quantumaikr commited on
Commit
3db30d1
1 Parent(s): 5fd1895

Upload FalconForCausalLM

Browse files
Files changed (44) hide show
  1. config.json +26 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00041.safetensors +3 -0
  4. model-00002-of-00041.safetensors +3 -0
  5. model-00003-of-00041.safetensors +3 -0
  6. model-00004-of-00041.safetensors +3 -0
  7. model-00005-of-00041.safetensors +3 -0
  8. model-00006-of-00041.safetensors +3 -0
  9. model-00007-of-00041.safetensors +3 -0
  10. model-00008-of-00041.safetensors +3 -0
  11. model-00009-of-00041.safetensors +3 -0
  12. model-00010-of-00041.safetensors +3 -0
  13. model-00011-of-00041.safetensors +3 -0
  14. model-00012-of-00041.safetensors +3 -0
  15. model-00013-of-00041.safetensors +3 -0
  16. model-00014-of-00041.safetensors +3 -0
  17. model-00015-of-00041.safetensors +3 -0
  18. model-00016-of-00041.safetensors +3 -0
  19. model-00017-of-00041.safetensors +3 -0
  20. model-00018-of-00041.safetensors +3 -0
  21. model-00019-of-00041.safetensors +3 -0
  22. model-00020-of-00041.safetensors +3 -0
  23. model-00021-of-00041.safetensors +3 -0
  24. model-00022-of-00041.safetensors +3 -0
  25. model-00023-of-00041.safetensors +3 -0
  26. model-00024-of-00041.safetensors +3 -0
  27. model-00025-of-00041.safetensors +3 -0
  28. model-00026-of-00041.safetensors +3 -0
  29. model-00027-of-00041.safetensors +3 -0
  30. model-00028-of-00041.safetensors +3 -0
  31. model-00029-of-00041.safetensors +3 -0
  32. model-00030-of-00041.safetensors +3 -0
  33. model-00031-of-00041.safetensors +3 -0
  34. model-00032-of-00041.safetensors +3 -0
  35. model-00033-of-00041.safetensors +3 -0
  36. model-00034-of-00041.safetensors +3 -0
  37. model-00035-of-00041.safetensors +3 -0
  38. model-00036-of-00041.safetensors +3 -0
  39. model-00037-of-00041.safetensors +3 -0
  40. model-00038-of-00041.safetensors +3 -0
  41. model-00039-of-00041.safetensors +3 -0
  42. model-00040-of-00041.safetensors +3 -0
  43. model-00041-of-00041.safetensors +3 -0
  44. model.safetensors.index.json +650 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "falcon-180B-chat-instruct",
3
+ "alibi": false,
4
+ "architectures": [
5
+ "FalconForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bias": false,
9
+ "bos_token_id": 11,
10
+ "eos_token_id": 11,
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 14848,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "model_type": "falcon",
16
+ "multi_query": true,
17
+ "new_decoder_architecture": true,
18
+ "num_attention_heads": 232,
19
+ "num_hidden_layers": 80,
20
+ "num_kv_heads": 8,
21
+ "parallel_attn": true,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 65024
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "eos_token_id": 11,
5
+ "transformers_version": "4.31.0"
6
+ }
model-00001-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0fa13734f56a302f4f65a9d477a3aea53fb845c2c6cfa1aff01d2471ff294f
3
+ size 9046709632
model-00002-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bff5ac95c81a6fffe084b8707ab24e34600e33e735552c7f5aaebf9f05875d
3
+ size 8879580960
model-00003-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7669b21d905352ba95b4b5f7385335fae702f89af245f80f5b8fc262a26a2b9b
3
+ size 8879580960
model-00004-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15a2e92a8d99ddf4b1931ecc40185f278a2c9b6383b134c08d8e19cf24491f38
3
+ size 8879580960
model-00005-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac9634192823166ecf134fff339f3692271378f689bb6f1036b8b5b978325f9e
3
+ size 8879580960
model-00006-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6200782bfaa0572f1887d7eba8b5e7fd5164073aaed06e53139922b29d45af
3
+ size 8879580968
model-00007-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc471bdda4c708d5615d1b2d31b2163b0231e1a24915235472a3bf809e4fc12c
3
+ size 8879580976
model-00008-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89cf8887b0bb33dd64e70a7b6a5fa7db8087688a9c406ef9570841c75f3c6dd1
3
+ size 8879580976
model-00009-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05be12040d386f5cd62a2747cc7f7e573b5c0dbb3d02ee66efda66ac1513a3fd
3
+ size 8879580976
model-00010-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:639e5096e16f4a4911cf51ea9a039f753c4c8c644ce042a7bb85a8425a5a4e22
3
+ size 8879580976
model-00011-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a2fa4a366afaaaaeb6e7941950e713b6c5b37abb79afe3311787f97e73b4b1
3
+ size 8879580976
model-00012-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf355a21f2f44b1abd00f02e7cb0219c6767221f2b6af3c1518cd4149477c041
3
+ size 8879580976
model-00013-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8449f93d84d1348401c25c794dc86f5a7a15db432626fe1e22afdbd3f8034fcd
3
+ size 8879580976
model-00014-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382f0ce96f243cd96dfb4d44cbb5aeb93d6cff68ffb3bd8eb0b940e92f815220
3
+ size 8879580976
model-00015-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae86f8679c0e9b5bec3a90b50f3360b2dcc24eefb24f96b114d287ba11b2fd7
3
+ size 8879580976
model-00016-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ddfa22dc765ec7e88e34915d64209c88883109c589390ee3155d3aa780176bf
3
+ size 8879580976
model-00017-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c0a85378fe31ea049552acfdecdfba9592feab89898a38239c0515f4e52414
3
+ size 8879580976
model-00018-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9ec74e0ce499c479d97ad83c33e9dd0f9b277693cdfc2902bb76670bc493dc
3
+ size 8879580976
model-00019-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6987f343119d5ff218d303cdf18f2f7c393babd74f6b2e79eb79a85e125907
3
+ size 8879580976
model-00020-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:712995c95b2900efd9e2de1714e259c961f7ad076909bb1352ae1aa63f39d4b3
3
+ size 8879580976
model-00021-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65792f2069b83062228686d68598a3d7a1d27531879db7267882f6dcc271904c
3
+ size 8879580976
model-00022-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a89fab137551b6d1660b685767ad0065a3917138093a4077dd3d6e8087608b4
3
+ size 8879580976
model-00023-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87cf46acfcd49ba799b7dfd248c5bbf76453932773b315decfa1c26983563ca
3
+ size 8879580976
model-00024-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b66390bb89c45b15305c1b3feeb626cdc7a8c398932b0efae962c0e76977df
3
+ size 8879580976
model-00025-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:964a71f9482c9a819a3aa051151590145f4ea770c7bd77a30b141dcaa9e42faa
3
+ size 8879580976
model-00026-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f361547f53b1e0906531bae86ed95508da90077e6a293bbfec4cd868eae0c4d
3
+ size 8879580976
model-00027-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9cdc4af96557d3dd996cd5acd699d1b3a7a8777d2028528e798e8e3d95932e
3
+ size 8879580976
model-00028-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f544618606e7f212a54bf83c10bac8ac9de2c26d9fd7fb2e5ec7d0247cdfd99e
3
+ size 8879580976
model-00029-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84fb596166224dc19ef7d8e379b7d9d4054bfc0dcb2c79617d227fab2ed32b25
3
+ size 8879580976
model-00030-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebbe4864608f7e0605a90aa11aea5d11301ed3dac74aa99cf87d1016bd503c79
3
+ size 8879580976
model-00031-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21beeea55f1235e7c92c816e1bdb62a1bf0663815aa0bafd9fee80402b1b94ac
3
+ size 8879580976
model-00032-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c1a7db2b25809e1339defef06319a26d03af8bed24951b5698cb648783e834
3
+ size 8879580976
model-00033-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f810799eee280e8e3f60652d3dc05b69e0a948672463e9e63c33e690b95fdb1
3
+ size 8879580976
