bruhzair commited on
Commit
59c3dad
·
verified ·
1 Parent(s): ddce7ee

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 +45 -0
  3. config.json +37 -0
  4. mergekit_config.yml +16 -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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # test-model-24
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--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022 as a base.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * /workspace/magnex
22
+ * /workspace/cache/models--bruhzair--ignore-merge-17/snapshots/bd0af76a6bc4d9ae4bab5fa6b50e6545e6f3fd4f
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ models:
30
+ - model: /workspace/magnex
31
+ parameters:
32
+ select_topk: 0.16
33
+ - model: /workspace/cache/models--bruhzair--ignore-merge-17/snapshots/bd0af76a6bc4d9ae4bab5fa6b50e6545e6f3fd4f
34
+ parameters:
35
+ select_topk: 0.16
36
+ - model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022
37
+ parameters:
38
+ select_topk: 0.16
39
+ base_model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022
40
+ merge_method: sce
41
+ tokenizer:
42
+ source: base
43
+ dtype: float32
44
+ out_dtype: bfloat16
45
+ ```
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128009,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 120,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128004,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.51.3",
34
+ "unsloth_fixed": true,
35
+ "use_cache": false,
36
+ "vocab_size": 128256
37
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: /workspace/magnex
3
+ parameters:
4
+ select_topk: 0.16
5
+ - model: /workspace/cache/models--bruhzair--ignore-merge-17/snapshots/bd0af76a6bc4d9ae4bab5fa6b50e6545e6f3fd4f
6
+ parameters:
7
+ select_topk: 0.16
8
+ - model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022
9
+ parameters:
10
+ select_topk: 0.16
11
+ base_model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022
12
+ merge_method: sce
13
+ tokenizer:
14
+ source: base
15
+ dtype: float32
16
+ out_dtype: bfloat16
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b6e0c861a36424c39852f31ddb4283fa0b416796c7e6eb01aa5444fc058d2e
3
+ size 3875621032
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb4edfb89eff010457d6a6d5de421252cd834d5b040c148dd390f93cae9e28f3
3
+ size 4618012992
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e6b1b48fb03255ade586008ff6ac986406a1be5f1f2e7165067ae9ea036b74
3
+ size 4550837664
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af5d33f19b407b5728db3f3e5119d53d300bc95330979c670a02d6abd9e7c12
3
+ size 4546726216
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eabb6f05298bbecbf94a9f83df4b6fbc5aea89882f4758b75e0e45b7d0c11311
3
+ size 4664134432
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:656b5e6e950c64a9cc6ecd7b04a003f3bddb9ccdf2d003043bbdf6c82ac01233
3
+ size 4966174304
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:141fe690d88154bfbf0cea31ab64e042f9389e7318e45425a67cda5fd2f5c035
3
+ size 4899031360
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31adcfb2bf8fc5622de33e19504ce91253c88193640f6baf2882a3cf47d8614
3
+ size 4865511008
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6407102fff7b91daccfba0bfea87dddad0e32b93794b12667b60b8b5dc40935
3
+ size 4999678752
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672f998bd2dac6bfb670f9654a9f4e8d2e58b1238bbe38fe46741979cbce55e3
3
+ size 4899047848
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f0eb7efca425f3718d8e88a14eb507ec54c71674b8c9f5ea3e4f79c9d3e438
3
+ size 4915842968
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f873e53b971f9ed0158daede9c51efde5495e22733b237abe1c11f241fe98d3c
3
+ size 4815128888
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd52529712612b9ffbd31779c3f3f8606f2ed3537c69c744bbe3fd173e35ac9
3
+ size 4697721360
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf5a3e2eab0d31807f5d65dfa10e0c9673e8fff9e3555df10ff719abf696836
3
+ size 4664184616
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:688dafaa11ec608a0b4769a42f774584b1903c96c1e69506561d78dc5f23fe78
3
+ size 4781541232
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd327d1f6e0db72951b3019d97e07c12686f2ed393aa5af73f20adc3c322e23
3
+ size 4546759880
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445dc4f798a1e8863cb792cd483cb2d1942efa442d5950bbdc3b609e89597fef
3
+ size 4848733760
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eace80618b3ea03afd3ba60048878751eaa034d1638f0bc2e988c650227ede30
3
+ size 4798335048
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2baeb46c5e237cce6ce97ffb39bbf0108f027f7241d9c8073aef673ae68f3a0c
3
+ size 4647390072
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ed9f09c218e1edecfcd0dc734e4a7f07dd3d0a681b12afd738eacd334d865d
3
+ size 4982951616
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06cc18971059ce85479bc62423c143e1bcb8ac0defee5fe76de372ab739c64c
3
+ size 4546709688
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be9e049dcc44df421b6f9649e707038d35820759cff5adcb18828b9a9199ee0
3
+ size 4949363936
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14ed2b23b4d8ee765a43a0f130ba994fc39c765afccad1bbdcad6cfafc6cd90
3
+ size 4664183920
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea97d521a753810fb3830d5ac1a9ddc1ac79eadfd32031e67584e3dea6ebb7d
3
+ size 4563454024
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b4462c05774af9317c78946ef9895a9042a9058e2ead339bbe1f258b71a41e
3
+ size 4932619592
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5acaf0a5cdf2fd85907f515ccc673870875401130cc94a1d71b2f17537eed3c2
3
+ size 4798385264
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a9d2a3a126a20d523f9b360c0c6e5e7387a7746ded65d0badb494da5a6b26f
3
+ size 4899047840
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cf41a4fce7bf2f7311a9f4f4a76f32446305059154faa4ec03a70c566a8a9c9
3
+ size 4915826464
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156611589021dd0531c082c53e720d1d7168d873e420afd098403334e5a7080e
3
+ size 4949346728
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d4e12eba570682d501a7cecdc725d434d2fec9ec45078431c4d7ae6698b1389
3
+ size 4798401152
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4199d8719e9b17ff5e007b42e98470df38da96248da3ac3d79b464b0ba9412
3
+ size 4731293848
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9346a439badd270bbbcb902205974106cb7658b07578e0989f1b7529d3024355
3
+ size 4647323376
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85d6b0db574b429ff26f75b754519aa3c0a196f93e4bfc009c81a9a47825996
3
+ size 4932635488
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b7b355aa23217010072c5ed1a96f885294704be41a2f85ca43e01ecca75c1f
3
+ size 4563521344
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad9b777079d2a0e0c14b92167da5c4546717de13e014784b1f151462bc17933
3
+ size 4999628528
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcbf1aa401f57d944efc6765f1f542936558b661043de09ab71afa4ee9ad72c6
3
+ size 4815195576
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3cf472e3c31378ea70b1fff094f41afe9de420d96a821bdbfa82d5c200926d
3
+ size 4680977760
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9641dc0ef7b0f945a156a391ce4fcdeec9a8f1d70d0b0acde11752f060447c85
3
+ size 4647290376
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2d106af61a8136175ba01c5fd936065bfc100a63acc461cad9ecc5015ba454
3
+ size 4966190760
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdb201cea295248c53f6f6b3f3c4858b0ce9492faea59f189d03d2a5634a5a8a
3
+ size 4546759912
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75798f0f0957cd1c5593a7cb476491af7779a039cea8c64a17b585024b110a36
3
+ size 4982834688
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ce0fe04035e05abb3b014bbf6a647a8b1b9613531fc78539c0c16a546857f19
3
+ size 4781691832
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2a88a579e929fa77f2e9b954b1371b133a91b9889fd3735e86f483b12be2fe
3
+ size 4865476672
