bruhzair commited on
Commit
5578a82
·
verified ·
1 Parent(s): afd307f

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. README.md +59 -0
  3. config.json +41 -0
  4. mergekit_config.yml +29 -0
  5. model-00001-of-00044.safetensors +3 -0
  6. model-00002-of-00044.safetensors +3 -0
  7. model-00003-of-00044.safetensors +3 -0
  8. model-00004-of-00044.safetensors +3 -0
  9. model-00005-of-00044.safetensors +3 -0
  10. model-00006-of-00044.safetensors +3 -0
  11. model-00007-of-00044.safetensors +3 -0
  12. model-00008-of-00044.safetensors +3 -0
  13. model-00009-of-00044.safetensors +3 -0
  14. model-00010-of-00044.safetensors +3 -0
  15. model-00011-of-00044.safetensors +3 -0
  16. model-00012-of-00044.safetensors +3 -0
  17. model-00013-of-00044.safetensors +3 -0
  18. model-00014-of-00044.safetensors +3 -0
  19. model-00015-of-00044.safetensors +3 -0
  20. model-00016-of-00044.safetensors +3 -0
  21. model-00017-of-00044.safetensors +3 -0
  22. model-00018-of-00044.safetensors +3 -0
  23. model-00019-of-00044.safetensors +3 -0
  24. model-00020-of-00044.safetensors +3 -0
  25. model-00021-of-00044.safetensors +3 -0
  26. model-00022-of-00044.safetensors +3 -0
  27. model-00023-of-00044.safetensors +3 -0
  28. model-00024-of-00044.safetensors +3 -0
  29. model-00025-of-00044.safetensors +3 -0
  30. model-00026-of-00044.safetensors +3 -0
  31. model-00027-of-00044.safetensors +3 -0
  32. model-00028-of-00044.safetensors +3 -0
  33. model-00029-of-00044.safetensors +3 -0
  34. model-00030-of-00044.safetensors +3 -0
  35. model-00031-of-00044.safetensors +3 -0
  36. model-00032-of-00044.safetensors +3 -0
  37. model-00033-of-00044.safetensors +3 -0
  38. model-00034-of-00044.safetensors +3 -0
  39. model-00035-of-00044.safetensors +3 -0
  40. model-00036-of-00044.safetensors +3 -0
  41. model-00037-of-00044.safetensors +3 -0
  42. model-00038-of-00044.safetensors +3 -0
  43. model-00039-of-00044.safetensors +3 -0
  44. model-00040-of-00044.safetensors +3 -0
  45. model-00041-of-00044.safetensors +3 -0
  46. model-00042-of-00044.safetensors +3 -0
  47. model-00043-of-00044.safetensors +3 -0
  48. model-00044-of-00044.safetensors +3 -0
  49. model.safetensors.index.json +1 -0
  50. special_tokens_map.json +23 -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
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # base
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/cache/models--TheDrummer--L3.3-Interleaved-Upscale-105B/snapshots/dc1c192564ddf43133a71a7bdc8e6e91c69a2835 as a base.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * /workspace/magnum2
22
+ * /workspace/nemo2
23
+ * /workspace/hydro2
24
+
25
+ ### Configuration
26
+
27
+ The following YAML configuration was used to produce this model:
28
+
29
+ ```yaml
30
+ base_model: /workspace/cache/models--TheDrummer--L3.3-Interleaved-Upscale-105B/snapshots/dc1c192564ddf43133a71a7bdc8e6e91c69a2835
31
+ chat_template: llama3
32
+ dtype: float32
33
+ merge_method: sce
34
+ modules:
35
+ default:
36
+ slices:
37
+ - sources:
38
+ - layer_range: [0, 120]
39
+ model: /workspace/hydro2
40
+ parameters:
41
+ select_topk: 0.5
42
+ - layer_range: [0, 120]
43
+ model: /workspace/nemo2
44
+ parameters:
45
+ select_topk: 0.4
46
+ - layer_range: [0, 120]
47
+ model: /workspace/magnum2
48
+ parameters:
49
+ select_topk: 0.3
50
+ - layer_range: [0, 120]
51
+ model: /workspace/cache/models--TheDrummer--L3.3-Interleaved-Upscale-105B/snapshots/dc1c192564ddf43133a71a7bdc8e6e91c69a2835
52
+ parameters:
53
+ select_topk: 0.4
54
+ out_dtype: bfloat16
55
+ parameters:
56
+ int8_mask: 1.0
57
+ tokenizer:
58
+ source: base
59
+ ```
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 8192,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 28672,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 64,
