bruhzair commited on
Commit
f7308ad
·
verified ·
1 Parent(s): 3943cb2

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 +53 -0
  3. config.json +37 -0
  4. mergekit_config.yml +20 -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 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # test-model-1
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 [Model Stock](https://arxiv.org/abs/2403.19522) 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/cache/models--bruhzair--ignore-merge-6/snapshots/87658005d40b593ba3e87e92e5fb3f28321266a1
22
+ * /workspace/cache/models--bruhzair--ignore-merge-1/snapshots/0994ed36502b7c1942553cae165a5813acfc7f4b
23
+ * /workspace/cache/models--bruhzair--ignore-merge-15/snapshots/e60ee5422f827ab08ac0f591cf18fb7f43f629e8
24
+ * /workspace/cache/models--bruhzair--ignore-merge-2/snapshots/e60c43daa0fc7893e7a909d2bae952cffa3831a3
25
+ * /workspace/fallen2
26
+ * /workspace/cache/models--bruhzair--ignore-merge-8/snapshots/253c403660e94c867c277d8408e8cb518ab8bf1b
27
+
28
+ ### Configuration
29
+
30
+ The following YAML configuration was used to produce this model:
31
+
32
+ ```yaml
33
+ base_model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022
34
+ merge_method: model_stock
35
+ modules:
36
+ default:
37
+ slices:
38
+ - sources:
39
+ - layer_range: [0, 120]
40
+ model: /workspace/cache/models--bruhzair--ignore-merge-6/snapshots/87658005d40b593ba3e87e92e5fb3f28321266a1
41
+ - layer_range: [0, 120]
42
+ model: /workspace/cache/models--bruhzair--ignore-merge-8/snapshots/253c403660e94c867c277d8408e8cb518ab8bf1b
43
+ - layer_range: [0, 120]
44
+ model: /workspace/cache/models--bruhzair--ignore-merge-1/snapshots/0994ed36502b7c1942553cae165a5813acfc7f4b
45
+ - layer_range: [0, 120]
46
+ model: /workspace/cache/models--bruhzair--ignore-merge-2/snapshots/e60c43daa0fc7893e7a909d2bae952cffa3831a3
47
+ - layer_range: [0, 120]
48
+ model: /workspace/fallen2
49
+ - layer_range: [0, 120]
50
+ model: /workspace/cache/models--bruhzair--ignore-merge-15/snapshots/e60ee5422f827ab08ac0f591cf18fb7f43f629e8
51
+ - layer_range: [0, 120]
52
+ model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022
53
+ ```
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022
2
+ merge_method: model_stock
3
+ modules:
4
+ default:
5
+ slices:
6
+ - sources:
7
+ - layer_range: [0, 120]
8
+ model: /workspace/cache/models--bruhzair--ignore-merge-6/snapshots/87658005d40b593ba3e87e92e5fb3f28321266a1
9
+ - layer_range: [0, 120]
10
+ model: /workspace/cache/models--bruhzair--ignore-merge-8/snapshots/253c403660e94c867c277d8408e8cb518ab8bf1b
11
+ - layer_range: [0, 120]
12
+ model: /workspace/cache/models--bruhzair--ignore-merge-1/snapshots/0994ed36502b7c1942553cae165a5813acfc7f4b
13
+ - layer_range: [0, 120]
14
+ model: /workspace/cache/models--bruhzair--ignore-merge-2/snapshots/e60c43daa0fc7893e7a909d2bae952cffa3831a3
15
+ - layer_range: [0, 120]
16
+ model: /workspace/fallen2
17
+ - layer_range: [0, 120]
18
+ model: /workspace/cache/models--bruhzair--ignore-merge-15/snapshots/e60ee5422f827ab08ac0f591cf18fb7f43f629e8
19
+ - layer_range: [0, 120]
20
+ model: /workspace/cache/models--TheDrummer--Anubis-Pro-105B-v1/snapshots/2bbf619c35ffcb8ae3fe7f7b5a62948aab0f3022
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e4bd08a02d89fb52795a6750c7e11bdfba26158393e7c1545ae23b1c61bafd
3
+ size 4672471504
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5083b876b46dc3ed2d5c2a4912453140be08e2c37b89394919aaf949c120c4bf
3
+ size 4664167400
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9494d043ef429fe5ade2d14ba50040a3f23dee87ea1208cbd3c4dd74e467afb
3
+ size 4982917928
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd2a1c08519d51484f0f1e602720fd5839fae40fe454da19a95a78b5f620b18
3
+ size 4999711760
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64447b90bc1b41e8a9148bdeea5a244a010f7387c4b2f99ecedd2d86606569bc
3
+ size 4647373600
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a374a2d51a210be37cfe7ac21661d35d3fbd7564d2bac1e7d663fc55d97d97
3
+ size 4664167424
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd46d6e16f1de995b06294a475d8e18dc7bc396dee6dd34b0abeefde47efd84a
3
+ size 4664167440
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355e3d6543b34bc7f6bb044ca5c7fbc5c7b194ff75618b033f71499716c27bba
3
+ size 4982917928
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a279adbed16f4b3e72e1d4e74bbcc2d4782a08d12a7b4faf92d02c39d967ced8
3
+ size 4999711760
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8420713a34a30d49ad75f17dd1e86cdb89e5d3f3a7fdff503eb37f3396ece13
3
+ size 4647373592
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74509ad32b8c01da7b7ede9f175679e0ebb5c907b54eb807d8df1efa97df11e
3
+ size 4664167408
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3bf5856c0ddf1dd100b6e2a13976a210e26bcf91d08c241c506c528ad5e9cd
3
+ size 4664167416
