xu3kev commited on
Commit
df36411
1 Parent(s): 416d24e

Upload folder using huggingface_hub

Browse files
Files changed (34) hide show
  1. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/config.json +31 -0
  2. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/generation_config.json +6 -0
  3. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00001-of-00028.safetensors +3 -0
  4. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00002-of-00028.safetensors +3 -0
  5. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00003-of-00028.safetensors +3 -0
  6. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00004-of-00028.safetensors +3 -0
  7. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00005-of-00028.safetensors +3 -0
  8. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00006-of-00028.safetensors +3 -0
  9. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00007-of-00028.safetensors +3 -0
  10. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00008-of-00028.safetensors +3 -0
  11. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00009-of-00028.safetensors +3 -0
  12. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00010-of-00028.safetensors +3 -0
  13. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00011-of-00028.safetensors +3 -0
  14. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00012-of-00028.safetensors +3 -0
  15. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00013-of-00028.safetensors +3 -0
  16. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00014-of-00028.safetensors +3 -0
  17. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00015-of-00028.safetensors +3 -0
  18. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00016-of-00028.safetensors +3 -0
  19. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00017-of-00028.safetensors +3 -0
  20. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00018-of-00028.safetensors +3 -0
  21. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00019-of-00028.safetensors +3 -0
  22. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00020-of-00028.safetensors +3 -0
  23. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00021-of-00028.safetensors +3 -0
  24. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00022-of-00028.safetensors +3 -0
  25. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00023-of-00028.safetensors +3 -0
  26. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00024-of-00028.safetensors +3 -0
  27. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00025-of-00028.safetensors +3 -0
  28. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00026-of-00028.safetensors +3 -0
  29. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00027-of-00028.safetensors +3 -0
  30. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00028-of-00028.safetensors +3 -0
  31. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model.safetensors.index.json +568 -0
  32. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/special_tokens_map.json +23 -0
  33. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/tokenizer.json +0 -0
  34. lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/tokenizer_config.json +193 -0
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepseek-ai/deepseek-coder-33b-instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32013,
9
+ "eos_token_id": 32021,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 7168,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 19200,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 56,
17
+ "num_hidden_layers": 62,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "factor": 4.0,
23
+ "type": "linear"
24
+ },
25
+ "rope_theta": 100000,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.40.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 32256
31
+ }
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32013,
4
+ "eos_token_id": 32021,
5
+ "transformers_version": "4.40.0.dev0"
6
+ }
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00001-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c018ce50f5451f852639108b71f0c7757414d94430d575e8fbff134b774d56e6
3
+ size 4616939328
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00002-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9764ae1c6a9dc31777d16d81a16f90058309923c3c34697c72716c968e44e4c
3
+ size 4998736368
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00003-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55936f6f6c252b55f0eb16a048add609a22d6185f6ee9839c51475d3d5636a29
3
+ size 4506896776
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00004-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e5c9c77a500231a1bcb3b791d445499d5896f728609cf872936ef8a415eeb98
3
+ size 4793157784
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00005-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe6b3f8f2dd59aaf7b6ffdaf57a242ef440b34e431a72957736c8ee898437d9
3
+ size 4793157800
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00006-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e36915fb3d0ef9f02dfe9fc8688d7f204f7b426cc3c82d9cd9244be7bd7207d
3
+ size 4998736392
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00007-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:411aa077abf55288a8cad7bd018dee26b67170c9d1385926c0e473d733f9b1d7
3
+ size 4506896792
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00008-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b97cb258f771882ed00a8eeda35ac078ef58484c8e679b90acf0b166c8bb008
3
+ size 4793157808
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00009-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d62abaa4a59455b299f030cf8c74c2c4db8d84284d31e3ccec0187e01802c16
3
+ size 4793157800
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00010-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044329957ae4aa6ac79466d88e26024cc0287fda06c1cad3bed97553c50ab874
3
+ size 4998736392
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00011-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dbab1bfc07de80eb3baeb203fe03169d0bda86481050aa7eb1a2fc14693244e
3
+ size 4506896792
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00012-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3174a86e15e9a6431377bb249f1a323cae1eaf4a666f20c62d89ab4cd50d77
3
+ size 4793157808
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00013-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf250e6fd43969ab1f5b6d404abc1f188d54eb0033234a03016ec51ded02f07
3
+ size 4793157800
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00014-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c59ca809c68ce1464f644013546ba318b292acd53ef53e4789b2328046a104
3
+ size 4998736392
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00015-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0473915da67ac61cebdf9087242d1f33f1b2963082725947702855541d59a91a
3
+ size 4506896792
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00016-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0bb09c3d041079fc23e4603f3c8e871f101b3dc5b8431a4d78b402572825b8