22
+ "num_hidden_layers": 120,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 128004,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 8.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.51.3",
38
+ "unsloth_fixed": true,
39
+ "use_cache": true,
40
+ "vocab_size": 128256
41
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: /workspace/cache/models--TheDrummer--L3.3-Interleaved-Upscale-105B/snapshots/dc1c192564ddf43133a71a7bdc8e6e91c69a2835
2
+ chat_template: llama3
3
+ dtype: float32
4
+ merge_method: sce
5
+ modules:
6
+ default:
7
+ slices:
8
+ - sources:
9
+ - layer_range: [0, 120]
10
+ model: /workspace/hydro2
11
+ parameters:
12
+ select_topk: 0.5
13
+ - layer_range: [0, 120]
14
+ model: /workspace/nemo2
15
+ parameters:
16
+ select_topk: 0.4
17
+ - layer_range: [0, 120]
18
+ model: /workspace/magnum2
19
+ parameters:
20
+ select_topk: 0.3
21
+ - layer_range: [0, 120]
22
+ model: /workspace/cache/models--TheDrummer--L3.3-Interleaved-Upscale-105B/snapshots/dc1c192564ddf43133a71a7bdc8e6e91c69a2835
23
+ parameters:
24
+ select_topk: 0.4
25
+ out_dtype: bfloat16
26
+ parameters:
27
+ int8_mask: 1.0
28
+ tokenizer:
29
+ source: base
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9944f224a2fd4060695948bbae46e2a4b4d29d5d78c1b4b884adc132aee750a6
3
+ size 4672471504
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8ee9e77812eff4316ccec9d64f33e1c71e15faf8661b1f062642d8e1c4978d
3
+ size 4664167400
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dfaed37d8b26441196ee0ae38db3ffd44fe112cb5251d165735c9f46b682836
3
+ size 4982917928
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bf011c1fe5d483fcd4868511f082f31e96e0bf33eebf5a6b4bdcf1d843654e2
3
+ size 4999711760
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d889fca4b085494f52a44ce6d6fdf77b5ffc8d2c86695d5810a88b491cb8d9
3
+ size 4647373600
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742fd6b9c2c22833bf4c54dd514825ec006170aab2cc6d7fb9478ba9c2975dd4
3
+ size 4664167424
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95088b0c5516e465b7deb530885a43cc11bad5f3941d5fadb0a2f469774d8b7
3
+ size 4664167440
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b3089dfdeaf388daa41e9b193c85fe052b6b838f6becc25ac16e2c34faee1a
3
+ size 4982917928
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:424477fff5388dc7c9ce70b5d67c5bf61fa1f977945e28b1cf90d63d6529d277
3
+ size 4999711760
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bccb6daa5f8886ee8d7c90a2335283fb101ad00bf8715d8182dcd12930e456fe
3
+ size 4647373592
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c05374abe0c05229340c672a47872fe566056af624920b6e283fea8884cb11
3
+ size 4664167408
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91285b30c1d1d5362fb1378611a1c06496c47fde8b07071d47c80c3bd589459a
3
+ size 4664167416
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b8d120365ebb6754fcfdf05f7792eb32abe88451a14d2ee1d7e87df7ff1a6a
3
+ size 4982917896
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45dc3ddd7b2caaa0ed03346558f9a45a157b2b6f1a2e94c33c815678c8c7b2e
3
+ size 4999711736
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140e1bce9f79489755a40455488c8cbd4938ce571c4565756c06eea7ed4f16bc
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:ed4773142fbecefa075799a907dbcf0b9f2ea38d7033a5f66b1d7efd865bc0bc
3
+ size 4664167408
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa5ed830df6cd046d0452da20dc631050fdb1396e060a90259939c3ff92a538
3
+ size 4664167408
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba1fbd9a82a4ff7b34d9dfc7041c1328add779d565e86e69e0966edbf22a38e2
3
+ size 4982917904
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e921991c6bb9b59fa1a5d06aa2bcb08769dcfc8eea10187e1d1767b96ad8f1
3
+ size 4999711736
