sharpbai commited on
Commit
0e80c8e
·
1 Parent(s): 80d6307

Upload LlamaForCausalLM

Browse files
Files changed (45) hide show
  1. config.json +23 -0
  2. generation_config.json +7 -0
  3. pytorch_model-00001-of-00042.bin +3 -0
  4. pytorch_model-00002-of-00042.bin +3 -0
  5. pytorch_model-00003-of-00042.bin +3 -0
  6. pytorch_model-00004-of-00042.bin +3 -0
  7. pytorch_model-00005-of-00042.bin +3 -0
  8. pytorch_model-00006-of-00042.bin +3 -0
  9. pytorch_model-00007-of-00042.bin +3 -0
  10. pytorch_model-00008-of-00042.bin +3 -0
  11. pytorch_model-00009-of-00042.bin +3 -0
  12. pytorch_model-00010-of-00042.bin +3 -0
  13. pytorch_model-00011-of-00042.bin +3 -0
  14. pytorch_model-00012-of-00042.bin +3 -0
  15. pytorch_model-00013-of-00042.bin +3 -0
  16. pytorch_model-00014-of-00042.bin +3 -0
  17. pytorch_model-00015-of-00042.bin +3 -0
  18. pytorch_model-00016-of-00042.bin +3 -0
  19. pytorch_model-00017-of-00042.bin +3 -0
  20. pytorch_model-00018-of-00042.bin +3 -0
  21. pytorch_model-00019-of-00042.bin +3 -0
  22. pytorch_model-00020-of-00042.bin +3 -0
  23. pytorch_model-00021-of-00042.bin +3 -0
  24. pytorch_model-00022-of-00042.bin +3 -0
  25. pytorch_model-00023-of-00042.bin +3 -0
  26. pytorch_model-00024-of-00042.bin +3 -0
  27. pytorch_model-00025-of-00042.bin +3 -0
  28. pytorch_model-00026-of-00042.bin +3 -0
  29. pytorch_model-00027-of-00042.bin +3 -0
  30. pytorch_model-00028-of-00042.bin +3 -0
  31. pytorch_model-00029-of-00042.bin +3 -0
  32. pytorch_model-00030-of-00042.bin +3 -0
  33. pytorch_model-00031-of-00042.bin +3 -0
  34. pytorch_model-00032-of-00042.bin +3 -0
  35. pytorch_model-00033-of-00042.bin +3 -0
  36. pytorch_model-00034-of-00042.bin +3 -0
  37. pytorch_model-00035-of-00042.bin +3 -0
  38. pytorch_model-00036-of-00042.bin +3 -0
  39. pytorch_model-00037-of-00042.bin +3 -0
  40. pytorch_model-00038-of-00042.bin +3 -0
  41. pytorch_model-00039-of-00042.bin +3 -0
  42. pytorch_model-00040-of-00042.bin +3 -0
  43. pytorch_model-00041-of-00042.bin +3 -0
  44. pytorch_model-00042-of-00042.bin +3 -0
  45. pytorch_model.bin.index.json +410 -0
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sharpbai/llama-13b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "pad_token_id": 0,
17
+ "rms_norm_eps": 1e-06,
18
+ "tie_word_embeddings": false,
19
+ "torch_dtype": "float16",
20
+ "transformers_version": "4.30.1",
21
+ "use_cache": true,
22
+ "vocab_size": 32000
23
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.30.1"
7
+ }
pytorch_model-00001-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ed476de4201911439b088d5c6bfb57ae0789858a59f45dcbc814e946051559
3
+ size 537397951
pytorch_model-00002-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060b08cef95051a860d4df5a1bf8b8acd2383464d2e80b1829424f30fdd655cb
3
+ size 634412995
pytorch_model-00003-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3389b32e4e1624d20e0902786ee6e7b70db36c227733710787065fe67e295bf
3
+ size 634412995
pytorch_model-00004-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84e4f13cdcc34b0cd7ce81b0b84e5fb33db2d7efaa60d95ac3aece822f24080
3
+ size 634412995
pytorch_model-00005-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c759dd236ba578da30ff0acfc1ee70cf73aa87cfa40eb0df3f60cfd9c47c3f
3
+ size 634412995
pytorch_model-00006-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c89208f8a688cee6b2472f1ec0f7b48042882930bb881c96791e3bb99b2dc6
3
+ size 634412995
pytorch_model-00007-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f2041804d0038d9c94bc623fb09d524abb36b53fc517836e1405797efffc0c
3
+ size 634412995
pytorch_model-00008-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0dc9f9c4220521b7b754a8fbd092993291d366024b678d4031bbc4ad4545ee4
3
+ size 634412995
pytorch_model-00009-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e960ad014360b7e631b37b43b1090dd9b6547e43c361539c44793d72ce5f899d
3
+ size 634412995
pytorch_model-00010-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d032ac7467288a5d014cf40ffc35591b59183ac5850aac93a273a12ba63f370f
3
+ size 634412995
pytorch_model-00011-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae7e946cd3a06b414494862cc53ecf7d45a78ca233d24c20bbd13c331f2831f6
3
+ size 634412995
pytorch_model-00012-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef31dd926c9c415f8fce8985f6481e41ec9f93df0407c58716dfc32df99bf0e9
3
+ size 634412995
pytorch_model-00013-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ca97bef67e3649c02e53c9e986aefeda5ba9aad4fc8720e0244b93e0091175
3
+ size 634412995
pytorch_model-00014-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:226f787eee2f71e99ace227465f3ed60222554d8ac70bfbba74ee9d140bc7e27
3
+ size 634412995
pytorch_model-00015-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392351699b422ff79b8fbc9fde0f32dadd06ded75d7af8de62ed58c045e14fdb
3
+ size 634412995
pytorch_model-00016-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb3236a3ec99748f62ffe85378c8c8b182fda2a1bb206be941e162c75863982
3
+ size 634412995
pytorch_model-00017-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246657b659fef5126dac5e16c3aae4409c292468ccdaf8e2042823fa23c6ab35
3
+ size 634412995
pytorch_model-00018-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f6fb2e42acc782eca34d1b49c888150462ea2720479cfb54cc0ea455abdceed
3
+ size 634412995
pytorch_model-00019-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463d67bb44c0b3ccb704906fba0c60e988791309e6abaacae25b67d7e95514fb
3
+ size 634412995
pytorch_model-00020-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494e86b0e75c4343c86b8e488fef7bdcff7fd9be82b6b6df4618abc77285a12e
3
+ size 634412995
pytorch_model-00021-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301e001fa44a57bd533379f969334bf08d031543bf5c509d28d9654dd7690989
3
+ size 634412995
pytorch_model-00022-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7a378c4511b4fa8ed971dcfd5574c358dae1d6542fca1fef03bf8f2d8b341f
3
+ size 634412995
pytorch_model-00023-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a005fc69f32b665cbe504f0f02d233da8c7fcb254052831c7a08e33eb0ea9604
3
+ size 634412995
pytorch_model-00024-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5170ca5858c2966e6c38d674e38faa2e99294d850fb3e2604f930a8de01ab091
3
+ size 634412995
pytorch_model-00025-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6010839b1ceb88d302a0913437fd6e4e7d456b2b57d60dac981ed4623ccbeb4c
3
+ size 634412995
pytorch_model-00026-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56fbb64cd51ab0ba19eebc2ea779c9689ea6140764411d4a96aef98bd0c4ebda
3
+ size 634412995
pytorch_model-00027-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf7f9e2849767f380c8e6efd3988a7e5c898368bfed763ec9aa0b2f856d614f
3
+ size 634412995
pytorch_model-00028-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f439e5a2fc3692a075e4b706d212ec62bcc02c18d46ff5c00c1a053066688297
3
+ size 634412995
pytorch_model-00029-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d07292bc9b9e40664c113fd0e5871e16d6f2cd6b4766aced8e93ffc30c67f28
3
+ size 634412995
pytorch_model-00030-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3371d79af348cb122f42e97dd91178b0c3a74a26f04e6a0bd161e1c1ef8ee3ce
3
+ size 634412995
pytorch_model-00031-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7edbc850a0e20c04e49e963fdb1e4279ca97dd1927c35c37d8ab9e9ffc7d4c8
3
+ size 634412995
pytorch_model-00032-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8ab169429293b54befdc7645529b377951df45db52382c2527304c074ffae9
3
+ size 634412995
pytorch_model-00033-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dfbec3e17b8627393140860a1c44b4d78bb9e29d4c985322c994d6bb8b4768f
3
+ size 634412995
pytorch_model-00034-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4339e78b99179387901182e8fca889dcfe9f573e221a2d21708989a071adbe56
3
+ size 634412995
pytorch_model-00035-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52105ef4561e559b054f2a1df4ecc118d3927da6f41f39df832962ba29a0e5b2
3
+ size 634412995
pytorch_model-00036-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f2d566d8400b2f16b89bf4b605827f9bc2d98a0b6f03bf0fd9bc27149703ec
3
+ size 634412995
pytorch_model-00037-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530f8a1a2bd61dd1c6e805f347c138d5aa75b5787a0e91decfeb700fef10d2e8
3
+ size 634412995
pytorch_model-00038-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb31bd6937ee5c8e0a0172954b35f7ce2ace47703a6bc4ef61d8527a707da4c
3
+ size 634412995
pytorch_model-00039-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff35382995ce7cb654912ce25dfbc36e1fd01f57dfd0a417940172a66a50e0cc
3
+ size 634412995
pytorch_model-00040-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f02357838b086491f2b2202ae764d6ee2d8e96403a95227aa92f33e8e39548
3
