TheDrummer commited on
Commit
dc1c192
·
verified ·
1 Parent(s): 1dbe7e2

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. .ipynb_checkpoints/config-checkpoint.json +42 -0
  3. config.json +42 -0
  4. model-00001-of-00044.safetensors +3 -0
  5. model-00002-of-00044.safetensors +3 -0
  6. model-00003-of-00044.safetensors +3 -0
  7. model-00004-of-00044.safetensors +3 -0
  8. model-00005-of-00044.safetensors +3 -0
  9. model-00006-of-00044.safetensors +3 -0
  10. model-00007-of-00044.safetensors +3 -0
  11. model-00008-of-00044.safetensors +3 -0
  12. model-00009-of-00044.safetensors +3 -0
  13. model-00010-of-00044.safetensors +3 -0
  14. model-00011-of-00044.safetensors +3 -0
  15. model-00012-of-00044.safetensors +3 -0
  16. model-00013-of-00044.safetensors +3 -0
  17. model-00014-of-00044.safetensors +3 -0
  18. model-00015-of-00044.safetensors +3 -0
  19. model-00016-of-00044.safetensors +3 -0
  20. model-00017-of-00044.safetensors +3 -0
  21. model-00018-of-00044.safetensors +3 -0
  22. model-00019-of-00044.safetensors +3 -0
  23. model-00020-of-00044.safetensors +3 -0
  24. model-00021-of-00044.safetensors +3 -0
  25. model-00022-of-00044.safetensors +3 -0
  26. model-00023-of-00044.safetensors +3 -0
  27. model-00024-of-00044.safetensors +3 -0
  28. model-00025-of-00044.safetensors +3 -0
  29. model-00026-of-00044.safetensors +3 -0
  30. model-00027-of-00044.safetensors +3 -0
  31. model-00028-of-00044.safetensors +3 -0
  32. model-00029-of-00044.safetensors +3 -0
  33. model-00030-of-00044.safetensors +3 -0
  34. model-00031-of-00044.safetensors +3 -0
  35. model-00032-of-00044.safetensors +3 -0
  36. model-00033-of-00044.safetensors +3 -0
  37. model-00034-of-00044.safetensors +3 -0
  38. model-00035-of-00044.safetensors +3 -0
  39. model-00036-of-00044.safetensors +3 -0
  40. model-00037-of-00044.safetensors +3 -0
  41. model-00038-of-00044.safetensors +3 -0
  42. model-00039-of-00044.safetensors +3 -0
  43. model-00040-of-00044.safetensors +3 -0
  44. model-00041-of-00044.safetensors +3 -0
  45. model-00042-of-00044.safetensors +3 -0
  46. model-00043-of-00044.safetensors +3 -0
  47. model-00044-of-00044.safetensors +3 -0
  48. model.safetensors.index.json +1 -0
  49. special_tokens_map.json +23 -0
  50. tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Llama-3.3-70B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 28672,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 64,
23
+ "num_hidden_layers": 120,
24
+ "num_key_value_heads": 8,
25
+ "pad_token_id": 128004,
26
+ "pretraining_tp": 1,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": {
29
+ "factor": 8.0,
30
+ "high_freq_factor": 4.0,
31
+ "low_freq_factor": 1.0,
32
+ "original_max_position_embeddings": 8192,
33
+ "rope_type": "llama3"
34
+ },
35
+ "rope_theta": 500000.0,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.48.0",
39
+ "unsloth_fixed": true,
40
+ "use_cache": true,
41
+ "vocab_size": 128256
42
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Llama-3.3-70B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 28672,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 64,
23
+ "num_hidden_layers": 120,
24
+ "num_key_value_heads": 8,
25
+ "pad_token_id": 128004,
26
+ "pretraining_tp": 1,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": {
29
+ "factor": 8.0,
30
+ "high_freq_factor": 4.0,
31
+ "low_freq_factor": 1.0,
32
+ "original_max_position_embeddings": 8192,
33
+ "rope_type": "llama3"
34
+ },
35
+ "rope_theta": 500000.0,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.48.0",
39
+ "unsloth_fixed": true,
40
+ "use_cache": true,
41
+ "vocab_size": 128256
42
+ }
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb5a0177f660b3f18caddb2f70db303369c3503ef6d6e7dc9c3c0a23bd7eb4f4
3
+ size 4672471504
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201d329eed0f51dd199d3d3a499da099a2578e8a0287bd62cc641bc973c50360
3
+ size 4664167400
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ba5a76bae995d29f92d958a87f50043b66b40c1e9eb531742d795bebc97e7c
3
+ size 4982917904
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944ecfc749edee88f6832c975a3f7365bde10f2275a3cbfa8ba155e35f835dfb
3
+ size 4999711736
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c21b0c162d0fc5ecd810149eb4029f39f13100e4322e2e7801e522bc271a51a
3
+ size 4647373576
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faaca74ca4d0ee932ff4709a81ae73fc0bd049f2f708c0732cea0742022ef6f5
3
+ size 4664167400
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62253d3b26f323666fbb1c831cff59b11623df3fcc03137c62d2689d3d4650ad
3
+ size 4664167416
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4796292283b861549730c2f07ebf7f0b97657d98c6c5b00a0d4ecebb7603c3
3
+ size 4982917904
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6ae1cbe03b947ac70e2c5897bfaa809dc4d594c97b298817f38a79d8d2b99f
3
+ size 4999711736
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8759561a83d9ab1884620cc2aa40e4e82361f7302e2feee4a0a704731705a2b1
3
+ size 4647373568
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b93eaefae98edb9f66cc5992ed95195a2c4f5f739ac3cedb5c740c930be7491
3
+ size 4664167408
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d90ac61804de65f6b0aedd754b1f5846a07e751437b171663c854416b06c306
3
+ size 4664167416
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b8a17b375a8b1f109aa3a0d62480ded8f4e5309037c7532a8d817cbff0cef98
3
+ size 4982917904
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154a415e53987639519e78a786adc6093eba5cd7637e48d4a34b7c66e111e2b8
3
+ size 4999711728
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54d8d69d286e4bccf006e03fb098f6ded2d36d116b6148ea699f7b3c70b47b4
3
+ size 4647373576
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6022ca098f53488bd1e05acd8a779fbde8d69e91a5c3c249cba59c9dbc4400e2
3
+ size 4999727520
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6b5f320d46b0d83254cd9cb6aa8caf39da813e518cd78bf7f8c8680723e68a
3
+ size 4664117880
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5de0ab3e0e6cff2f7c208b3e5d77faf6d10e9abb54e40b78a103d9e5a44a4676
3
+ size 4664167408
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a99ccd36935d696903af38eef522b06c3dd214b251c86f4808c7c62fb0d38d
3
+ size 4664167416