model-00034-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ec3450620b199036209aeea7fc489dcc8c7c7f19fbb6f5154e8a191a950e31
3
+ size 8879580976
model-00035-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c329b5ae35e85333893ecd3f00ff75fbe86acf13a8a0d371de20356b50b94cb
3
+ size 8879580976
model-00036-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f28a5a3b250b3e16ca944467f3795b81cbec82e3275c875cb5a7a86fa63c7e2
3
+ size 8879580976
model-00037-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2239c11ef9b59677eeecaab9c9f3f996081195e4226e973f0818f9914878fe66
3
+ size 8879580976
model-00038-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cecf1eb322a8107b0b229f5b4b8275223bb42c51af7c8b2e4796b2cb9239244d
3
+ size 8879580976
model-00039-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da04a98674b82c9362d1f5991efa8b3388c6ae62d42268252e1bd07185d075d7
3
+ size 8879580976
model-00040-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe96cc3b14b1d0be882a0180e466e18e85c48916cdf6edf26eadec16a810afb8
3
+ size 8879580976
model-00041-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a7b29896999887da12780ab62087d6a3f17ffedc0c08ed81bfa12581d36ad5
3
+ size 1763883736
model.safetensors.index.json ADDED
@@ -0,0 +1,650 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 357114177536
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.ln_attn.bias": "model-00001-of-00041.safetensors",
7
+ "transformer.h.0.ln_attn.weight": "model-00001-of-00041.safetensors",
8
+ "transformer.h.0.ln_mlp.bias": "model-00001-of-00041.safetensors",
9
+ "transformer.h.0.ln_mlp.weight": "model-00001-of-00041.safetensors",
10
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00041.safetensors",
11
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00041.safetensors",
12
+ "transformer.h.0.self_attention.dense.weight": "model-00001-of-00041.safetensors",
13
+ "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00041.safetensors",
14
+ "transformer.h.1.ln_attn.bias": "model-00002-of-00041.safetensors",
15
+ "transformer.h.1.ln_attn.weight": "model-00002-of-00041.safetensors",
16
+ "transformer.h.1.ln_mlp.bias": "model-00002-of-00041.safetensors",
17
+ "transformer.h.1.ln_mlp.weight": "model-00002-of-00041.safetensors",
18
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00041.safetensors",
19
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00041.safetensors",
20
+ "transformer.h.1.self_attention.dense.weight": "model-00001-of-00041.safetensors",
21
+ "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00041.safetensors",
22
+ "transformer.h.10.ln_attn.bias": "model-00006-of-00041.safetensors",
23
+ "transformer.h.10.ln_attn.weight": "model-00006-of-00041.safetensors",
24
+ "transformer.h.10.ln_mlp.bias": "model-00006-of-00041.safetensors",
25
+ "transformer.h.10.ln_mlp.weight": "model-00006-of-00041.safetensors",
26
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00006-of-00041.safetensors",
27
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00006-of-00041.safetensors",
28
+ "transformer.h.10.self_attention.dense.weight": "model-00006-of-00041.safetensors",
29
+ "transformer.h.10.self_attention.query_key_value.weight": "model-00006-of-00041.safetensors",
30
+ "transformer.h.11.ln_attn.bias": "model-00007-of-00041.safetensors",
31
+ "transformer.h.11.ln_attn.weight": "model-00007-of-00041.safetensors",
32
+ "transformer.h.11.ln_mlp.bias": "model-00007-of-00041.safetensors",
33
+ "transformer.h.11.ln_mlp.weight": "model-00007-of-00041.safetensors",
34
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00007-of-00041.safetensors",
35
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00006-of-00041.safetensors",
36
+ "transformer.h.11.self_attention.dense.weight": "model-00006-of-00041.safetensors",
37
+ "transformer.h.11.self_attention.query_key_value.weight": "model-00006-of-00041.safetensors",
38
+ "transformer.h.12.ln_attn.bias": "model-00007-of-00041.safetensors",
39
+ "transformer.h.12.ln_attn.weight": "model-00007-of-00041.safetensors",
40
+ "transformer.h.12.ln_mlp.bias": "model-00007-of-00041.safetensors",
41
+ "transformer.h.12.ln_mlp.weight": "model-00007-of-00041.safetensors",
42
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00007-of-00041.safetensors",
43
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00007-of-00041.safetensors",
44
+ "transformer.h.12.self_attention.dense.weight": "model-00007-of-00041.safetensors",
45
+ "transformer.h.12.self_attention.query_key_value.weight": "model-00007-of-00041.safetensors",
46
+ "transformer.h.13.ln_attn.bias": "model-00008-of-00041.safetensors",
47
+ "transformer.h.13.ln_attn.weight": "model-00008-of-00041.safetensors",
48
+ "transformer.h.13.ln_mlp.bias": "model-00008-of-00041.safetensors",
49
+ "transformer.h.13.ln_mlp.weight": "model-00008-of-00041.safetensors",
50
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00008-of-00041.safetensors",
51
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00007-of-00041.safetensors",
52
+ "transformer.h.13.self_attention.dense.weight": "model-00007-of-00041.safetensors",
53
+ "transformer.h.13.self_attention.query_key_value.weight": "model-00007-of-00041.safetensors",
54
+ "transformer.h.14.ln_attn.bias": "model-00008-of-00041.safetensors",
55
+ "transformer.h.14.ln_attn.weight": "model-00008-of-00041.safetensors",
56
+ "transformer.h.14.ln_mlp.bias": "model-00008-of-00041.safetensors",
57
+ "transformer.h.14.ln_mlp.weight": "model-00008-of-00041.safetensors",
58
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00008-of-00041.safetensors",
59
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00008-of-00041.safetensors",
60
+ "transformer.h.14.self_attention.dense.weight": "model-00008-of-00041.safetensors",
61
+ "transformer.h.14.self_attention.query_key_value.weight": "model-00008-of-00041.safetensors",
62
+ "transformer.h.15.ln_attn.bias": "model-00009-of-00041.safetensors",
63
+ "transformer.h.15.ln_attn.weight": "model-00009-of-00041.safetensors",
64
+ "transformer.h.15.ln_mlp.bias": "model-00009-of-00041.safetensors",
65
+ "transformer.h.15.ln_mlp.weight": "model-00009-of-00041.safetensors",
66
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00009-of-00041.safetensors",
67
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00008-of-00041.safetensors",
68
+ "transformer.h.15.self_attention.dense.weight": "model-00008-of-00041.safetensors",
69
+ "transformer.h.15.self_attention.query_key_value.weight": "model-00008-of-00041.safetensors",
70
+ "transformer.h.16.ln_attn.bias": "model-00009-of-00041.safetensors",
71
+ "transformer.h.16.ln_attn.weight": "model-00009-of-00041.safetensors",
72
+ "transformer.h.16.ln_mlp.bias": "model-00009-of-00041.safetensors",
73
+ "transformer.h.16.ln_mlp.weight": "model-00009-of-00041.safetensors",
74
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00009-of-00041.safetensors",
75
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00009-of-00041.safetensors",
76
+ "transformer.h.16.self_attention.dense.weight": "model-00009-of-00041.safetensors",
77
+ "transformer.h.16.self_attention.query_key_value.weight": "model-00009-of-00041.safetensors",
78
+ "transformer.h.17.ln_attn.bias": "model-00010-of-00041.safetensors",
79
+ "transformer.h.17.ln_attn.weight": "model-00010-of-00041.safetensors",
80
+ "transformer.h.17.ln_mlp.bias": "model-00010-of-00041.safetensors",
81
+ "transformer.h.17.ln_mlp.weight": "model-00010-of-00041.safetensors",
82
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00010-of-00041.safetensors",
83
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00009-of-00041.safetensors",
84
+ "transformer.h.17.self_attention.dense.weight": "model-00009-of-00041.safetensors",
85
+ "transformer.h.17.self_attention.query_key_value.weight": "model-00009-of-00041.safetensors",
86
