beomi commited on
Commit
bc9686e
1 Parent(s): b15336f

Add >250B trained ckpt(ko+en)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. config.json +1 -1
  2. generation_config.json +1 -1
  3. pytorch_model-00001-of-00003.bin → model-00001-of-00028.safetensors +2 -2
  4. pytorch_model-00002-of-00003.bin → model-00002-of-00028.safetensors +2 -2
  5. pytorch_model-00003-of-00003.bin → model-00003-of-00028.safetensors +2 -2
  6. model-00004-of-00028.safetensors +3 -0
  7. model-00005-of-00028.safetensors +3 -0
  8. model-00006-of-00028.safetensors +3 -0
  9. model-00007-of-00028.safetensors +3 -0
  10. model-00008-of-00028.safetensors +3 -0
  11. model-00009-of-00028.safetensors +3 -0
  12. model-00010-of-00028.safetensors +3 -0
  13. model-00011-of-00028.safetensors +3 -0
  14. model-00012-of-00028.safetensors +3 -0
  15. model-00013-of-00028.safetensors +3 -0
  16. model-00014-of-00028.safetensors +3 -0
  17. model-00015-of-00028.safetensors +3 -0
  18. model-00016-of-00028.safetensors +3 -0
  19. model-00017-of-00028.safetensors +3 -0
  20. model-00018-of-00028.safetensors +3 -0
  21. model-00019-of-00028.safetensors +3 -0
  22. model-00020-of-00028.safetensors +3 -0
  23. model-00021-of-00028.safetensors +3 -0
  24. model-00022-of-00028.safetensors +3 -0
  25. model-00023-of-00028.safetensors +3 -0
  26. model-00024-of-00028.safetensors +3 -0
  27. model-00025-of-00028.safetensors +3 -0
  28. model-00026-of-00028.safetensors +3 -0
  29. model-00027-of-00028.safetensors +3 -0
  30. model-00028-of-00028.safetensors +3 -0
  31. model.safetensors.index.json +410 -0
  32. pytorch_model-00001-of-00028.bin +3 -0
  33. pytorch_model-00002-of-00028.bin +3 -0
  34. pytorch_model-00003-of-00028.bin +3 -0
  35. pytorch_model-00004-of-00028.bin +3 -0
  36. pytorch_model-00005-of-00028.bin +3 -0
  37. pytorch_model-00006-of-00028.bin +3 -0
  38. pytorch_model-00007-of-00028.bin +3 -0
  39. pytorch_model-00008-of-00028.bin +3 -0
  40. pytorch_model-00009-of-00028.bin +3 -0
  41. pytorch_model-00010-of-00028.bin +3 -0
  42. pytorch_model-00011-of-00028.bin +3 -0
  43. pytorch_model-00012-of-00028.bin +3 -0
  44. pytorch_model-00013-of-00028.bin +3 -0
  45. pytorch_model-00014-of-00028.bin +3 -0
  46. pytorch_model-00015-of-00028.bin +3 -0
  47. pytorch_model-00016-of-00028.bin +3 -0
  48. pytorch_model-00017-of-00028.bin +3 -0
  49. pytorch_model-00018-of-00028.bin +3 -0
  50. pytorch_model-00019-of-00028.bin +3 -0
config.json CHANGED
@@ -16,7 +16,7 @@
16
  "rms_norm_eps": 1e-06,
17
  "tie_word_embeddings": false,
18
  "torch_dtype": "float16",
19
- "transformers_version": "4.30.0",
20
  "use_cache": true,
21
  "vocab_size": 52000
22
  }
 
16
  "rms_norm_eps": 1e-06,
17
  "tie_word_embeddings": false,
18
  "torch_dtype": "float16",
19
+ "transformers_version": "4.28.0.dev0",
20
  "use_cache": true,
21
  "vocab_size": 52000
22
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 0,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.30.0"
7
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 0,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.28.0.dev0"
7
  }
pytorch_model-00001-of-00003.bin → model-00001-of-00028.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7785c4057c9b9b0041ea58509467c24be6ef2b54a3c1f241fdea0bc11a43411
3
- size 9907090895
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29912762ced57be1cd94520a508b4e558ddc89428229911f4bfdf3d3fd9d84a3
3
+ size 883754024
pytorch_model-00002-of-00003.bin → model-00002-of-00028.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a659a75e3d8eb1af839aced8892f4c9c9ddd6b8d756361c29eb57436b7f5d9b4
3
- size 9867486361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a1e380fbdd663b9103f64d93f2822e831d9f65699d52ecdff31cf0bb5d8377
3
+ size 969975720
pytorch_model-00003-of-00003.bin → model-00003-of-00028.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3142854fca7fab0d756369c9e055dedc91ec1fa0b4112659448d596fd21e62c0
3
- size 6666899881
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b950cc4292324494598074e277f95c73d81a5220d696fb00751d9ab123fb63e
3
+ size 933255328
model-00004-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ba7f03dd01cef8c6e2057624c93b6c6f61f86686402a02c83a1e60d4c205fa
3
+ size 969975720
model-00005-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a430a3f6b68ca4756e40bf93ee10137a7b233bb8bead624b748d762bd8249a84
3
+ size 933255328
model-00006-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18eae0463af72bd26b948311363edf733b4a28732c10e564d24c0f3f8d6c1a3a
3
+ size 969975720
model-00007-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bd326f182800d954ea04ec7ce2c0a7a24767eb9e008b4eb855de7eed9e6e8f9
3
+ size 933255328
model-00008-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d97007d2ad725fe9ef865b7c8374909625d82667058a8a264af8dd3d3a3f34
3
+ size 969975728
model-00009-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e7f8e7672e4b6f49eefaf77fec35df719ec4a5802a8c1d4276b330681d7290
3
+ size 933255344
model-00010-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3689c4534e6c3523743a6e57af4502074c189eed6623472dc14952fa6aad37db
3
+ size 969975736
model-00011-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f8f2fd4658c684b07f70d56088208ee4deff34f1183e03d4e42b92a0b7e554
3
+ size 933255344
model-00012-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee95a5e98b7b4c6e66b03db737b7fd85da1cfc1a00bbd538e39d11c8db934f6
3
+ size 969975736
model-00013-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9996ed42ea245dbab2e0ef086f11d18ebdff9b412e433f1d7bba0368bb759269
3
+ size 933255344
model-00014-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321022996d2a18e0763c042f60c199b047d989cde2dcd67d0d2fbb68df9856fc
3
+ size 969975736
model-00015-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649781dcd3c63e1879e7d9c35b1a87b05c4c1b6997fab224c2cac281e0e242a0
3
+ size 933255344
model-00016-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:184dcabf1f2cc50583cdbc66b4b81b241ae62deeff4e5e5b7e078e1719867c9a
3
+ size 969975736