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f46f6c3abf19b622b8565a324980fbfecbff7b9b0171b52a5177d499e3a87d8
3
+ size 4664167408
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27eb181922f1cd174192c88fe439dc129e0014843111cdc35aa4827513fb699c
3
+ size 4966190760
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:941662a14b550cde75d128447395f761d1b038dac079a09e0ec9450acfc3ebb5
3
+ size 4664167416
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4b65557a416df6156e637ff4cd72ead14840330df9b881f026c0b9c307707b
3
+ size 4949330248
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888e959d3e61e8af6176efa197ef772d318637477858a146c768f28016982d68
3
+ size 4999711728
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0310483cdbf1c67c0597d28d7f68de337c660e3536e6d33d50aa31f5ab559bc6
3
+ size 4999711728
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0149cc420d71d26476d7089a2f6d272277c2424c72cf04e50a317e7e6069b9c
3
+ size 4999711728
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a32541ec5ea26ee748ecc0f35975995dc0dbb018b08d0263a31114c82af8e8c
3
+ size 4999711728
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65eccb6f0bc499df6044a9c014bf68694f0ceb7e46e1851d2eee6c5d9138a3c
3
+ size 4999711720
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08f14595b736cca13623685fe49e03d0d03e31405d3d48366918d6caccdc346
3
+ size 4613785888
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3db841a4127dd0122ea653fba36be6ad6de778482013663593a2057661f5e54
3
+ size 4664167408
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b92966262634eae5f510565698bdd2d44ffede7bfc8a2a861b3f0e42f747fdcf
3
+ size 4664167416
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4cbc394f62994e047aa381c0b6029ed0e0f63491bc4bb49b1bb653ad78a79c4
3
+ size 4966190760
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d42c1d97a61a877d0aba13a60acbe2839b71eea08a6104ad635181faa71fe4
3
+ size 4664167416
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7ac0b0e238f7bbac7e60550fc78a5c013e7b087bc1798348fcfcba40383a0a
3
+ size 4664167416
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f75d48b12b224f934f2772bd6a7a8be8200b313e87ee6f750e27af287ef8ba1
3
+ size 4949330248
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efaeb6208c65050505b278f3470ee3f6e0e7bd71adfd2604717a72039d5ec49a
3
+ size 4999711744
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4a38dbd16f06dc0c98db18816ffbf443eb8fde3671bda694e91520e16cb1a3
3
+ size 4999711752
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f462c5c297a1da289e0c71e75168ef9c741e4ab693bd9d68319cad5195ff607a
3
+ size 4815146112
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d9050f5852f4b0d7f82da8cd46b782514352bdb298eaded8766ac4a4816787
3
+ size 4664167432
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403179676ef4c972b7c424c4dcfecbbf8885a614cced7f988d049a0e51bc1ce0
3
+ size 4664167424
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf065a0a9807e49f19414c324f5b7bd976b9745e46a87caa9c400291dde1c91
3
+ size 4982917928
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae6e2eae278ec79592c406f3463ba21142740991ed37a14e03b275330d3870e
3
+ size 4999711760
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d102f4e12698dd079200db1b3392a53ff10854322f88ea73a7dc53a67d5577
3
+ size 4647373592
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285fc834b7ef28c47041281538fcd432e1d35f14bfe1ff0445a4dd3b8824e887
3
+ size 2483095360
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.5.2", "total_size": 209559764992}, "weight_map": {"lm_head.weight": "model-00001-of-00044.safetensors", "model.embed_tokens.weight": "model-00001-of-00044.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.50.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.53.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.52.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.51.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.56.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.55.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.54.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.58.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.57.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.62.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.61.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.60.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.65.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.64.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.63.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.67.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.70.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.73.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.72.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.76.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.75.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.79.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.78.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.83.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.82.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.81.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.86.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.85.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.84.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.89.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.88.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.87.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.92.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.91.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.90.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.95.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.94.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.93.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.97.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.96.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.100.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.99.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.103.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.102.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.norm.weight": "model-00044-of-00044.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920