3
+ size 4793157808
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00017-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cd54c85f93ec32a4257529568a4dce4509286c7f48edc102269374a29194a1c
3
+ size 4793157800
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00018-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78146101ecac4eee8190ba0183b012e21b2bf4539b710ea0a8ef495e5f7b555f
3
+ size 4998736392
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00019-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e98a525b9797f7cb6f43bc76b2cf22b34eec8f990b06b114419bf6e152bb5381
3
+ size 4506896792
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00020-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfab2cd1e7c19c092fb516a3f6fb265a9faf9a8ab7135dddb8f5e0b8b94fb572
3
+ size 4793157808
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00021-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae7f0800c7cb5fe5992794da04d123485aec2f3b1b025e2a871e21af484c6a9f
3
+ size 4793157800
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00022-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a70eb66daaa7466a3f54986d2d33d3ef3575553ca24d417eccc3780ab63827
3
+ size 4998736392
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00023-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0194245df9ee933e2a0bbefbe702d81f37aea66843c1dbe4f94f0280ed66ca
3
+ size 4506896792
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00024-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:550e41f109b4a445c75d82d9234d37562a296b607b2cbe1a2c0e740a7e10ac48
3
+ size 4793157808
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00025-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307a0ca0cbea8e7f39cb3f2baaf386634fd47f55577759e43705dfb748abc3b9
3
+ size 4793157800
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00026-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68dcfbb0b0e52f4772d34a7d95a735fc0f89b2f327160bdc652651feeb86cb66
3
+ size 4998736392
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00027-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0002a24335d960dca50744c0ecef40f4016a2a32e8fbded8cc5611d5c8845b9c
3
+ size 4506896792
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00028-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e5c28b8cca86c52e1ed4bb2d9042e6ea80605eba1128cd5cf40fccfc03e8fd
3
+ size 4697765672
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model.safetensors.index.json ADDED
@@ -0,0 +1,568 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 133371965440
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-00001-of-00028.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-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-00001-of-00028.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-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.v_proj.weight": "model-00001-of-00028.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00028.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00028.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00006-of-00028.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00006-of-00028.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00006-of-00028.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00007-of-00028.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00007-of-00028.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00008-of-00028.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00008-of-00028.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00009-of-00028.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00009-of-00028.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00010-of-00028.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00010-of-00028.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00010-of-00028.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00011-of-00028.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00011-of-00028.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00012-of-00028.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00012-of-00028.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00013-of-00028.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00013-of-00028.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00014-of-00028.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00014-of-00028.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00028.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00014-of-00028.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00015-of-00028.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00015-of-00028.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00016-of-00028.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00016-of-00028.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00017-of-00028.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00017-of-00028.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00018-of-00028.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00018-of-00028.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00018-of-00028.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00028.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00019-of-00028.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00019-of-00028.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00020-of-00028.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00020-of-00028.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00021-of-00028.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00021-of-00028.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00022-of-00028.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00022-of-00028.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
395
+ "model.layers.48.input_layernorm.weight": "model-00022-of-00028.safetensors",
396
+ "model.layers.48.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
397
+ "model.layers.48.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
398
+ "model.layers.48.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
399
+ "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
400
+ "model.layers.48.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
401
+ "model.layers.48.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
402
+ "model.layers.48.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
403
+ "model.layers.48.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
404
+ "model.layers.49.input_layernorm.weight": "model-00023-of-00028.safetensors",
405
+ "model.layers.49.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
406
+ "model.layers.49.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
407
+ "model.layers.49.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
408
+ "model.layers.49.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
409
+ "model.layers.49.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
410
+ "model.layers.49.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