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0024bb09b6d3631d1326d2672a69d27d70c9d4ed43d35f92a7eab84b99510dbd
3
+ size 4982917896
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d969ac28cffbaf6eaea3525c2aadf5fa584dd6c07c8c392b2ba01fde9963989
3
+ size 4999711736
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3be717535ac65fdd01b413427c21102a10af616e5f970a81ccda47c6ca8c8c4
3
+ size 4647373576
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:202ea0ae0cfe7edc5fd3520bcea3be19330a07127a9ad820bcf42a575ef86603
3
+ size 4664167408
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de30ff3db46aa5a5644756e11aedd2d2aa56e53d12426296fa8fb572f8e7464
3
+ size 4664167408
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:393dfc6440dec9f624bc739f09c363422a8801f2fb18adab17be34faf8164601
3
+ size 4982917904
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b67729f40d260d220189d86da4afd1aa3fbfc96555313d0b8f1b3e51629d99dd
3
+ size 4999711736
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53127c882c2a931775cd7456fb853c629d1196ab8a51c4af0fc2c9773bac3d93
3
+ size 4647373576
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f585e2775c932d0c42d28186085aeee9a1a29b43b6cdb206be1e85fbe6d6422e
3
+ size 4664167400
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2310e5ce5876330bfaf715a9607d25646496a8cc44630bad8e5d4f668973f79
3
+ size 4664167416
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d1477ce8564ecb04cdef5db0a0527239a136f0dc297ddb3075d7dca604df6a
3
+ size 4982917904
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83d831833c81f46672820fc559d9e7465dc602af0e404d0c12e7642974017727
3
+ size 4999711736
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34d70670196b092bffe286817c363dbe66b5d3f7f5e2b39ee7210499cbb4675
3
+ size 4647373568
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e16c431c7b6e2fda334bae715a1dfce52973d3878611f0fc22b5fd91ee553d0
3
+ size 4664167408
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef506669ada800533cb961eed7d8eadf3be41df54946d7ba9060f4c5a2a4490c
3
+ size 4664167416
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b03efcf761c229b3fff873a07396b2541d196debccd1de96346437351a3d21
3
+ size 4982917904
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35db6e36692697be330d6752350ed87d7b804fb9b68655cde696cf17d9a00f4b
3
+ size 4999711728
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdbbbe9f49d7ab509cf2f5fc466282face23408aa4174159065935ec04258652
3
+ size 4647373576
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c1aab22846b6f1c53147b4c271373d32f291776cb6c10928344a4dec8e4873
3
+ size 4664167408
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c7fa77e8faa806dd84585fed405c438720bf7d81dd2fcbdd77d7099ef49511
3
+ size 4664167416
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d250bce5b4478623656870d58bf133d5abfe3f6c75aa394674fd6b9eccb5cdd1
3
+ size 4982917896
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37cd14dd220f6deab5bed90a121bee626fdfe919b0ac8bc403ebc7716184d39d
3
+ size 4999711736
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5fde9ff33292da1950830907f80a72230e9aaf5df89e4e1db546827498d8a2
3
+ size 4647373576
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb0dfc42a8cef78839801ff04b464e8e0025d9404deab88ee720e5a9076297d
3
+ size 4664167408
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d72439fec7ab8486efbe4e94e9eb72f6fe48b67edbc0763a9258cea4689bbfc
3
+ size 4664167408
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8221f4dac36b55643f40d9e6b608e3843649792647c9ba73521b96e822092a9
3
+ size 4982917904
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b880b4cd500a15d07ddd18d1205bc3c1cfaf46ebb510d5fbdf473b47274071
3
+ size 4999711736
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23092770390bf047bd224be688eddeec02750eebef595ba533d4f92cb27c5dc1
3
+ size 4647373576
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e042e8d76865c32300c3f325b6ba24d4f0191edbe4ad6685ba4e0e690a009960
3
+ size 4664167400
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:830476bbe39a6362556ab0a14d9d8d37e28dde73fb0cac2301229db972d4586f
3
+ size 4664167416
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd80820e2e2dced629f47504e580b96ad04e78e451c7192741317a6873bfdc2
3
+ size 4982917904
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c3fcc1a9d14960dd01c32487cea6ac7e8f484e95dece2c70e375bf6b6cd500c
3
+ size 3573631384
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"lm_head.weight": "model-00001-of-00044.safetensors", "model.embed_tokens.weight": "model-00001-of-00044.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.113.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.44.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.57.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.norm.weight": "model-00044-of-00044.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }