attention.wo.bucket.stats" : "buckets-FP16-00001-of-00032.safetensors",
770
+ "layers.12.attention.wv.bucket.stats" : "buckets-FP16-00013-of-00032.safetensors",
771
+ "layers.10.attention.wv.probes" : "buckets-FP16-00011-of-00032.safetensors",
772
+ "layers.12.attention.wv.core" : "buckets-FP16-00013-of-00032.safetensors",
773
+ "layers.7.attention.wq.probes" : "buckets-FP16-00008-of-00032.safetensors",
774
+ "layers.20.attention.wo.core" : "buckets-FP16-00021-of-00032.safetensors",
775
+ "layers.17.attention.wq.buckets" : "buckets-FP16-00018-of-00032.safetensors",
776
+ "layers.9.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00010-of-00032.safetensors",
777
+ "layers.8.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00009-of-00032.safetensors",
778
+ "layers.15.attention.wq.buckets" : "buckets-FP16-00016-of-00032.safetensors",
779
+ "layers.8.feed_forward.experts.0.w2.probes" : "buckets-FP16-00009-of-00032.safetensors",
780
+ "layers.24.feed_forward.experts.0.w2.buckets" : "buckets-FP16-00025-of-00032.safetensors",
781
+ "layers.29.feed_forward.experts.0.w2.probes" : "buckets-FP16-00030-of-00032.safetensors",
782
+ "layers.31.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00032-of-00032.safetensors",
783
+ "layers.25.attention.wv.bucket.stats" : "buckets-FP16-00026-of-00032.safetensors",
784
+ "layers.16.attention.wk.buckets" : "buckets-FP16-00017-of-00032.safetensors",
785
+ "layers.13.feed_forward.experts.0.w3.probes" : "buckets-FP16-00014-of-00032.safetensors",
786
+ "layers.16.attention.wo.bucket.stats" : "buckets-FP16-00017-of-00032.safetensors",
787
+ "layers.11.attention.wv.bucket.stats" : "buckets-FP16-00012-of-00032.safetensors",
788
+ "layers.19.attention.wv.buckets" : "buckets-FP16-00020-of-00032.safetensors",
789
+ "layers.28.feed_forward.experts.0.w3.probes" : "buckets-FP16-00029-of-00032.safetensors",
790
+ "layers.12.attention.wv.probes" : "buckets-FP16-00013-of-00032.safetensors",
791
+ "layers.9.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00010-of-00032.safetensors",
792
+ "layers.27.attention.wk.bucket.stats" : "buckets-FP16-00028-of-00032.safetensors",
793
+ "layers.24.attention.wk.core" : "buckets-FP16-00025-of-00032.safetensors",
794
+ "layers.30.attention.wq.core" : "buckets-FP16-00031-of-00032.safetensors",
795
+ "layers.31.attention.wo.core" : "buckets-FP16-00032-of-00032.safetensors",
796
+ "layers.13.attention.wk.buckets" : "buckets-FP16-00014-of-00032.safetensors",
797
+ "layers.11.attention.wq.probes" : "buckets-FP16-00012-of-00032.safetensors",
798
+ "layers.6.attention.wo.bucket.stats" : "buckets-FP16-00007-of-00032.safetensors",
799
+ "layers.0.ffn_norm" : "buckets-FP16-00001-of-00032.safetensors",
800
+ "layers.28.attention.wk.core" : "buckets-FP16-00029-of-00032.safetensors",
801
+ "layers.5.feed_forward.experts.0.w1.probes" : "buckets-FP16-00006-of-00032.safetensors",
802
+ "layers.1.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00002-of-00032.safetensors",
803
+ "layers.29.attention.wv.bucket.stats" : "buckets-FP16-00030-of-00032.safetensors",
804
+ "layers.17.attention.wq.core" : "buckets-FP16-00018-of-00032.safetensors",
805
+ "layers.8.attention.wq.probes" : "buckets-FP16-00009-of-00032.safetensors",
806
+ "layers.5.attention.wk.bucket.stats" : "buckets-FP16-00006-of-00032.safetensors",
807
+ "layers.21.ffn_norm" : "buckets-FP16-00022-of-00032.safetensors",
808
+ "layers.23.attention.wk.buckets" : "buckets-FP16-00024-of-00032.safetensors",
809
+ "layers.21.attention.wv.core" : "buckets-FP16-00022-of-00032.safetensors",
810
+ "layers.10.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00011-of-00032.safetensors",
811
+ "layers.28.feed_forward.experts.0.w1.probes" : "buckets-FP16-00029-of-00032.safetensors",
812
+ "layers.11.attention.wo.bucket.stats" : "buckets-FP16-00012-of-00032.safetensors",
813
+ "layers.3.attention_norm" : "buckets-FP16-00004-of-00032.safetensors",
814
+ "layers.4.feed_forward.experts.0.w1.probes" : "buckets-FP16-00005-of-00032.safetensors",
815
+ "layers.2.attention.wk.buckets" : "buckets-FP16-00003-of-00032.safetensors",
816
+ "layers.25.attention.wo.core" : "buckets-FP16-00026-of-00032.safetensors",
817
+ "layers.6.attention.wq.bucket.stats" : "buckets-FP16-00007-of-00032.safetensors",
818
+ "layers.22.attention.wv.core" : "buckets-FP16-00023-of-00032.safetensors",
819
+ "layers.22.attention.wv.bucket.stats" : "buckets-FP16-00023-of-00032.safetensors",