+ "transformer.h.18.ln_attn.bias": "model-00010-of-00041.safetensors",
87
+ "transformer.h.18.ln_attn.weight": "model-00010-of-00041.safetensors",
88
+ "transformer.h.18.ln_mlp.bias": "model-00010-of-00041.safetensors",
89
+ "transformer.h.18.ln_mlp.weight": "model-00010-of-00041.safetensors",
90
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00010-of-00041.safetensors",
91
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00010-of-00041.safetensors",
92
+ "transformer.h.18.self_attention.dense.weight": "model-00010-of-00041.safetensors",
93
+ "transformer.h.18.self_attention.query_key_value.weight": "model-00010-of-00041.safetensors",
94
+ "transformer.h.19.ln_attn.bias": "model-00011-of-00041.safetensors",
95
+ "transformer.h.19.ln_attn.weight": "model-00011-of-00041.safetensors",
96
+ "transformer.h.19.ln_mlp.bias": "model-00011-of-00041.safetensors",
97
+ "transformer.h.19.ln_mlp.weight": "model-00011-of-00041.safetensors",
98
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00011-of-00041.safetensors",
99
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00010-of-00041.safetensors",
100
+ "transformer.h.19.self_attention.dense.weight": "model-00010-of-00041.safetensors",
101
+ "transformer.h.19.self_attention.query_key_value.weight": "model-00010-of-00041.safetensors",
102
+ "transformer.h.2.ln_attn.bias": "model-00002-of-00041.safetensors",
103
+ "transformer.h.2.ln_attn.weight": "model-00002-of-00041.safetensors",
104
+ "transformer.h.2.ln_mlp.bias": "model-00002-of-00041.safetensors",
105
+ "transformer.h.2.ln_mlp.weight": "model-00002-of-00041.safetensors",
106
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00002-of-00041.safetensors",
107
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00002-of-00041.safetensors",
108
+ "transformer.h.2.self_attention.dense.weight": "model-00002-of-00041.safetensors",
109
+ "transformer.h.2.self_attention.query_key_value.weight": "model-00002-of-00041.safetensors",
110
+ "transformer.h.20.ln_attn.bias": "model-00011-of-00041.safetensors",
111
+ "transformer.h.20.ln_attn.weight": "model-00011-of-00041.safetensors",
112
+ "transformer.h.20.ln_mlp.bias": "model-00011-of-00041.safetensors",
113
+ "transformer.h.20.ln_mlp.weight": "model-00011-of-00041.safetensors",
114
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00011-of-00041.safetensors",
115
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00011-of-00041.safetensors",
116
+ "transformer.h.20.self_attention.dense.weight": "model-00011-of-00041.safetensors",
117
+ "transformer.h.20.self_attention.query_key_value.weight": "model-00011-of-00041.safetensors",
118
+ "transformer.h.21.ln_attn.bias": "model-00012-of-00041.safetensors",
119
+ "transformer.h.21.ln_attn.weight": "model-00012-of-00041.safetensors",
120
+ "transformer.h.21.ln_mlp.bias": "model-00012-of-00041.safetensors",
121
+ "transformer.h.21.ln_mlp.weight": "model-00012-of-00041.safetensors",
122
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00012-of-00041.safetensors",
123
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00011-of-00041.safetensors",
124
+ "transformer.h.21.self_attention.dense.weight": "model-00011-of-00041.safetensors",
125
+ "transformer.h.21.self_attention.query_key_value.weight": "model-00011-of-00041.safetensors",
126
+ "transformer.h.22.ln_attn.bias": "model-00012-of-00041.safetensors",
127
+ "transformer.h.22.ln_attn.weight": "model-00012-of-00041.safetensors",
128
+ "transformer.h.22.ln_mlp.bias": "model-00012-of-00041.safetensors",
129
+ "transformer.h.22.ln_mlp.weight": "model-00012-of-00041.safetensors",
130
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00012-of-00041.safetensors",
131
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00012-of-00041.safetensors",
132
+ "transformer.h.22.self_attention.dense.weight": "model-00012-of-00041.safetensors",
133
+ "transformer.h.22.self_attention.query_key_value.weight": "model-00012-of-00041.safetensors",
134
+ "transformer.h.23.ln_attn.bias": "model-00013-of-00041.safetensors",
135
+ "transformer.h.23.ln_attn.weight": "model-00013-of-00041.safetensors",
136
+ "transformer.h.23.ln_mlp.bias": "model-00013-of-00041.safetensors",
137
+ "transformer.h.23.ln_mlp.weight": "model-00013-of-00041.safetensors",
138
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00013-of-00041.safetensors",
139
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00012-of-00041.safetensors",
140
+ "transformer.h.23.self_attention.dense.weight": "model-00012-of-00041.safetensors",
141
+ "transformer.h.23.self_attention.query_key_value.weight": "model-00012-of-00041.safetensors",
142
+ "transformer.h.24.ln_attn.bias": "model-00013-of-00041.safetensors",
143
+ "transformer.h.24.ln_attn.weight": "model-00013-of-00041.safetensors",
144
+ "transformer.h.24.ln_mlp.bias": "model-00013-of-00041.safetensors",
145
+ "transformer.h.24.ln_mlp.weight": "model-00013-of-00041.safetensors",
146
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00013-of-00041.safetensors",
147
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00013-of-00041.safetensors",
148
+ "transformer.h.24.self_attention.dense.weight": "model-00013-of-00041.safetensors",
149
+ "transformer.h.24.self_attention.query_key_value.weight": "model-00013-of-00041.safetensors",
150
+ "transformer.h.25.ln_attn.bias": "model-00014-of-00041.safetensors",
151
+ "transformer.h.25.ln_attn.weight": "model-00014-of-00041.safetensors",
152
+ "transformer.h.25.ln_mlp.bias": "model-00014-of-00041.safetensors",
153
+ "transformer.h.25.ln_mlp.weight": "model-00014-of-00041.safetensors",
154
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00014-of-00041.safetensors",
155
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00013-of-00041.safetensors",
156
+ "transformer.h.25.self_attention.dense.weight": "model-00013-of-00041.safetensors",
157
+ "transformer.h.25.self_attention.query_key_value.weight": "model-00013-of-00041.safetensors",
158
+ "transformer.h.26.ln_attn.bias": "model-00014-of-00041.safetensors",
159
+ "transformer.h.26.ln_attn.weight": "model-00014-of-00041.safetensors",
160
+ "transformer.h.26.ln_mlp.bias": "model-00014-of-00041.safetensors",
161
+ "transformer.h.26.ln_mlp.weight": "model-00014-of-00041.safetensors",
162
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00014-of-00041.safetensors",
163
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00014-of-00041.safetensors",
164
+ "transformer.h.26.self_attention.dense.weight": "model-00014-of-00041.safetensors",
165
+ "transformer.h.26.self_attention.query_key_value.weight": "model-00014-of-00041.safetensors",
166
+ "transformer.h.27.ln_attn.bias": "model-00015-of-00041.safetensors",
167
+ "transformer.h.27.ln_attn.weight": "model-00015-of-00041.safetensors",
168
+ "transformer.h.27.ln_mlp.bias": "model-00015-of-00041.safetensors",
169
+ "transformer.h.27.ln_mlp.weight": "model-00015-of-00041.safetensors",
170
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00015-of-00041.safetensors",
171
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00014-of-00041.safetensors",
172
+ "transformer.h.27.self_attention.dense.weight": "model-00014-of-00041.safetensors",
173
+ "transformer.h.27.self_attention.query_key_value.weight": "model-00014-of-00041.safetensors",
174
+ "transformer.h.28.ln_attn.bias": "model-00015-of-00041.safetensors",
175
+ "transformer.h.28.ln_attn.weight": "model-00015-of-00041.safetensors",
176
+ "transformer.h.28.ln_mlp.bias": "model-00015-of-00041.safetensors",
177
+ "transformer.h.28.ln_mlp.weight": "model-00015-of-00041.safetensors",
178
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00015-of-00041.safetensors",
179
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00015-of-00041.safetensors",
180
+ "transformer.h.28.self_attention.dense.weight": "model-00015-of-00041.safetensors",