411
+ "model.layers.49.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
412
+ "model.layers.49.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
413
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00028.safetensors",
414
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
415
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
416
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
417
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
418
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
419
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
420
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
421
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
422
+ "model.layers.50.input_layernorm.weight": "model-00023-of-00028.safetensors",
423
+ "model.layers.50.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
424
+ "model.layers.50.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
425
+ "model.layers.50.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
426
+ "model.layers.50.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
427
+ "model.layers.50.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
428
+ "model.layers.50.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
429
+ "model.layers.50.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
430
+ "model.layers.50.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
431
+ "model.layers.51.input_layernorm.weight": "model-00024-of-00028.safetensors",
432
+ "model.layers.51.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
433
+ "model.layers.51.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
434
+ "model.layers.51.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
435
+ "model.layers.51.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
436
+ "model.layers.51.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
437
+ "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
438
+ "model.layers.51.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
439
+ "model.layers.51.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
440
+ "model.layers.52.input_layernorm.weight": "model-00024-of-00028.safetensors",
441
+ "model.layers.52.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
442
+ "model.layers.52.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
443
+ "model.layers.52.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
444
+ "model.layers.52.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
445
+ "model.layers.52.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
446
+ "model.layers.52.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
447
+ "model.layers.52.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
448
+ "model.layers.52.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
449
+ "model.layers.53.input_layernorm.weight": "model-00025-of-00028.safetensors",
450
+ "model.layers.53.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
451
+ "model.layers.53.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
452
+ "model.layers.53.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
453
+ "model.layers.53.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
454
+ "model.layers.53.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
455
+ "model.layers.53.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
456
+ "model.layers.53.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
457
+ "model.layers.53.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
458
+ "model.layers.54.input_layernorm.weight": "model-00025-of-00028.safetensors",
459
+ "model.layers.54.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
460
+ "model.layers.54.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
461
+ "model.layers.54.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
462
+ "model.layers.54.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
463
+ "model.layers.54.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
464
+ "model.layers.54.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
465
+ "model.layers.54.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
466
+ "model.layers.54.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
467
+ "model.layers.55.input_layernorm.weight": "model-00026-of-00028.safetensors",
468
+ "model.layers.55.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
469
+ "model.layers.55.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
470
+ "model.layers.55.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
471
+ "model.layers.55.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
472
+ "model.layers.55.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
473
+ "model.layers.55.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
474
+ "model.layers.55.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
475
+ "model.layers.55.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
476
+ "model.layers.56.input_layernorm.weight": "model-00026-of-00028.safetensors",
477
+ "model.layers.56.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
478
+ "model.layers.56.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
479
+ "model.layers.56.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
480
+ "model.layers.56.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
481
+ "model.layers.56.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
482
+ "model.layers.56.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
483
+ "model.layers.56.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
484
+ "model.layers.56.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
485
+ "model.layers.57.input_layernorm.weight": "model-00026-of-00028.safetensors",
486
+ "model.layers.57.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
487
+ "model.layers.57.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
488
+ "model.layers.57.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
489
+ "model.layers.57.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
490
+ "model.layers.57.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
491
+ "model.layers.57.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
492
+ "model.layers.57.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
493
+ "model.layers.57.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
494
+ "model.layers.58.input_layernorm.weight": "model-00027-of-00028.safetensors",
495
+ "model.layers.58.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
496
+ "model.layers.58.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
497
+ "model.layers.58.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
498
+ "model.layers.58.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
499
+ "model.layers.58.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
500
+ "model.layers.58.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
501
+ "model.layers.58.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
502
+ "model.layers.58.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
503