model-00017-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988b2b18c0c0afa608bc5a3e139326482e786218572351fd456281b7afd25b1c
3
+ size 933255344
model-00018-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704f5490455b66b1b44202d0a0f7066c8fe56b9d9f80740ca8ec2da6b160a55a
3
+ size 969975736
model-00019-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d85ea989eb7e2ce7f5d373b7248fb7e55c6780e44d9a3cd04a322de9038a186
3
+ size 933255344
model-00020-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b0861f77ad745ec6ebcc3834ef862dd7de526591ef9463c7c1df6c3922fe7a
3
+ size 969975736
model-00021-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab0f6556424ca995db043de2372562c969ca055b9d44967c931cf469494093d
3
+ size 933255344
model-00022-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e42f4978cf3f113b229dee2c38ac80b4073e05008b0b1e4c0239ec59f53549
3
+ size 969975736
model-00023-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301fe277844c725cfc04664d4354895e8c004e60874409e5d50b85e1923c3db0
3
+ size 933255344
model-00024-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac89771a8b714312c481788a2b8a04099d8e44d95829dd1d71eb95c3be54eca
3
+ size 969975736
model-00025-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0973973b16a934b88ae75777963619cad81224d35b05fecbd19f90f543d8f65
3
+ size 933255344
model-00026-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d085d4c8415c98efe47d57ddf8b9ea892f9a70f6e06ecf7f1ad3d34050cb4e3b
3
+ size 969975736
model-00027-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb81571ccfbc70d8c99f3330bc9295956b450f750467c7889ceef286959e775
3
+ size 933255344
model-00028-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af40a9d84101d8ce0452e46ae05ab6b5d9cea00e0f6e3d2711b89d241ac824e
3
+ size 815626904
model.safetensors.index.json ADDED
@@ -0,0 +1,410 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26441338880
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00028-of-00028.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00028.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00028.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00028.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00002-of-00028.safetensors",
27
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
28
+ "model.layers.10.input_layernorm.weight": "model-00008-of-00028.safetensors",
29
+ "model.layers.10.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
30
+ "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
31
+ "model.layers.10.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
32
+ "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
33
+ "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
34
+ "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
35
+ "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00008-of-00028.safetensors",
37
+ "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
38
+ "model.layers.11.input_layernorm.weight": "model-00009-of-00028.safetensors",
39
+ "model.layers.11.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
40
+ "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
41
+ "model.layers.11.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
42
+ "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
43
+ "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
44
+ "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
45
+ "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00009-of-00028.safetensors",
47
+ "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
48
+ "model.layers.12.input_layernorm.weight": "model-00010-of-00028.safetensors",
49
+ "model.layers.12.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
50
+ "model.layers.12.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
51
+ "model.layers.12.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
52
+ "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
53
+ "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
54
+ "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
55
+ "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00009-of-00028.safetensors",
57
+ "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
58
+ "model.layers.13.input_layernorm.weight": "model-00010-of-00028.safetensors",
59
+ "model.layers.13.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
60
+ "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
61
+ "model.layers.13.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
62
+ "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
63
+ "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
64
+ "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
65
+ "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00010-of-00028.safetensors",
67
+ "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
68
+ "model.layers.14.input_layernorm.weight": "model-00011-of-00028.safetensors",
69
+ "model.layers.14.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
70
+ "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
71
+ "model.layers.14.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
72
+ "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
73
+ "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
74
+ "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
75
+ "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00011-of-00028.safetensors",
77
+ "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
78
+ "model.layers.15.input_layernorm.weight": "model-00012-of-00028.safetensors",
79
+ "model.layers.15.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
80
+ "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
81
+ "model.layers.15.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
82
+ "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
83
+ "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
84
+ "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
85
+ "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00011-of-00028.safetensors",
87
+ "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
88
+ "model.layers.16.input_layernorm.weight": "model-00012-of-00028.safetensors",