181
+ "transformer.h.28.self_attention.query_key_value.weight": "model-00015-of-00041.safetensors",
182
+ "transformer.h.29.ln_attn.bias": "model-00016-of-00041.safetensors",
183
+ "transformer.h.29.ln_attn.weight": "model-00016-of-00041.safetensors",
184
+ "transformer.h.29.ln_mlp.bias": "model-00016-of-00041.safetensors",
185
+ "transformer.h.29.ln_mlp.weight": "model-00016-of-00041.safetensors",
186
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00016-of-00041.safetensors",
187
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00015-of-00041.safetensors",
188
+ "transformer.h.29.self_attention.dense.weight": "model-00015-of-00041.safetensors",
189
+ "transformer.h.29.self_attention.query_key_value.weight": "model-00015-of-00041.safetensors",
190
+ "transformer.h.3.ln_attn.bias": "model-00003-of-00041.safetensors",
191
+ "transformer.h.3.ln_attn.weight": "model-00003-of-00041.safetensors",
192
+ "transformer.h.3.ln_mlp.bias": "model-00003-of-00041.safetensors",
193
+ "transformer.h.3.ln_mlp.weight": "model-00003-of-00041.safetensors",
194
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00003-of-00041.safetensors",
195
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00041.safetensors",
196
+ "transformer.h.3.self_attention.dense.weight": "model-00002-of-00041.safetensors",
197
+ "transformer.h.3.self_attention.query_key_value.weight": "model-00002-of-00041.safetensors",
198
+ "transformer.h.30.ln_attn.bias": "model-00016-of-00041.safetensors",
199
+ "transformer.h.30.ln_attn.weight": "model-00016-of-00041.safetensors",
200
+ "transformer.h.30.ln_mlp.bias": "model-00016-of-00041.safetensors",
201
+ "transformer.h.30.ln_mlp.weight": "model-00016-of-00041.safetensors",
202
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00016-of-00041.safetensors",
203
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00016-of-00041.safetensors",
204
+ "transformer.h.30.self_attention.dense.weight": "model-00016-of-00041.safetensors",
205
+ "transformer.h.30.self_attention.query_key_value.weight": "model-00016-of-00041.safetensors",
206
+ "transformer.h.31.ln_attn.bias": "model-00017-of-00041.safetensors",
207
+ "transformer.h.31.ln_attn.weight": "model-00017-of-00041.safetensors",
208
+ "transformer.h.31.ln_mlp.bias": "model-00017-of-00041.safetensors",
209
+ "transformer.h.31.ln_mlp.weight": "model-00017-of-00041.safetensors",
210
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00017-of-00041.safetensors",
211
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00016-of-00041.safetensors",
212
+ "transformer.h.31.self_attention.dense.weight": "model-00016-of-00041.safetensors",
213
+ "transformer.h.31.self_attention.query_key_value.weight": "model-00016-of-00041.safetensors",
214
+ "transformer.h.32.ln_attn.bias": "model-00017-of-00041.safetensors",
215
+ "transformer.h.32.ln_attn.weight": "model-00017-of-00041.safetensors",
216
+ "transformer.h.32.ln_mlp.bias": "model-00017-of-00041.safetensors",
217
+ "transformer.h.32.ln_mlp.weight": "model-00017-of-00041.safetensors",
218
+ "transformer.h.32.mlp.dense_4h_to_h.weight": "model-00017-of-00041.safetensors",
219
+ "transformer.h.32.mlp.dense_h_to_4h.weight": "model-00017-of-00041.safetensors",
220
+ "transformer.h.32.self_attention.dense.weight": "model-00017-of-00041.safetensors",
221
+ "transformer.h.32.self_attention.query_key_value.weight": "model-00017-of-00041.safetensors",
222
+ "transformer.h.33.ln_attn.bias": "model-00018-of-00041.safetensors",
223
+ "transformer.h.33.ln_attn.weight": "model-00018-of-00041.safetensors",
224
+ "transformer.h.33.ln_mlp.bias": "model-00018-of-00041.safetensors",
225
+ "transformer.h.33.ln_mlp.weight": "model-00018-of-00041.safetensors",
226
+ "transformer.h.33.mlp.dense_4h_to_h.weight": "model-00018-of-00041.safetensors",
227
+ "transformer.h.33.mlp.dense_h_to_4h.weight": "model-00017-of-00041.safetensors",
228
+ "transformer.h.33.self_attention.dense.weight": "model-00017-of-00041.safetensors",
229
+ "transformer.h.33.self_attention.query_key_value.weight": "model-00017-of-00041.safetensors",
230
+ "transformer.h.34.ln_attn.bias": "model-00018-of-00041.safetensors",
231
+ "transformer.h.34.ln_attn.weight": "model-00018-of-00041.safetensors",
232
+ "transformer.h.34.ln_mlp.bias": "model-00018-of-00041.safetensors",
233
+ "transformer.h.34.ln_mlp.weight": "model-00018-of-00041.safetensors",
234
+ "transformer.h.34.mlp.dense_4h_to_h.weight": "model-00018-of-00041.safetensors",
235
+ "transformer.h.34.mlp.dense_h_to_4h.weight": "model-00018-of-00041.safetensors",
236
+ "transformer.h.34.self_attention.dense.weight": "model-00018-of-00041.safetensors",
237
+ "transformer.h.34.self_attention.query_key_value.weight": "model-00018-of-00041.safetensors",
238
+ "transformer.h.35.ln_attn.bias": "model-00019-of-00041.safetensors",
239
+ "transformer.h.35.ln_attn.weight": "model-00019-of-00041.safetensors",
240
+ "transformer.h.35.ln_mlp.bias": "model-00019-of-00041.safetensors",
241
+ "transformer.h.35.ln_mlp.weight": "model-00019-of-00041.safetensors",
242
+ "transformer.h.35.mlp.dense_4h_to_h.weight": "model-00019-of-00041.safetensors",
243
+ "transformer.h.35.mlp.dense_h_to_4h.weight": "model-00018-of-00041.safetensors",
244
+ "transformer.h.35.self_attention.dense.weight": "model-00018-of-00041.safetensors",
245
+ "transformer.h.35.self_attention.query_key_value.weight": "model-00018-of-00041.safetensors",
246
+ "transformer.h.36.ln_attn.bias": "model-00019-of-00041.safetensors",
247
+ "transformer.h.36.ln_attn.weight": "model-00019-of-00041.safetensors",
248
+ "transformer.h.36.ln_mlp.bias": "model-00019-of-00041.safetensors",
249
+ "transformer.h.36.ln_mlp.weight": "model-00019-of-00041.safetensors",
250
+ "transformer.h.36.mlp.dense_4h_to_h.weight": "model-00019-of-00041.safetensors",
251
+ "transformer.h.36.mlp.dense_h_to_4h.weight": "model-00019-of-00041.safetensors",
252
+ "transformer.h.36.self_attention.dense.weight": "model-00019-of-00041.safetensors",
253
+ "transformer.h.36.self_attention.query_key_value.weight": "model-00019-of-00041.safetensors",
254
+ "transformer.h.37.ln_attn.bias": "model-00020-of-00041.safetensors",
255
+ "transformer.h.37.ln_attn.weight": "model-00020-of-00041.safetensors",
256
+ "transformer.h.37.ln_mlp.bias": "model-00020-of-00041.safetensors",
257
+ "transformer.h.37.ln_mlp.weight": "model-00020-of-00041.safetensors",
258
+ "transformer.h.37.mlp.dense_4h_to_h.weight": "model-00020-of-00041.safetensors",
259
+ "transformer.h.37.mlp.dense_h_to_4h.weight": "model-00019-of-00041.safetensors",
260
+ "transformer.h.37.self_attention.dense.weight": "model-00019-of-00041.safetensors",
261
+ "transformer.h.37.self_attention.query_key_value.weight": "model-00019-of-00041.safetensors",
262
+ "transformer.h.38.ln_attn.bias": "model-00020-of-00041.safetensors",
263
+ "transformer.h.38.ln_attn.weight": "model-00020-of-00041.safetensors",
264
+ "transformer.h.38.ln_mlp.bias": "model-00020-of-00041.safetensors",
265
+ "transformer.h.38.ln_mlp.weight": "model-00020-of-00041.safetensors",
266
+ "transformer.h.38.mlp.dense_4h_to_h.weight": "model-00020-of-00041.safetensors",
267
+ "transformer.h.38.mlp.dense_h_to_4h.weight": "model-00020-of-00041.safetensors",
268
+ "transformer.h.38.self_attention.dense.weight": "model-00020-of-00041.safetensors",
269
+ "transformer.h.38.self_attention.query_key_value.weight": "model-00020-of-00041.safetensors",
270
+ "transformer.h.39.ln_attn.bias": "model-00021-of-00041.safetensors",
271
+ "transformer.h.39.ln_attn.weight": "model-00021-of-00041.safetensors",
272
+ "transformer.h.39.ln_mlp.bias": "model-00021-of-00041.safetensors",
273
+ "transformer.h.39.ln_mlp.weight": "model-00021-of-00041.safetensors",
274