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762c3f9b9b4948770583f6385a349212197964f2e2019a4fbdbefbfd02fac30d
3
+ size 4647373576
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b010144b4b081d51bce97c7e91d9a1b7de8ea2410170bb350a090465d0c5b0c1
3
+ size 4664167400
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e92b9142a28f685ce836a6b9ee28b06a406bd498ad4ca2022263bb264dc302b
3
+ size 4664167416
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac8596a77435af8036df703712c7889a9710a5771f611e8dd127f00bc07c3e6
3
+ size 4982917904
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5197266c8ff6c32d43029216f61bb4b49a353a70cad2435540f76d10f6c74ce
3
+ size 4999711736
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4dc01db6ea90162ba81fec2ca3828de1c1c87ae45bfbe0721ea1fda49ff377
3
+ size 4647373568
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e05e81df833d14c17b49c160f66e356132a723eb47379345ddbfba93c840cd0f
3
+ size 4664167408
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72cf3bb3772c09c391a784bafc7a7616a0491f6845b0e54359b82d78eeb06c69
3
+ size 4664167416
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe4dd427dea605c7aedbab1f360b173946eed66d0bd892a9fd927317b65af27
3
+ size 4982917904
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552c8379b7d231c8664601b038d66a78ab82024c60674bb9f3c7cb01cb40e9fb
3
+ size 4999711728
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8ce2daca100fa01fb8bcd6a48446060c944dd751582ac6978a444f9a46aeeb
3
+ size 4647373576
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f3fd887d79ddfcfb4dd09238ff7b95fb2452e57a38a6d3c823dce4365c3189
3
+ size 4664167408
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:135ab29f44b19d355feb9864c59e011d312ae515a40a8d6b0897146541e44a53
3
+ size 4664167416
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4fa22781727c43bd6dc7124855e2f97c7326a454f5ffc14e48323d5a7b2734
3
+ size 4982917896
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8704bcc773368350e375e6d34b11d3447a56dfcb9f0ab78a7f601e97585b2fa9
3
+ size 4999711736
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884413e1458491d6c2d2e2aa807d3ccb974f50452913d29ce0af26608971c682
3
+ size 4647373576
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa94c6811f3bc3941d3226c8c8212fea8a381f7e57e3779cc010194d84a23e4
3
+ size 4664167408
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a02e2a02feb3c52f1b7ace6b9c9c169f4e5d6474c8c1a017e7a058fe67797d8
3
+ size 4664167408
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e46741ec013ee5425db27f2ec42cbdf83d4bb94d9fc1dd8a988f8b02c0f0f5
3
+ size 4982917904
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4426ba56fe3f804fc128ce36c6c46ccc146209aa6f2c84c7b876c057c51c9be
3
+ size 4999711736
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a3f9df4a20f0300d45fda38c61ae5f95bedf5e83922d7c0881be020a448691
3
+ size 4647373576
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:438964b9d89543aff0aca5eb52e8a3fcc2fa3b88658943debfa9c544bd5d9ed3
3
+ size 4664167400
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3918fdb2334701b51f3b6eac94fc4c729b7bc5531aa3bf6c6b5c61a594df5899
3
+ size 4664167416
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ae1d6c8898bee907e0567b3a2ae9f4ed8c3034b6d45a82c72c3b7d97f02d9f
3
+ size 4982917904
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90052da8a4f06d297a4af1289ee38d1ee088331afe5c696d04bc0acd1d3b4759
3
+ size 3573631384
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.1.2"}, "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.100.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.113.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.44.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.57.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.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
+ }