+ size 634412995
pytorch_model-00041-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeca5cce1f105b9ac32614bc5b4020e66c257d910df1ecfaa9ffd18e99e34f6a
3
+ size 752386495
pytorch_model-00042-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8a98cefb947b9bdf9a87682636b2996e326140e0b26970d6fc2d49a6148c27
3
+ size 327680938
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,410 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26031738880
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00042-of-00042.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00042.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00042.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00042.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00042.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00042.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00042.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00042.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00042.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00042.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00042.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00042.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00042.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00042.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00042.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00042.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00042.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00042.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00042.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00042.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00042.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00042.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00042.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00012-of-00042.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00012-of-00042.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00012-of-00042.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00042.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00042.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00042.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00042.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00042.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00042.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00042.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00013-of-00042.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00013-of-00042.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00013-of-00042.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00042.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00042.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00042.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00042.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00042.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00042.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00042.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00014-of-00042.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00014-of-00042.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00014-of-00042.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00042.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00042.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00042.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00042.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00042.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00042.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00042.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00015-of-00042.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00015-of-00042.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00015-of-00042.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00042.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00042.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00042.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00042.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00042.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00042.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00042.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00016-of-00042.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00016-of-00042.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00016-of-00042.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00042.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00042.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00042.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00042.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00042.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00042.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00042.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00017-of-00042.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00017-of-00042.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00017-of-00042.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00042.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00042.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00042.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00042.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00042.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00042.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00042.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00018-of-00042.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00018-of-00042.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00018-of-00042.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00042.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00042.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00042.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00042.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00042.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00042.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00042.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00019-of-00042.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00019-of-00042.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00019-of-00042.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00042.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00042.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00042.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00042.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00042.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00042.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00042.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00020-of-00042.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00020-of-00042.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00020-of-00042.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00042.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00042.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00042.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00042.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00042.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00042.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00042.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00021-of-00042.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00021-of-00042.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00021-of-00042.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00042.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00042.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00042.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00042.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00042.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00042.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00042.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00042.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00042.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00042.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00042.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00042.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00042.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00042.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00042.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00042.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00042.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00022-of-00042.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00022-of-00042.