+ "transformer.h.39.mlp.dense_4h_to_h.weight": "model-00021-of-00041.safetensors",
275
+ "transformer.h.39.mlp.dense_h_to_4h.weight": "model-00020-of-00041.safetensors",
276
+ "transformer.h.39.self_attention.dense.weight": "model-00020-of-00041.safetensors",
277
+ "transformer.h.39.self_attention.query_key_value.weight": "model-00020-of-00041.safetensors",
278
+ "transformer.h.4.ln_attn.bias": "model-00003-of-00041.safetensors",
279
+ "transformer.h.4.ln_attn.weight": "model-00003-of-00041.safetensors",
280
+ "transformer.h.4.ln_mlp.bias": "model-00003-of-00041.safetensors",
281
+ "transformer.h.4.ln_mlp.weight": "model-00003-of-00041.safetensors",
282
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00003-of-00041.safetensors",
283
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00003-of-00041.safetensors",
284
+ "transformer.h.4.self_attention.dense.weight": "model-00003-of-00041.safetensors",
285
+ "transformer.h.4.self_attention.query_key_value.weight": "model-00003-of-00041.safetensors",
286
+ "transformer.h.40.ln_attn.bias": "model-00021-of-00041.safetensors",
287
+ "transformer.h.40.ln_attn.weight": "model-00021-of-00041.safetensors",
288
+ "transformer.h.40.ln_mlp.bias": "model-00021-of-00041.safetensors",
289
+ "transformer.h.40.ln_mlp.weight": "model-00021-of-00041.safetensors",
290
+ "transformer.h.40.mlp.dense_4h_to_h.weight": "model-00021-of-00041.safetensors",
291
+ "transformer.h.40.mlp.dense_h_to_4h.weight": "model-00021-of-00041.safetensors",
292
+ "transformer.h.40.self_attention.dense.weight": "model-00021-of-00041.safetensors",
293
+ "transformer.h.40.self_attention.query_key_value.weight": "model-00021-of-00041.safetensors",
294
+ "transformer.h.41.ln_attn.bias": "model-00022-of-00041.safetensors",
295
+ "transformer.h.41.ln_attn.weight": "model-00022-of-00041.safetensors",
296
+ "transformer.h.41.ln_mlp.bias": "model-00022-of-00041.safetensors",
297
+ "transformer.h.41.ln_mlp.weight": "model-00022-of-00041.safetensors",
298
+ "transformer.h.41.mlp.dense_4h_to_h.weight": "model-00022-of-00041.safetensors",
299
+ "transformer.h.41.mlp.dense_h_to_4h.weight": "model-00021-of-00041.safetensors",
300
+ "transformer.h.41.self_attention.dense.weight": "model-00021-of-00041.safetensors",
301
+ "transformer.h.41.self_attention.query_key_value.weight": "model-00021-of-00041.safetensors",
302
+ "transformer.h.42.ln_attn.bias": "model-00022-of-00041.safetensors",
303
+ "transformer.h.42.ln_attn.weight": "model-00022-of-00041.safetensors",
304
+ "transformer.h.42.ln_mlp.bias": "model-00022-of-00041.safetensors",
305
+ "transformer.h.42.ln_mlp.weight": "model-00022-of-00041.safetensors",
306
+ "transformer.h.42.mlp.dense_4h_to_h.weight": "model-00022-of-00041.safetensors",
307
+ "transformer.h.42.mlp.dense_h_to_4h.weight": "model-00022-of-00041.safetensors",
308
+ "transformer.h.42.self_attention.dense.weight": "model-00022-of-00041.safetensors",
309
+ "transformer.h.42.self_attention.query_key_value.weight": "model-00022-of-00041.safetensors",
310
+ "transformer.h.43.ln_attn.bias": "model-00023-of-00041.safetensors",
311
+ "transformer.h.43.ln_attn.weight": "model-00023-of-00041.safetensors",
312
+ "transformer.h.43.ln_mlp.bias": "model-00023-of-00041.safetensors",
313
+ "transformer.h.43.ln_mlp.weight": "model-00023-of-00041.safetensors",
314
+ "transformer.h.43.mlp.dense_4h_to_h.weight": "model-00023-of-00041.safetensors",
315
+ "transformer.h.43.mlp.dense_h_to_4h.weight": "model-00022-of-00041.safetensors",
316
+ "transformer.h.43.self_attention.dense.weight": "model-00022-of-00041.safetensors",
317
+ "transformer.h.43.self_attention.query_key_value.weight": "model-00022-of-00041.safetensors",
318
+ "transformer.h.44.ln_attn.bias": "model-00023-of-00041.safetensors",
319
+ "transformer.h.44.ln_attn.weight": "model-00023-of-00041.safetensors",
320
+ "transformer.h.44.ln_mlp.bias": "model-00023-of-00041.safetensors",
321
+ "transformer.h.44.ln_mlp.weight": "model-00023-of-00041.safetensors",
322
+ "transformer.h.44.mlp.dense_4h_to_h.weight": "model-00023-of-00041.safetensors",
323
+ "transformer.h.44.mlp.dense_h_to_4h.weight": "model-00023-of-00041.safetensors",
324
+ "transformer.h.44.self_attention.dense.weight": "model-00023-of-00041.safetensors",
325
+ "transformer.h.44.self_attention.query_key_value.weight": "model-00023-of-00041.safetensors",
326
+ "transformer.h.45.ln_attn.bias": "model-00024-of-00041.safetensors",
327
+ "transformer.h.45.ln_attn.weight": "model-00024-of-00041.safetensors",
328
+ "transformer.h.45.ln_mlp.bias": "model-00024-of-00041.safetensors",
329
+ "transformer.h.45.ln_mlp.weight": "model-00024-of-00041.safetensors",
330
+ "transformer.h.45.mlp.dense_4h_to_h.weight": "model-00024-of-00041.safetensors",
331
+ "transformer.h.45.mlp.dense_h_to_4h.weight": "model-00023-of-00041.safetensors",
332
+ "transformer.h.45.self_attention.dense.weight": "model-00023-of-00041.safetensors",
333
+ "transformer.h.45.self_attention.query_key_value.weight": "model-00023-of-00041.safetensors",
334
+ "transformer.h.46.ln_attn.bias": "model-00024-of-00041.safetensors",
335
+ "transformer.h.46.ln_attn.weight": "model-00024-of-00041.safetensors",
336
+ "transformer.h.46.ln_mlp.bias": "model-00024-of-00041.safetensors",
337
+ "transformer.h.46.ln_mlp.weight": "model-00024-of-00041.safetensors",
338
+ "transformer.h.46.mlp.dense_4h_to_h.weight": "model-00024-of-00041.safetensors",
339
+ "transformer.h.46.mlp.dense_h_to_4h.weight": "model-00024-of-00041.safetensors",
340
+ "transformer.h.46.self_attention.dense.weight": "model-00024-of-00041.safetensors",
341
+ "transformer.h.46.self_attention.query_key_value.weight": "model-00024-of-00041.safetensors",
342
+ "transformer.h.47.ln_attn.bias": "model-00025-of-00041.safetensors",
343
+ "transformer.h.47.ln_attn.weight": "model-00025-of-00041.safetensors",
344
+ "transformer.h.47.ln_mlp.bias": "model-00025-of-00041.safetensors",
345
+ "transformer.h.47.ln_mlp.weight": "model-00025-of-00041.safetensors",
346
+ "transformer.h.47.mlp.dense_4h_to_h.weight": "model-00025-of-00041.safetensors",
347
+ "transformer.h.47.mlp.dense_h_to_4h.weight": "model-00024-of-00041.safetensors",
348
+ "transformer.h.47.self_attention.dense.weight": "model-00024-of-00041.safetensors",
349
+ "transformer.h.47.self_attention.query_key_value.weight": "model-00024-of-00041.safetensors",
350
+ "transformer.h.48.ln_attn.bias": "model-00025-of-00041.safetensors",
351
+ "transformer.h.48.ln_attn.weight": "model-00025-of-00041.safetensors",
352
+ "transformer.h.48.ln_mlp.bias": "model-00025-of-00041.safetensors",
353
+ "transformer.h.48.ln_mlp.weight": "model-00025-of-00041.safetensors",
354
+ "transformer.h.48.mlp.dense_4h_to_h.weight": "model-00025-of-00041.safetensors",
355
+ "transformer.h.48.mlp.dense_h_to_4h.weight": "model-00025-of-00041.safetensors",
356
+ "transformer.h.48.self_attention.dense.weight": "model-00025-of-00041.safetensors",
357
+ "transformer.h.48.self_attention.query_key_value.weight": "model-00025-of-00041.safetensors",
358
+ "transformer.h.49.ln_attn.bias": "model-00026-of-00041.safetensors",
359
+ "transformer.h.49.ln_attn.weight": "model-00026-of-00041.safetensors",
360
+ "transformer.h.49.ln_mlp.bias": "model-00026-of-00041.safetensors",
361
+ "transformer.h.49.ln_mlp.weight": "model-00026-of-00041.safetensors",
362
+ "transformer.h.49.mlp.dense_4h_to_h.weight": "model-00026-of-00041.safetensors",
363
+ "transformer.h.49.mlp.dense_h_to_4h.weight": "model-00025-of-00041.safetensors",
364
+ "transformer.h.49.self_attention.dense.weight": "model-00025-of-00041.safetensors",
365
+ "transformer.h.49.self_attention.query_key_value.weight": "model-00025-of-00041.safetensors",
366
+ "transformer.h.5.ln_attn.bias": "model-00004-of-00041.safetensors",
367
+ "transformer.h.5.ln_attn.weight": "model-00004-of-00041.safetensors",