820
+ "layers.29.attention.wo.probes" : "buckets-FP16-00030-of-00032.safetensors",
821
+ "layers.17.feed_forward.experts.0.w2.probes" : "buckets-FP16-00018-of-00032.safetensors",
822
+ "layers.6.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00007-of-00032.safetensors",
823
+ "layers.23.feed_forward.experts.0.w1.probes" : "buckets-FP16-00024-of-00032.safetensors",
824
+ "layers.31.attention_norm" : "buckets-FP16-00032-of-00032.safetensors",
825
+ "layers.29.attention.wv.probes" : "buckets-FP16-00030-of-00032.safetensors",
826
+ "layers.20.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00021-of-00032.safetensors",
827
+ "layers.7.attention.wk.probes" : "buckets-FP16-00008-of-00032.safetensors",
828
+ "layers.31.attention.wk.probes" : "buckets-FP16-00032-of-00032.safetensors",
829
+ "layers.4.attention.wk.probes" : "buckets-FP16-00005-of-00032.safetensors",
830
+ "layers.21.attention.wv.bucket.stats" : "buckets-FP16-00022-of-00032.safetensors",
831
+ "layers.29.attention.wq.buckets" : "buckets-FP16-00030-of-00032.safetensors",
832
+ "layers.20.feed_forward.experts.0.w3.probes" : "buckets-FP16-00021-of-00032.safetensors",
833
+ "layers.15.feed_forward.experts.0.w1.probes" : "buckets-FP16-00016-of-00032.safetensors",
834
+ "layers.31.attention.wk.bucket.stats" : "buckets-FP16-00032-of-00032.safetensors",
835
+ "layers.27.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00028-of-00032.safetensors",
836
+ "layers.4.attention.wo.probes" : "buckets-FP16-00005-of-00032.safetensors",
837
+ "layers.2.attention_norm" : "buckets-FP16-00003-of-00032.safetensors",
838
+ "layers.31.attention.wv.bucket.stats" : "buckets-FP16-00032-of-00032.safetensors",
839
+ "layers.29.attention.wk.bucket.stats" : "buckets-FP16-00030-of-00032.safetensors",
840
+ "layers.0.attention.wo.core" : "buckets-FP16-00001-of-00032.safetensors",
841
+ "layers.9.attention.wk.probes" : "buckets-FP16-00010-of-00032.safetensors",
842
+ "layers.9.attention.wk.core" : "buckets-FP16-00010-of-00032.safetensors",
843
+ "layers.22.attention.wk.bucket.stats" : "buckets-FP16-00023-of-00032.safetensors",
844
+ "layers.18.attention_norm" : "buckets-FP16-00019-of-00032.safetensors",
845
+ "layers.3.attention.wv.probes" : "buckets-FP16-00004-of-00032.safetensors",
846
+ "layers.3.attention.wv.buckets" : "buckets-FP16-00004-of-00032.safetensors",
847
+ "layers.12.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00013-of-00032.safetensors",
848
+ "layers.19.feed_forward.experts.0.w3.buckets" : "buckets-FP16-00020-of-00032.safetensors",
849
+ "layers.9.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00010-of-00032.safetensors",
850
+ "layers.0.attention.wv.core" : "buckets-FP16-00001-of-00032.safetensors",
851
+ "layers.23.attention.wq.core" : "buckets-FP16-00024-of-00032.safetensors",
852
+ "layers.11.attention.wq.core" : "buckets-FP16-00012-of-00032.safetensors",
853
+ "layers.11.feed_forward.experts.0.w3.probes" : "buckets-FP16-00012-of-00032.safetensors",
854
+ "layers.25.attention.wo.probes" : "buckets-FP16-00026-of-00032.safetensors",
855
+ "layers.28.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00029-of-00032.safetensors",
856
+ "layers.4.attention.wk.core" : "buckets-FP16-00005-of-00032.safetensors",
857
+ "layers.7.attention.wq.buckets" : "buckets-FP16-00008-of-00032.safetensors",
858
+ "layers.10.attention.wk.buckets" : "buckets-FP16-00011-of-00032.safetensors",
859
+ "layers.0.attention.wk.buckets" : "buckets-FP16-00001-of-00032.safetensors",
860
+ "layers.9.feed_forward.experts.0.w2.bucket.stats" : "buckets-FP16-00010-of-00032.safetensors",
861
+ "layers.23.feed_forward.experts.0.w1.bucket.stats" : "buckets-FP16-00024-of-00032.safetensors",
862
+ "layers.23.attention.wo.probes" : "buckets-FP16-00024-of-00032.safetensors",
863
+ "layers.30.attention.wk.buckets" : "buckets-FP16-00031-of-00032.safetensors",
864
+ "layers.16.feed_forward.experts.0.w1.probes" : "buckets-FP16-00017-of-00032.safetensors",
865
+ "layers.2.attention.wq.bucket.stats" : "buckets-FP16-00003-of-00032.safetensors",
866
+ "layers.4.attention.wq.probes" : "buckets-FP16-00005-of-00032.safetensors",
867
+ "layers.16.feed_forward.experts.0.w1.buckets" : "buckets-FP16-00017-of-00032.safetensors",
868
+ "layers.11.attention.wk.probes" : "buckets-FP16-00012-of-00032.safetensors",
869
+ "layers.7.feed_forward.experts.0.w3.bucket.stats" : "buckets-FP16-00008-of-00032.safetensors"
870
+ }
871
+ }