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd3a3e8ac662788da37418a740f41ea2dd6ea9fad728ff58aad96917aa52c49
3
+ size 4798368736
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", "lm_head.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.down_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.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.101.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.mlp.gate_proj.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.102.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.embed_tokens.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.104.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.105.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00005-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.106.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.102.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.gate_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.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.107.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.108.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.110.self_attn.q_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.116.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.116.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.115.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.up_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.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.119.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.117.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.12.self_attn.o_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.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.15.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.17.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.o_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.20.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.down_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.23.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.up_proj.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-00014-of-00044.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.21.mlp.up_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.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.23.mlp.down_proj.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.26.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.28.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.24.self_attn.v_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.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.25.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.29.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.mlp.down_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.o_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.30.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.3.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.mlp.up_proj.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.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.mlp.down_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.30.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.o_proj.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.31.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.34.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.32.self_attn.k_proj.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.30.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.33.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.31.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.31.self_attn.v_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.36.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.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.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.33.self_attn.o_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.37.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.38.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.34.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.37.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.39.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.up_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.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.mlp.down_proj.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-00025-of-00044.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.48.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.46.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.48.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.50.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.input_layernorm.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.54.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.53.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.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.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.q_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.60.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.63.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.62.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.60.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.64.mlp.gate_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.63.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.61.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.63.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.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.63.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00031-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.67.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.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.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.69.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.68.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.71.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.72.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.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.72.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.down_proj.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-00034-of-00044.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.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.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.76.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.78.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.75.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.79.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.up_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.79.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.80.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.81.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.83.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.84.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.86.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.82.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.o_proj.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.84.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.90.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.93.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.9.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.gate_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.98.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.99.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.norm.weight": "model-00044-of-00044.safetensors", "model.layers.97.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.97.self_attn.v_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.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.q_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.98.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.o_proj.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
+ }