368
+ "transformer.h.5.ln_mlp.bias": "model-00004-of-00041.safetensors",
369
+ "transformer.h.5.ln_mlp.weight": "model-00004-of-00041.safetensors",
370
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00004-of-00041.safetensors",
371
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00003-of-00041.safetensors",
372
+ "transformer.h.5.self_attention.dense.weight": "model-00003-of-00041.safetensors",
373
+ "transformer.h.5.self_attention.query_key_value.weight": "model-00003-of-00041.safetensors",
374
+ "transformer.h.50.ln_attn.bias": "model-00026-of-00041.safetensors",
375
+ "transformer.h.50.ln_attn.weight": "model-00026-of-00041.safetensors",
376
+ "transformer.h.50.ln_mlp.bias": "model-00026-of-00041.safetensors",
377
+ "transformer.h.50.ln_mlp.weight": "model-00026-of-00041.safetensors",
378
+ "transformer.h.50.mlp.dense_4h_to_h.weight": "model-00026-of-00041.safetensors",
379
+ "transformer.h.50.mlp.dense_h_to_4h.weight": "model-00026-of-00041.safetensors",
380
+ "transformer.h.50.self_attention.dense.weight": "model-00026-of-00041.safetensors",
381
+ "transformer.h.50.self_attention.query_key_value.weight": "model-00026-of-00041.safetensors",
382
+ "transformer.h.51.ln_attn.bias": "model-00027-of-00041.safetensors",
383
+ "transformer.h.51.ln_attn.weight": "model-00027-of-00041.safetensors",
384
+ "transformer.h.51.ln_mlp.bias": "model-00027-of-00041.safetensors",
385
+ "transformer.h.51.ln_mlp.weight": "model-00027-of-00041.safetensors",
386
+ "transformer.h.51.mlp.dense_4h_to_h.weight": "model-00027-of-00041.safetensors",
387
+ "transformer.h.51.mlp.dense_h_to_4h.weight": "model-00026-of-00041.safetensors",
388
+ "transformer.h.51.self_attention.dense.weight": "model-00026-of-00041.safetensors",
389
+ "transformer.h.51.self_attention.query_key_value.weight": "model-00026-of-00041.safetensors",
390
+ "transformer.h.52.ln_attn.bias": "model-00027-of-00041.safetensors",
391
+ "transformer.h.52.ln_attn.weight": "model-00027-of-00041.safetensors",
392
+ "transformer.h.52.ln_mlp.bias": "model-00027-of-00041.safetensors",
393
+ "transformer.h.52.ln_mlp.weight": "model-00027-of-00041.safetensors",
394
+ "transformer.h.52.mlp.dense_4h_to_h.weight": "model-00027-of-00041.safetensors",
395
+ "transformer.h.52.mlp.dense_h_to_4h.weight": "model-00027-of-00041.safetensors",
396
+ "transformer.h.52.self_attention.dense.weight": "model-00027-of-00041.safetensors",
397
+ "transformer.h.52.self_attention.query_key_value.weight": "model-00027-of-00041.safetensors",
398
+ "transformer.h.53.ln_attn.bias": "model-00028-of-00041.safetensors",
399
+ "transformer.h.53.ln_attn.weight": "model-00028-of-00041.safetensors",
400
+ "transformer.h.53.ln_mlp.bias": "model-00028-of-00041.safetensors",
401
+ "transformer.h.53.ln_mlp.weight": "model-00028-of-00041.safetensors",
402
+ "transformer.h.53.mlp.dense_4h_to_h.weight": "model-00028-of-00041.safetensors",
403
+ "transformer.h.53.mlp.dense_h_to_4h.weight": "model-00027-of-00041.safetensors",
404
+ "transformer.h.53.self_attention.dense.weight": "model-00027-of-00041.safetensors",
405
+ "transformer.h.53.self_attention.query_key_value.weight": "model-00027-of-00041.safetensors",
406
+ "transformer.h.54.ln_attn.bias": "model-00028-of-00041.safetensors",
407
+ "transformer.h.54.ln_attn.weight": "model-00028-of-00041.safetensors",
408
+ "transformer.h.54.ln_mlp.bias": "model-00028-of-00041.safetensors",
409
+ "transformer.h.54.ln_mlp.weight": "model-00028-of-00041.safetensors",
410
+ "transformer.h.54.mlp.dense_4h_to_h.weight": "model-00028-of-00041.safetensors",
411
+ "transformer.h.54.mlp.dense_h_to_4h.weight": "model-00028-of-00041.safetensors",
412
+ "transformer.h.54.self_attention.dense.weight": "model-00028-of-00041.safetensors",
413
+ "transformer.h.54.self_attention.query_key_value.weight": "model-00028-of-00041.safetensors",
414
+ "transformer.h.55.ln_attn.bias": "model-00029-of-00041.safetensors",
415
+ "transformer.h.55.ln_attn.weight": "model-00029-of-00041.safetensors",
416
+ "transformer.h.55.ln_mlp.bias": "model-00029-of-00041.safetensors",
417
+ "transformer.h.55.ln_mlp.weight": "model-00029-of-00041.safetensors",
418
+ "transformer.h.55.mlp.dense_4h_to_h.weight": "model-00029-of-00041.safetensors",
419
+ "transformer.h.55.mlp.dense_h_to_4h.weight": "model-00028-of-00041.safetensors",
420
+ "transformer.h.55.self_attention.dense.weight": "model-00028-of-00041.safetensors",
421
+ "transformer.h.55.self_attention.query_key_value.weight": "model-00028-of-00041.safetensors",
422
+ "transformer.h.56.ln_attn.bias": "model-00029-of-00041.safetensors",
423
+ "transformer.h.56.ln_attn.weight": "model-00029-of-00041.safetensors",
424
+ "transformer.h.56.ln_mlp.bias": "model-00029-of-00041.safetensors",
425
+ "transformer.h.56.ln_mlp.weight": "model-00029-of-00041.safetensors",
426
+ "transformer.h.56.mlp.dense_4h_to_h.weight": "model-00029-of-00041.safetensors",
427
+ "transformer.h.56.mlp.dense_h_to_4h.weight": "model-00029-of-00041.safetensors",
428
+ "transformer.h.56.self_attention.dense.weight": "model-00029-of-00041.safetensors",
429
+ "transformer.h.56.self_attention.query_key_value.weight": "model-00029-of-00041.safetensors",
430
+ "transformer.h.57.ln_attn.bias": "model-00030-of-00041.safetensors",
431
+ "transformer.h.57.ln_attn.weight": "model-00030-of-00041.safetensors",
432
+ "transformer.h.57.ln_mlp.bias": "model-00030-of-00041.safetensors",
433
+ "transformer.h.57.ln_mlp.weight": "model-00030-of-00041.safetensors",
434
+ "transformer.h.57.mlp.dense_4h_to_h.weight": "model-00030-of-00041.safetensors",
435
+ "transformer.h.57.mlp.dense_h_to_4h.weight": "model-00029-of-00041.safetensors",
436
+ "transformer.h.57.self_attention.dense.weight": "model-00029-of-00041.safetensors",
437
+ "transformer.h.57.self_attention.query_key_value.weight": "model-00029-of-00041.safetensors",
438
+ "transformer.h.58.ln_attn.bias": "model-00030-of-00041.safetensors",
439
+ "transformer.h.58.ln_attn.weight": "model-00030-of-00041.safetensors",
440
+ "transformer.h.58.ln_mlp.bias": "model-00030-of-00041.safetensors",
441
+ "transformer.h.58.ln_mlp.weight": "model-00030-of-00041.safetensors",
442
+ "transformer.h.58.mlp.dense_4h_to_h.weight": "model-00030-of-00041.safetensors",
443
+ "transformer.h.58.mlp.dense_h_to_4h.weight": "model-00030-of-00041.safetensors",
444
+ "transformer.h.58.self_attention.dense.weight": "model-00030-of-00041.safetensors",
445
+ "transformer.h.58.self_attention.query_key_value.weight": "model-00030-of-00041.safetensors",
446
+ "transformer.h.59.ln_attn.bias": "model-00031-of-00041.safetensors",
447
+ "transformer.h.59.ln_attn.weight": "model-00031-of-00041.safetensors",
448
+ "transformer.h.59.ln_mlp.bias": "model-00031-of-00041.safetensors",
449
+ "transformer.h.59.ln_mlp.weight": "model-00031-of-00041.safetensors",
450
+ "transformer.h.59.mlp.dense_4h_to_h.weight": "model-00031-of-00041.safetensors",
451
+ "transformer.h.59.mlp.dense_h_to_4h.weight": "model-00030-of-00041.safetensors",
452
+ "transformer.h.59.self_attention.dense.weight": "model-00030-of-00041.safetensors",
453
+ "transformer.h.59.self_attention.query_key_value.weight": "model-00030-of-00041.safetensors",
454
+ "transformer.h.6.ln_attn.bias": "model-00004-of-00041.safetensors",
455
+ "transformer.h.6.ln_attn.weight": "model-00004-of-00041.safetensors",
456
+ "transformer.h.6.ln_mlp.bias": "model-00004-of-00041.safetensors",
457
+ "transformer.h.6.ln_mlp.weight": "model-00004-of-00041.safetensors",
458
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00004-of-00041.safetensors",
459
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00004-of-00041.safetensors",
460
+ "transformer.h.6.self_attention.dense.weight": "model-00004-of-00041.safetensors",
461
+ "transformer.h.6.self_attention.query_key_value.weight": "model-00004-of-00041.safetensors",