89
+ "model.layers.16.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
90
+ "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
91
+ "model.layers.16.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
92
+ "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
93
+ "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
94
+ "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
95
+ "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00012-of-00028.safetensors",
97
+ "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
98
+ "model.layers.17.input_layernorm.weight": "model-00013-of-00028.safetensors",
99
+ "model.layers.17.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
100
+ "model.layers.17.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
101
+ "model.layers.17.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
102
+ "model.layers.17.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
103
+ "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
104
+ "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
105
+ "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00013-of-00028.safetensors",
107
+ "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
108
+ "model.layers.18.input_layernorm.weight": "model-00014-of-00028.safetensors",
109
+ "model.layers.18.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
110
+ "model.layers.18.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
111
+ "model.layers.18.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
112
+ "model.layers.18.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
113
+ "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
114
+ "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
115
+ "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00013-of-00028.safetensors",
117
+ "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
118
+ "model.layers.19.input_layernorm.weight": "model-00014-of-00028.safetensors",
119
+ "model.layers.19.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
120
+ "model.layers.19.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
121
+ "model.layers.19.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
122
+ "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
123
+ "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
124
+ "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
125
+ "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00014-of-00028.safetensors",
127
+ "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
128
+ "model.layers.2.input_layernorm.weight": "model-00003-of-00028.safetensors",
129
+ "model.layers.2.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
130
+ "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
131
+ "model.layers.2.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
132
+ "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
133
+ "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
134
+ "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
135
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00003-of-00028.safetensors",
137
+ "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
138
+ "model.layers.20.input_layernorm.weight": "model-00015-of-00028.safetensors",
139
+ "model.layers.20.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
140
+ "model.layers.20.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
141
+ "model.layers.20.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
142
+ "model.layers.20.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
143
+ "model.layers.20.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
144
+ "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
145
+ "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00015-of-00028.safetensors",
147
+ "model.layers.20.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
148
+ "model.layers.21.input_layernorm.weight": "model-00016-of-00028.safetensors",
149
+ "model.layers.21.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
150
+ "model.layers.21.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
151
+ "model.layers.21.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
152
+ "model.layers.21.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
153
+ "model.layers.21.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
154
+ "model.layers.21.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
155
+ "model.layers.21.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00015-of-00028.safetensors",
157
+ "model.layers.21.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
158
+ "model.layers.22.input_layernorm.weight": "model-00016-of-00028.safetensors",
159
+ "model.layers.22.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
160
+ "model.layers.22.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
161
+ "model.layers.22.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
162
+ "model.layers.22.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
163
+ "model.layers.22.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
164
+ "model.layers.22.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
165
+ "model.layers.22.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00016-of-00028.safetensors",
167
+ "model.layers.22.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
168
+ "model.layers.23.input_layernorm.weight": "model-00017-of-00028.safetensors",
169
+ "model.layers.23.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
170
+ "model.layers.23.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
171
+ "model.layers.23.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
172
+ "model.layers.23.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
173
+ "model.layers.23.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
174
+ "model.layers.23.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
175
+ "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00017-of-00028.safetensors",
177
+ "model.layers.23.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
178