+ "model.layers.59.input_layernorm.weight": "model-00027-of-00028.safetensors",
504
+ "model.layers.59.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
505
+ "model.layers.59.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
506
+ "model.layers.59.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
507
+ "model.layers.59.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
508
+ "model.layers.59.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
509
+ "model.layers.59.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
510
+ "model.layers.59.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
511
+ "model.layers.59.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
512
+ "model.layers.6.input_layernorm.weight": "model-00004-of-00028.safetensors",
513
+ "model.layers.6.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
514
+ "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
515
+ "model.layers.6.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
516
+ "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
517
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
518
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
519
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
520
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
521
+ "model.layers.60.input_layernorm.weight": "model-00028-of-00028.safetensors",
522
+ "model.layers.60.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
523
+ "model.layers.60.mlp.gate_proj.weight": "model-00028-of-00028.safetensors",
524
+ "model.layers.60.mlp.up_proj.weight": "model-00028-of-00028.safetensors",
525
+ "model.layers.60.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
526
+ "model.layers.60.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
527
+ "model.layers.60.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
528
+ "model.layers.60.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
529
+ "model.layers.60.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
530
+ "model.layers.61.input_layernorm.weight": "model-00028-of-00028.safetensors",
531
+ "model.layers.61.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
532
+ "model.layers.61.mlp.gate_proj.weight": "model-00028-of-00028.safetensors",
533
+ "model.layers.61.mlp.up_proj.weight": "model-00028-of-00028.safetensors",
534
+ "model.layers.61.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
535
+ "model.layers.61.self_attn.k_proj.weight": "model-00028-of-00028.safetensors",
536
+ "model.layers.61.self_attn.o_proj.weight": "model-00028-of-00028.safetensors",
537
+ "model.layers.61.self_attn.q_proj.weight": "model-00028-of-00028.safetensors",
538
+ "model.layers.61.self_attn.v_proj.weight": "model-00028-of-00028.safetensors",
539
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00028.safetensors",
540
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
541
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
542
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
543
+ "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
544
+ "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
545
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
546
+ "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
547
+ "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
548
+ "model.layers.8.input_layernorm.weight": "model-00005-of-00028.safetensors",
549
+ "model.layers.8.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
550
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
551
+ "model.layers.8.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
552
+ "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
553
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
554
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
555
+ "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
556
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
557
+ "model.layers.9.input_layernorm.weight": "model-00005-of-00028.safetensors",
558
+ "model.layers.9.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
559
+ "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
560
+ "model.layers.9.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
561
+ "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
562
+ "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
563
+ "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
564
+ "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
565
+ "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
566
+ "model.norm.weight": "model-00028-of-00028.safetensors"
567
+ }
568
+ }
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|EOT|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/tokenizer_config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "32000": {
6
+ "content": "õ",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "32001": {
14
+ "content": "÷",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "32002": {
22
+ "content": "Á",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32003": {
30
+ "content": "ý",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "32004": {
38
+ "content": "À",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "32005": {
46
+ "content": "ÿ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "32006": {
54
+ "content": "ø",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "32007": {
62
+ "content": "ú",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "32008": {
70
+ "content": "þ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "32009": {
78
+ "content": "ü",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "32010": {
86
+ "content": "ù",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "32011": {
94
+ "content": "ö",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "32012": {
102
+ "content": "û",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "32013": {
110
+ "content": "<|begin▁of▁sentence|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32014": {
118
+ "content": "<|end▁of▁sentence|>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32015": {
126
+ "content": "<|fim▁hole|>",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "32016": {
134
+ "content": "<|fim▁begin|>",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "32017": {
142
+ "content": "<|fim▁end|>",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "32018": {
150
+ "content": "<pad>",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "32019": {
158
+ "content": "<|User|>",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "32020": {
166
+ "content": "<|Assistant|>",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "32021": {
174
+ "content": "<|EOT|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ }
181
+ },
182
+ "bos_token": "<|begin▁of▁sentence|>",
183
+ "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<|EOT|>",
186
+ "legacy": true,
187
+ "model_max_length": 16384,
188
+ "pad_token": "<|end▁of▁sentence|>",
189
+ "sp_model_kwargs": {},
190
+ "tokenizer_class": "LlamaTokenizer",
191
+ "unk_token": null,
192
+ "use_default_system_prompt": false
193
+ }