462
+ "transformer.h.60.ln_attn.bias": "model-00031-of-00041.safetensors",
463
+ "transformer.h.60.ln_attn.weight": "model-00031-of-00041.safetensors",
464
+ "transformer.h.60.ln_mlp.bias": "model-00031-of-00041.safetensors",
465
+ "transformer.h.60.ln_mlp.weight": "model-00031-of-00041.safetensors",
466
+ "transformer.h.60.mlp.dense_4h_to_h.weight": "model-00031-of-00041.safetensors",
467
+ "transformer.h.60.mlp.dense_h_to_4h.weight": "model-00031-of-00041.safetensors",
468
+ "transformer.h.60.self_attention.dense.weight": "model-00031-of-00041.safetensors",
469
+ "transformer.h.60.self_attention.query_key_value.weight": "model-00031-of-00041.safetensors",
470
+ "transformer.h.61.ln_attn.bias": "model-00032-of-00041.safetensors",
471
+ "transformer.h.61.ln_attn.weight": "model-00032-of-00041.safetensors",
472
+ "transformer.h.61.ln_mlp.bias": "model-00032-of-00041.safetensors",
473
+ "transformer.h.61.ln_mlp.weight": "model-00032-of-00041.safetensors",
474
+ "transformer.h.61.mlp.dense_4h_to_h.weight": "model-00032-of-00041.safetensors",
475
+ "transformer.h.61.mlp.dense_h_to_4h.weight": "model-00031-of-00041.safetensors",
476
+ "transformer.h.61.self_attention.dense.weight": "model-00031-of-00041.safetensors",
477
+ "transformer.h.61.self_attention.query_key_value.weight": "model-00031-of-00041.safetensors",
478
+ "transformer.h.62.ln_attn.bias": "model-00032-of-00041.safetensors",
479
+ "transformer.h.62.ln_attn.weight": "model-00032-of-00041.safetensors",
480
+ "transformer.h.62.ln_mlp.bias": "model-00032-of-00041.safetensors",
481
+ "transformer.h.62.ln_mlp.weight": "model-00032-of-00041.safetensors",
482
+ "transformer.h.62.mlp.dense_4h_to_h.weight": "model-00032-of-00041.safetensors",
483
+ "transformer.h.62.mlp.dense_h_to_4h.weight": "model-00032-of-00041.safetensors",
484
+ "transformer.h.62.self_attention.dense.weight": "model-00032-of-00041.safetensors",
485
+ "transformer.h.62.self_attention.query_key_value.weight": "model-00032-of-00041.safetensors",
486
+ "transformer.h.63.ln_attn.bias": "model-00033-of-00041.safetensors",
487
+ "transformer.h.63.ln_attn.weight": "model-00033-of-00041.safetensors",
488
+ "transformer.h.63.ln_mlp.bias": "model-00033-of-00041.safetensors",
489
+ "transformer.h.63.ln_mlp.weight": "model-00033-of-00041.safetensors",
490
+ "transformer.h.63.mlp.dense_4h_to_h.weight": "model-00033-of-00041.safetensors",
491
+ "transformer.h.63.mlp.dense_h_to_4h.weight": "model-00032-of-00041.safetensors",
492
+ "transformer.h.63.self_attention.dense.weight": "model-00032-of-00041.safetensors",
493
+ "transformer.h.63.self_attention.query_key_value.weight": "model-00032-of-00041.safetensors",
494
+ "transformer.h.64.ln_attn.bias": "model-00033-of-00041.safetensors",
495
+ "transformer.h.64.ln_attn.weight": "model-00033-of-00041.safetensors",
496
+ "transformer.h.64.ln_mlp.bias": "model-00033-of-00041.safetensors",
497
+ "transformer.h.64.ln_mlp.weight": "model-00033-of-00041.safetensors",
498
+ "transformer.h.64.mlp.dense_4h_to_h.weight": "model-00033-of-00041.safetensors",
499
+ "transformer.h.64.mlp.dense_h_to_4h.weight": "model-00033-of-00041.safetensors",
500
+ "transformer.h.64.self_attention.dense.weight": "model-00033-of-00041.safetensors",
501
+ "transformer.h.64.self_attention.query_key_value.weight": "model-00033-of-00041.safetensors",
502
+ "transformer.h.65.ln_attn.bias": "model-00034-of-00041.safetensors",
503
+ "transformer.h.65.ln_attn.weight": "model-00034-of-00041.safetensors",
504
+ "transformer.h.65.ln_mlp.bias": "model-00034-of-00041.safetensors",
505
+ "transformer.h.65.ln_mlp.weight": "model-00034-of-00041.safetensors",
506
+ "transformer.h.65.mlp.dense_4h_to_h.weight": "model-00034-of-00041.safetensors",
507
+ "transformer.h.65.mlp.dense_h_to_4h.weight": "model-00033-of-00041.safetensors",
508
+ "transformer.h.65.self_attention.dense.weight": "model-00033-of-00041.safetensors",
509
+ "transformer.h.65.self_attention.query_key_value.weight": "model-00033-of-00041.safetensors",
510
+ "transformer.h.66.ln_attn.bias": "model-00034-of-00041.safetensors",
511
+ "transformer.h.66.ln_attn.weight": "model-00034-of-00041.safetensors",
512
+ "transformer.h.66.ln_mlp.bias": "model-00034-of-00041.safetensors",
513
+ "transformer.h.66.ln_mlp.weight": "model-00034-of-00041.safetensors",
514
+ "transformer.h.66.mlp.dense_4h_to_h.weight": "model-00034-of-00041.safetensors",
515
+ "transformer.h.66.mlp.dense_h_to_4h.weight": "model-00034-of-00041.safetensors",
516
+ "transformer.h.66.self_attention.dense.weight": "model-00034-of-00041.safetensors",
517
+ "transformer.h.66.self_attention.query_key_value.weight": "model-00034-of-00041.safetensors",
518
+ "transformer.h.67.ln_attn.bias": "model-00035-of-00041.safetensors",
519
+ "transformer.h.67.ln_attn.weight": "model-00035-of-00041.safetensors",
520
+ "transformer.h.67.ln_mlp.bias": "model-00035-of-00041.safetensors",
521
+ "transformer.h.67.ln_mlp.weight": "model-00035-of-00041.safetensors",
522
+ "transformer.h.67.mlp.dense_4h_to_h.weight": "model-00035-of-00041.safetensors",
523
+ "transformer.h.67.mlp.dense_h_to_4h.weight": "model-00034-of-00041.safetensors",
524
+ "transformer.h.67.self_attention.dense.weight": "model-00034-of-00041.safetensors",
525
+ "transformer.h.67.self_attention.query_key_value.weight": "model-00034-of-00041.safetensors",
526
+ "transformer.h.68.ln_attn.bias": "model-00035-of-00041.safetensors",
527
+ "transformer.h.68.ln_attn.weight": "model-00035-of-00041.safetensors",
528
+ "transformer.h.68.ln_mlp.bias": "model-00035-of-00041.safetensors",
529
+ "transformer.h.68.ln_mlp.weight": "model-00035-of-00041.safetensors",
530
+ "transformer.h.68.mlp.dense_4h_to_h.weight": "model-00035-of-00041.safetensors",
531
+ "transformer.h.68.mlp.dense_h_to_4h.weight": "model-00035-of-00041.safetensors",
532
+ "transformer.h.68.self_attention.dense.weight": "model-00035-of-00041.safetensors",
533
+ "transformer.h.68.self_attention.query_key_value.weight": "model-00035-of-00041.safetensors",
534
+ "transformer.h.69.ln_attn.bias": "model-00036-of-00041.safetensors",
535
+ "transformer.h.69.ln_attn.weight": "model-00036-of-00041.safetensors",
536
+ "transformer.h.69.ln_mlp.bias": "model-00036-of-00041.safetensors",
537
+ "transformer.h.69.ln_mlp.weight": "model-00036-of-00041.safetensors",
538
+ "transformer.h.69.mlp.dense_4h_to_h.weight": "model-00036-of-00041.safetensors",
539
+ "transformer.h.69.mlp.dense_h_to_4h.weight": "model-00035-of-00041.safetensors",
540
+ "transformer.h.69.self_attention.dense.weight": "model-00035-of-00041.safetensors",
541
+ "transformer.h.69.self_attention.query_key_value.weight": "model-00035-of-00041.safetensors",
542
+ "transformer.h.7.ln_attn.bias": "model-00005-of-00041.safetensors",
543
+ "transformer.h.7.ln_attn.weight": "model-00005-of-00041.safetensors",
544
+ "transformer.h.7.ln_mlp.bias": "model-00005-of-00041.safetensors",
545
+ "transformer.h.7.ln_mlp.weight": "model-00005-of-00041.safetensors",
546
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00005-of-00041.safetensors",
547
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00004-of-00041.safetensors",
548
+ "transformer.h.7.self_attention.dense.weight": "model-00004-of-00041.safetensors",
549
+ "transformer.h.7.self_attention.query_key_value.weight": "model-00004-of-00041.safetensors",
550
+ "transformer.h.70.ln_attn.bias": "model-00036-of-00041.safetensors",
551
+ "transformer.h.70.ln_attn.weight": "model-00036-of-00041.safetensors",
552
+ "transformer.h.70.ln_mlp.bias": "model-00036-of-00041.safetensors",
553
+ "transformer.h.70.ln_mlp.weight": "model-00036-of-00041.safetensors",
554
+ "transformer.h.70.mlp.dense_4h_to_h.weight": "model-00036-of-00041.safetensors",
555