+ "model.layers.24.input_layernorm.weight": "model-00018-of-00028.safetensors",
179
+ "model.layers.24.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
180
+ "model.layers.24.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
181
+ "model.layers.24.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
182
+ "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
183
+ "model.layers.24.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
184
+ "model.layers.24.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
185
+ "model.layers.24.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00017-of-00028.safetensors",
187
+ "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
188
+ "model.layers.25.input_layernorm.weight": "model-00018-of-00028.safetensors",
189
+ "model.layers.25.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
190
+ "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
191
+ "model.layers.25.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
192
+ "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
193
+ "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
194
+ "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
195
+ "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00018-of-00028.safetensors",
197
+ "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
198
+ "model.layers.26.input_layernorm.weight": "model-00019-of-00028.safetensors",
199
+ "model.layers.26.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
200
+ "model.layers.26.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
201
+ "model.layers.26.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
202
+ "model.layers.26.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
203
+ "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
204
+ "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
205
+ "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00019-of-00028.safetensors",
207
+ "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
208
+ "model.layers.27.input_layernorm.weight": "model-00020-of-00028.safetensors",
209
+ "model.layers.27.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
210
+ "model.layers.27.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
211
+ "model.layers.27.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
212
+ "model.layers.27.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
213
+ "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
214
+ "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
215
+ "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00019-of-00028.safetensors",
217
+ "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
218
+ "model.layers.28.input_layernorm.weight": "model-00020-of-00028.safetensors",
219
+ "model.layers.28.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
220
+ "model.layers.28.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
221
+ "model.layers.28.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
222
+ "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
223
+ "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
224
+ "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
225
+ "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00020-of-00028.safetensors",
227
+ "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
228
+ "model.layers.29.input_layernorm.weight": "model-00021-of-00028.safetensors",
229
+ "model.layers.29.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
230
+ "model.layers.29.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
231
+ "model.layers.29.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
232
+ "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
233
+ "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
234
+ "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
235
+ "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00021-of-00028.safetensors",
237
+ "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
238
+ "model.layers.3.input_layernorm.weight": "model-00004-of-00028.safetensors",
239
+ "model.layers.3.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
240
+ "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
241
+ "model.layers.3.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
242
+ "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
243
+ "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
244
+ "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
245
+ "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00003-of-00028.safetensors",
247
+ "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
248
+ "model.layers.30.input_layernorm.weight": "model-00022-of-00028.safetensors",
249
+ "model.layers.30.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
250
+ "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
251
+ "model.layers.30.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
252
+ "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
253
+ "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
254
+ "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
255
+ "model.layers.30.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00021-of-00028.safetensors",
257
+ "model.layers.30.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
258
+ "model.layers.31.input_layernorm.weight": "model-00022-of-00028.safetensors",
259
+ "model.layers.31.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
260
+ "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
261
+ "model.layers.31.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
262
+ "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
263
+ "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
264
+ "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
265
+ "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00022-of-00028.safetensors",
267
+ "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
268
+ "model.layers.32.input_layernorm.weight": "model-00023-of-00028.safetensors",
269
+ "model.layers.32.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
270
+ "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
271