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00022-of-00042.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00042.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00042.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00042.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00042.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00042.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00042.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00042.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00023-of-00042.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00023-of-00042.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00023-of-00042.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00042.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00042.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00042.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00042.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00042.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00042.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00042.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00024-of-00042.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00024-of-00042.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00024-of-00042.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00042.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00042.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00042.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00042.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00042.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00042.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00042.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00025-of-00042.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00025-of-00042.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00025-of-00042.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00042.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00042.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00042.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00042.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00042.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00042.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00042.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00026-of-00042.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00026-of-00042.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00026-of-00042.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00042.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00042.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00042.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00042.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00042.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00042.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00042.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00027-of-00042.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00027-of-00042.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00027-of-00042.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00042.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00042.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00042.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00042.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00042.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00042.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00042.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00028-of-00042.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00028-of-00042.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00028-of-00042.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00028-of-00042.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00042.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00042.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00042.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00042.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00042.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00042.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00029-of-00042.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00029-of-00042.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00029-of-00042.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00042.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00042.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00042.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00042.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00042.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00042.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00030-of-00042.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00030-of-00042.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00030-of-00042.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00030-of-00042.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00030-of-00042.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00042.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00042.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00042.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00042.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00042.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00031-of-00042.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00031-of-00042.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00031-of-00042.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00031-of-00042.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00031-of-00042.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00042.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00042.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00042.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00042.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00042.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00042.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00042.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00042.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00042.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00042.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00042.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00042.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00042.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00042.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00042.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00032-of-00042.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00032-of-00042.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00032-of-00042.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00032-of-00042.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00032-of-00042.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00042.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00042.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00042.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00042.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00042.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00033-of-00042.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00033-of-00042.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00033-of-00042.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00033-of-00042.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00033-of-00042.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00042.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00042.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00042.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00042.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00042.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00034-of-00042.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00034-of-00042.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00034-of-00042.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00034-of-00042.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00034-of-00042.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00033-of-00042.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00033-of-00042.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00033-of-00042.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00042.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00033-of-00042.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00035-of-00042.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00035-of-00042.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00035-of-00042.