+ "transformer.h.70.mlp.dense_h_to_4h.weight": "model-00036-of-00041.safetensors",
556
+ "transformer.h.70.self_attention.dense.weight": "model-00036-of-00041.safetensors",
557
+ "transformer.h.70.self_attention.query_key_value.weight": "model-00036-of-00041.safetensors",
558
+ "transformer.h.71.ln_attn.bias": "model-00037-of-00041.safetensors",
559
+ "transformer.h.71.ln_attn.weight": "model-00037-of-00041.safetensors",
560
+ "transformer.h.71.ln_mlp.bias": "model-00037-of-00041.safetensors",
561
+ "transformer.h.71.ln_mlp.weight": "model-00037-of-00041.safetensors",
562
+ "transformer.h.71.mlp.dense_4h_to_h.weight": "model-00037-of-00041.safetensors",
563
+ "transformer.h.71.mlp.dense_h_to_4h.weight": "model-00036-of-00041.safetensors",
564
+ "transformer.h.71.self_attention.dense.weight": "model-00036-of-00041.safetensors",
565
+ "transformer.h.71.self_attention.query_key_value.weight": "model-00036-of-00041.safetensors",
566
+ "transformer.h.72.ln_attn.bias": "model-00037-of-00041.safetensors",
567
+ "transformer.h.72.ln_attn.weight": "model-00037-of-00041.safetensors",
568
+ "transformer.h.72.ln_mlp.bias": "model-00037-of-00041.safetensors",
569
+ "transformer.h.72.ln_mlp.weight": "model-00037-of-00041.safetensors",
570
+ "transformer.h.72.mlp.dense_4h_to_h.weight": "model-00037-of-00041.safetensors",
571
+ "transformer.h.72.mlp.dense_h_to_4h.weight": "model-00037-of-00041.safetensors",
572
+ "transformer.h.72.self_attention.dense.weight": "model-00037-of-00041.safetensors",
573
+ "transformer.h.72.self_attention.query_key_value.weight": "model-00037-of-00041.safetensors",
574
+ "transformer.h.73.ln_attn.bias": "model-00038-of-00041.safetensors",
575
+ "transformer.h.73.ln_attn.weight": "model-00038-of-00041.safetensors",
576
+ "transformer.h.73.ln_mlp.bias": "model-00038-of-00041.safetensors",
577
+ "transformer.h.73.ln_mlp.weight": "model-00038-of-00041.safetensors",
578
+ "transformer.h.73.mlp.dense_4h_to_h.weight": "model-00038-of-00041.safetensors",
579
+ "transformer.h.73.mlp.dense_h_to_4h.weight": "model-00037-of-00041.safetensors",
580
+ "transformer.h.73.self_attention.dense.weight": "model-00037-of-00041.safetensors",
581
+ "transformer.h.73.self_attention.query_key_value.weight": "model-00037-of-00041.safetensors",
582
+ "transformer.h.74.ln_attn.bias": "model-00038-of-00041.safetensors",
583
+ "transformer.h.74.ln_attn.weight": "model-00038-of-00041.safetensors",
584
+ "transformer.h.74.ln_mlp.bias": "model-00038-of-00041.safetensors",
585
+ "transformer.h.74.ln_mlp.weight": "model-00038-of-00041.safetensors",
586
+ "transformer.h.74.mlp.dense_4h_to_h.weight": "model-00038-of-00041.safetensors",
587
+ "transformer.h.74.mlp.dense_h_to_4h.weight": "model-00038-of-00041.safetensors",
588
+ "transformer.h.74.self_attention.dense.weight": "model-00038-of-00041.safetensors",
589
+ "transformer.h.74.self_attention.query_key_value.weight": "model-00038-of-00041.safetensors",
590
+ "transformer.h.75.ln_attn.bias": "model-00039-of-00041.safetensors",
591
+ "transformer.h.75.ln_attn.weight": "model-00039-of-00041.safetensors",
592
+ "transformer.h.75.ln_mlp.bias": "model-00039-of-00041.safetensors",
593
+ "transformer.h.75.ln_mlp.weight": "model-00039-of-00041.safetensors",
594
+ "transformer.h.75.mlp.dense_4h_to_h.weight": "model-00039-of-00041.safetensors",
595
+ "transformer.h.75.mlp.dense_h_to_4h.weight": "model-00038-of-00041.safetensors",
596
+ "transformer.h.75.self_attention.dense.weight": "model-00038-of-00041.safetensors",
597
+ "transformer.h.75.self_attention.query_key_value.weight": "model-00038-of-00041.safetensors",
598
+ "transformer.h.76.ln_attn.bias": "model-00039-of-00041.safetensors",
599
+ "transformer.h.76.ln_attn.weight": "model-00039-of-00041.safetensors",
600
+ "transformer.h.76.ln_mlp.bias": "model-00039-of-00041.safetensors",
601
+ "transformer.h.76.ln_mlp.weight": "model-00039-of-00041.safetensors",
602
+ "transformer.h.76.mlp.dense_4h_to_h.weight": "model-00039-of-00041.safetensors",
603
+ "transformer.h.76.mlp.dense_h_to_4h.weight": "model-00039-of-00041.safetensors",
604
+ "transformer.h.76.self_attention.dense.weight": "model-00039-of-00041.safetensors",
605
+ "transformer.h.76.self_attention.query_key_value.weight": "model-00039-of-00041.safetensors",
606
+ "transformer.h.77.ln_attn.bias": "model-00040-of-00041.safetensors",
607
+ "transformer.h.77.ln_attn.weight": "model-00040-of-00041.safetensors",
608
+ "transformer.h.77.ln_mlp.bias": "model-00040-of-00041.safetensors",
609
+ "transformer.h.77.ln_mlp.weight": "model-00040-of-00041.safetensors",
610
+ "transformer.h.77.mlp.dense_4h_to_h.weight": "model-00040-of-00041.safetensors",
611
+ "transformer.h.77.mlp.dense_h_to_4h.weight": "model-00039-of-00041.safetensors",
612
+ "transformer.h.77.self_attention.dense.weight": "model-00039-of-00041.safetensors",
613
+ "transformer.h.77.self_attention.query_key_value.weight": "model-00039-of-00041.safetensors",
614
+ "transformer.h.78.ln_attn.bias": "model-00040-of-00041.safetensors",
615
+ "transformer.h.78.ln_attn.weight": "model-00040-of-00041.safetensors",
616
+ "transformer.h.78.ln_mlp.bias": "model-00040-of-00041.safetensors",
617
+ "transformer.h.78.ln_mlp.weight": "model-00040-of-00041.safetensors",
618
+ "transformer.h.78.mlp.dense_4h_to_h.weight": "model-00040-of-00041.safetensors",
619
+ "transformer.h.78.mlp.dense_h_to_4h.weight": "model-00040-of-00041.safetensors",
620
+ "transformer.h.78.self_attention.dense.weight": "model-00040-of-00041.safetensors",
621
+ "transformer.h.78.self_attention.query_key_value.weight": "model-00040-of-00041.safetensors",
622
+ "transformer.h.79.ln_attn.bias": "model-00041-of-00041.safetensors",
623
+ "transformer.h.79.ln_attn.weight": "model-00041-of-00041.safetensors",
624
+ "transformer.h.79.ln_mlp.bias": "model-00041-of-00041.safetensors",
625
+ "transformer.h.79.ln_mlp.weight": "model-00041-of-00041.safetensors",
626
+ "transformer.h.79.mlp.dense_4h_to_h.weight": "model-00041-of-00041.safetensors",
627
+ "transformer.h.79.mlp.dense_h_to_4h.weight": "model-00040-of-00041.safetensors",
628
+ "transformer.h.79.self_attention.dense.weight": "model-00040-of-00041.safetensors",
629
+ "transformer.h.79.self_attention.query_key_value.weight": "model-00040-of-00041.safetensors",
630
+ "transformer.h.8.ln_attn.bias": "model-00005-of-00041.safetensors",
631
+ "transformer.h.8.ln_attn.weight": "model-00005-of-00041.safetensors",
632
+ "transformer.h.8.ln_mlp.bias": "model-00005-of-00041.safetensors",
633
+ "transformer.h.8.ln_mlp.weight": "model-00005-of-00041.safetensors",
634
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00005-of-00041.safetensors",
635
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00005-of-00041.safetensors",
636
+ "transformer.h.8.self_attention.dense.weight": "model-00005-of-00041.safetensors",
637
+ "transformer.h.8.self_attention.query_key_value.weight": "model-00005-of-00041.safetensors",
638
+ "transformer.h.9.ln_attn.bias": "model-00006-of-00041.safetensors",
639
+ "transformer.h.9.ln_attn.weight": "model-00006-of-00041.safetensors",
640
+ "transformer.h.9.ln_mlp.bias": "model-00006-of-00041.safetensors",
641
+ "transformer.h.9.ln_mlp.weight": "model-00006-of-00041.safetensors",
642
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00006-of-00041.safetensors",
643
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00005-of-00041.safetensors",
644
+ "transformer.h.9.self_attention.dense.weight": "model-00005-of-00041.safetensors",
645
+ "transformer.h.9.self_attention.query_key_value.weight": "model-00005-of-00041.safetensors",
646
+ "transformer.ln_f.bias": "model-00041-of-00041.safetensors",
647
+ "transformer.ln_f.weight": "model-00041-of-00041.safetensors",
648
+ "transformer.word_embeddings.weight": "model-00001-of-00041.safetensors"
649
+ }
650
+ }