+ "model.layers.32.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
272
+ "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
273
+ "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
274
+ "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
275
+ "model.layers.32.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00023-of-00028.safetensors",
277
+ "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
278
+ "model.layers.33.input_layernorm.weight": "model-00024-of-00028.safetensors",
279
+ "model.layers.33.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
280
+ "model.layers.33.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
281
+ "model.layers.33.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
282
+ "model.layers.33.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
283
+ "model.layers.33.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
284
+ "model.layers.33.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
285
+ "model.layers.33.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00023-of-00028.safetensors",
287
+ "model.layers.33.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
288
+ "model.layers.34.input_layernorm.weight": "model-00024-of-00028.safetensors",
289
+ "model.layers.34.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
290
+ "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
291
+ "model.layers.34.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
292
+ "model.layers.34.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
293
+ "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
294
+ "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
295
+ "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00024-of-00028.safetensors",
297
+ "model.layers.34.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
298
+ "model.layers.35.input_layernorm.weight": "model-00025-of-00028.safetensors",
299
+ "model.layers.35.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
300
+ "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
301
+ "model.layers.35.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
302
+ "model.layers.35.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
303
+ "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
304
+ "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
305
+ "model.layers.35.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00025-of-00028.safetensors",
307
+ "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
308
+ "model.layers.36.input_layernorm.weight": "model-00026-of-00028.safetensors",
309
+ "model.layers.36.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
310
+ "model.layers.36.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
311
+ "model.layers.36.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
312
+ "model.layers.36.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
313
+ "model.layers.36.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
314
+ "model.layers.36.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
315
+ "model.layers.36.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00025-of-00028.safetensors",
317
+ "model.layers.36.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
318
+ "model.layers.37.input_layernorm.weight": "model-00026-of-00028.safetensors",
319
+ "model.layers.37.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
320
+ "model.layers.37.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
321
+ "model.layers.37.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
322
+ "model.layers.37.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
323
+ "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
324
+ "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
325
+ "model.layers.37.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00026-of-00028.safetensors",
327
+ "model.layers.37.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
328
+ "model.layers.38.input_layernorm.weight": "model-00027-of-00028.safetensors",
329
+ "model.layers.38.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
330
+ "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
331
+ "model.layers.38.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
332
+ "model.layers.38.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
333
+ "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
334
+ "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
335
+ "model.layers.38.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00027-of-00028.safetensors",
337
+ "model.layers.38.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
338
+ "model.layers.39.input_layernorm.weight": "model-00028-of-00028.safetensors",
339
+ "model.layers.39.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
340
+ "model.layers.39.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
341
+ "model.layers.39.mlp.up_proj.weight": "model-00028-of-00028.safetensors",
342
+ "model.layers.39.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
343
+ "model.layers.39.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
344
+ "model.layers.39.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
345
+ "model.layers.39.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00027-of-00028.safetensors",
347
+ "model.layers.39.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
348
+ "model.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors",
349
+ "model.layers.4.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
350
+ "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
351
+ "model.layers.4.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
352
+ "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
353
+ "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
354
+ "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
355
+ "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00004-of-00028.safetensors",
357
+ "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
358
+ "model.layers.5.input_layernorm.weight": "model-00005-of-00028.safetensors",
359
+ "model.layers.5.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