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00035-of-00042.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00035-of-00042.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00034-of-00042.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00034-of-00042.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00034-of-00042.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00042.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00034-of-00042.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00036-of-00042.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00036-of-00042.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00036-of-00042.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00036-of-00042.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00036-of-00042.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00035-of-00042.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00035-of-00042.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00035-of-00042.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00042.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00035-of-00042.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00037-of-00042.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00037-of-00042.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00037-of-00042.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00037-of-00042.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00037-of-00042.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00036-of-00042.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00036-of-00042.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00036-of-00042.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00042.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00036-of-00042.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00038-of-00042.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00038-of-00042.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00038-of-00042.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00038-of-00042.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00038-of-00042.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00037-of-00042.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00037-of-00042.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00037-of-00042.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00037-of-00042.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00037-of-00042.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00039-of-00042.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00039-of-00042.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00039-of-00042.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00039-of-00042.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00039-of-00042.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00038-of-00042.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00038-of-00042.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00038-of-00042.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00042.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00038-of-00042.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00040-of-00042.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00040-of-00042.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00040-of-00042.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00040-of-00042.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00040-of-00042.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00039-of-00042.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00039-of-00042.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00039-of-00042.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00039-of-00042.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00039-of-00042.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00041-of-00042.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00041-of-00042.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00041-of-00042.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00041-of-00042.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00041-of-00042.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00040-of-00042.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00040-of-00042.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00040-of-00042.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00040-of-00042.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00040-of-00042.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00042.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00042.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00042.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00006-of-00042.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00042.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00042.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00042.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00042.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00042.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00042.bin",
358
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00042.bin",
359
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00007-of-00042.bin",
360
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00042.bin",
361
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00007-of-00042.bin",
362
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00042.bin",
363
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00042.bin",
364
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00042.bin",
365
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00042.bin",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00042.bin",
367
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00042.bin",
368
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00042.bin",
369
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00008-of-00042.bin",
370
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00008-of-00042.bin",
371
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00008-of-00042.bin",
372
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00042.bin",
373
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00042.bin",
374
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00042.bin",
375
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00042.bin",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00042.bin",
377
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00042.bin",
378
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00042.bin",
379
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00009-of-00042.bin",
380
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00009-of-00042.bin",
381
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00009-of-00042.bin",
382
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00042.bin",
383
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00042.bin",
384
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00042.bin",
385
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00042.bin",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00042.bin",
387
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00042.bin",
388
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00042.bin",
389
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00010-of-00042.bin",
390
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00010-of-00042.bin",
391
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00010-of-00042.bin",
392
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00042.bin",
393
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00042.bin",
394
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00042.bin",
395
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00042.bin",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00042.bin",
397
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00042.bin",
398
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00042.bin",
399
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00011-of-00042.bin",
400
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00011-of-00042.bin",
401
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00011-of-00042.bin",
402
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00042.bin",
403
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00042.bin",
404
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00042.bin",
405
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00042.bin",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00042.bin",
407
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00042.bin",
408
+ "model.norm.weight": "pytorch_model-00041-of-00042.bin"
409
+ }
410
+ }