360
+ "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
361
+ "model.layers.5.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
362
+ "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
363
+ "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
364
+ "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
365
+ "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00005-of-00028.safetensors",
367
+ "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
368
+ "model.layers.6.input_layernorm.weight": "model-00006-of-00028.safetensors",
369
+ "model.layers.6.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
370
+ "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
371
+ "model.layers.6.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
372
+ "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
373
+ "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
374
+ "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
375
+ "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00005-of-00028.safetensors",
377
+ "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
378
+ "model.layers.7.input_layernorm.weight": "model-00006-of-00028.safetensors",
379
+ "model.layers.7.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
380
+ "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
381
+ "model.layers.7.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
382
+ "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
383
+ "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
384
+ "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
385
+ "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00006-of-00028.safetensors",
387
+ "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
388
+ "model.layers.8.input_layernorm.weight": "model-00007-of-00028.safetensors",
389
+ "model.layers.8.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
390
+ "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
391
+ "model.layers.8.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
392
+ "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
393
+ "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
394
+ "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
395
+ "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00007-of-00028.safetensors",
397
+ "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
398
+ "model.layers.9.input_layernorm.weight": "model-00008-of-00028.safetensors",
399
+ "model.layers.9.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
400
+ "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
401
+ "model.layers.9.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
402
+ "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
403
+ "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
404
+ "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
405
+ "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00007-of-00028.safetensors",
407
+ "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
408
+ "model.norm.weight": "model-00028-of-00028.safetensors"
409
+ }
410
+ }
pytorch_model-00001-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f080290e479e5303e06a8a69bd4ec6835191e40022f90e7f8c5fe3a0ad3059a
3
+ size 883756048
pytorch_model-00002-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e3f8fcea4aeeca003b0b228907aa61aa8d8c912ea98f7a99d1d1337348f007
3
+ size 969979357
pytorch_model-00003-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7856dee5e481e21e6279460c912118afbf3861a58c6593379fb2c7227537dc1
3
+ size 933258973
pytorch_model-00004-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2af83e24ab7ec3642c9716cae975224e01728cc4c47fb711c2e0b223342c62
3
+ size 969979357
pytorch_model-00005-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bdb317c89a0e899152d72c2bad92a9c86d858470518d4eedddd3fba3bfcd432
3
+ size 933258973
pytorch_model-00006-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26faa44b322949cf4c4178fe081a6ed0e6a3d4f3631e90207f6e353d9089e5a0
3
+ size 969979357
pytorch_model-00007-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5db0bfb4162a58425622f134faf10ce652b8ce3d140c39c7bad664e3c4ba33d
3
+ size 933258973
pytorch_model-00008-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca421cc47467d35463bc9f24a79d4943c0a79e76fc22853f7e606019e0d3755
3
+ size 969979357
pytorch_model-00009-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb042e180e8c3e919d9229893d835c218686a5d75b94e2b38a2b4aa1fda7335e
3
+ size 933258973
pytorch_model-00010-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4074fc82c1bf6eb9bcda2b54d674c1c78b883e8dfbd53087894a1e8b3f0c2d
3
+ size 969979357
pytorch_model-00011-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eecbb52e0cc739c8e703da53c4eb7d0c6fda6a42a7857e9ddda208155c87ad01
3
+ size 933258973
pytorch_model-00012-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d87ef24cd81803688bf360749ee5e18bd89685ff93ca9e68fa0aac5557a9a7b1
3
+ size 969979357
pytorch_model-00013-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138102a2c3a30335b2b62b989f08715cb2b972724cd22aa25396849e6d3a8789
3
+ size 933258973
pytorch_model-00014-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0a556a74c60d9cb20ef26fda6f915bc7a3a0cd4465f7fa43c1b6b5f1bef127
3
+ size 969979357
pytorch_model-00015-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db7c4c907df33969791673f52e60517647388735897549f703fe13c94fc7da7
3
+ size 933258973
pytorch_model-00016-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f977ca91f477e744fb9421cb0b252c87ff7be17d76fe3e52b9fd83ce7e6705
3
+ size 969979357
pytorch_model-00017-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b06f96ca0776e21ec4fa3fcb6e791c61bbab70da108e12c3bca27be72bb8800
3
+ size 933258973
pytorch_model-00018-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a676d42cdc8268f07e3c838e59790d4657e5030ef93f60612aa991fc6e837ed8
3
+ size 969979357
pytorch_model-00019-of-00028.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac69f5e9e55dc3833aa97bb44a3c672d27f6c08cecd312cd48ccd68f162b189
3
+ size 933258973