Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- README.md +42 -0
- config.json +39 -0
- mergekit_config.yml +13 -0
- model-00001-of-00044.safetensors +3 -0
- model-00002-of-00044.safetensors +3 -0
- model-00003-of-00044.safetensors +3 -0
- model-00004-of-00044.safetensors +3 -0
- model-00005-of-00044.safetensors +3 -0
- model-00006-of-00044.safetensors +3 -0
- model-00007-of-00044.safetensors +3 -0
- model-00008-of-00044.safetensors +3 -0
- model-00009-of-00044.safetensors +3 -0
- model-00010-of-00044.safetensors +3 -0
- model-00011-of-00044.safetensors +3 -0
- model-00012-of-00044.safetensors +3 -0
- model-00013-of-00044.safetensors +3 -0
- model-00014-of-00044.safetensors +3 -0
- model-00015-of-00044.safetensors +3 -0
- model-00016-of-00044.safetensors +3 -0
- model-00017-of-00044.safetensors +3 -0
- model-00018-of-00044.safetensors +3 -0
- model-00019-of-00044.safetensors +3 -0
- model-00020-of-00044.safetensors +3 -0
- model-00021-of-00044.safetensors +3 -0
- model-00022-of-00044.safetensors +3 -0
- model-00023-of-00044.safetensors +3 -0
- model-00024-of-00044.safetensors +3 -0
- model-00025-of-00044.safetensors +3 -0
- model-00026-of-00044.safetensors +3 -0
- model-00027-of-00044.safetensors +3 -0
- model-00028-of-00044.safetensors +3 -0
- model-00029-of-00044.safetensors +3 -0
- model-00030-of-00044.safetensors +3 -0
- model-00031-of-00044.safetensors +3 -0
- model-00032-of-00044.safetensors +3 -0
- model-00033-of-00044.safetensors +3 -0
- model-00034-of-00044.safetensors +3 -0
- model-00035-of-00044.safetensors +3 -0
- model-00036-of-00044.safetensors +3 -0
- model-00037-of-00044.safetensors +3 -0
- model-00038-of-00044.safetensors +3 -0
- model-00039-of-00044.safetensors +3 -0
- model-00040-of-00044.safetensors +3 -0
- model-00041-of-00044.safetensors +3 -0
- model-00042-of-00044.safetensors +3 -0
- model-00043-of-00044.safetensors +3 -0
- model-00044-of-00044.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +16 -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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
|
8 |
+
---
|
9 |
+
# test-model-13
|
10 |
+
|
11 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
+
|
13 |
+
## Merge Details
|
14 |
+
### Merge Method
|
15 |
+
|
16 |
+
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/test-model-12 as a base.
|
17 |
+
|
18 |
+
### Models Merged
|
19 |
+
|
20 |
+
The following models were included in the merge:
|
21 |
+
* /workspace/electra2
|
22 |
+
* /workspace/perm2
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
models:
|
30 |
+
- model: /workspace/perm2
|
31 |
+
parameters:
|
32 |
+
select_topk: 0.3
|
33 |
+
- model: /workspace/electra2
|
34 |
+
parameters:
|
35 |
+
select_topk: 0.3
|
36 |
+
base_model: /workspace/test-model-12
|
37 |
+
merge_method: sce
|
38 |
+
tokenizer:
|
39 |
+
source: base
|
40 |
+
dtype: float32
|
41 |
+
out_dtype: bfloat16
|
42 |
+
```
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 128000,
|
8 |
+
"eos_token_id": [
|
9 |
+
128001,
|
10 |
+
128008,
|
11 |
+
128009
|
12 |
+
],
|
13 |
+
"head_dim": 128,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 8192,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 28672,
|
18 |
+
"max_position_embeddings": 131072,
|
19 |
+
"mlp_bias": false,
|
20 |
+
"model_type": "llama",
|
21 |
+
"num_attention_heads": 64,
|
22 |
+
"num_hidden_layers": 120,
|
23 |
+
"num_key_value_heads": 8,
|
24 |
+
"pretraining_tp": 1,
|
25 |
+
"rms_norm_eps": 1e-05,
|
26 |
+
"rope_scaling": {
|
27 |
+
"factor": 8.0,
|
28 |
+
"high_freq_factor": 4.0,
|
29 |
+
"low_freq_factor": 1.0,
|
30 |
+
"original_max_position_embeddings": 8192,
|
31 |
+
"rope_type": "llama3"
|
32 |
+
},
|
33 |
+
"rope_theta": 500000.0,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "bfloat16",
|
36 |
+
"transformers_version": "4.51.3",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 128256
|
39 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: /workspace/perm2
|
3 |
+
parameters:
|
4 |
+
select_topk: 0.3
|
5 |
+
- model: /workspace/electra2
|
6 |
+
parameters:
|
7 |
+
select_topk: 0.3
|
8 |
+
base_model: /workspace/test-model-12
|
9 |
+
merge_method: sce
|
10 |
+
tokenizer:
|
11 |
+
source: base
|
12 |
+
dtype: float32
|
13 |
+
out_dtype: bfloat16
|
model-00001-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6590da4e8704c9b327c18a8b9c59e1cdd8226eeb2c8eaf81dfbffd91f46ae31
|
3 |
+
size 4815162576
|
model-00002-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d6ed1ecc4c532c99f3790b5039b6c7bc4ad6cd242850313062d12327f6a86aa
|
3 |
+
size 4903192304
|
model-00003-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62bd10f43d014a01d6fa72b55e2918b098494afb520a813f3c9f4cd0ffbdbb95
|
3 |
+
size 4752213632
|
model-00004-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ae74659f7b225f59a530992720872de1fc8b1ef840761b117c557f59bf988b6
|
3 |
+
size 4982901408
|
model-00005-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44b95e749c843a8aff0238a78df0ef3aa4ed7a2bf0624f109c66b4ba08c47977
|
3 |
+
size 4680977784
|
model-00006-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ab4a62eb18a21ffbd5527bccffe147ca1b00c745a59478f26ac1692126fe8a
|
3 |
+
size 4664150920
|
model-00007-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a53b110e4f91a036f4f3b20793ac7085ef82b92965bb1734b13958c17c84cc89
|
3 |
+
size 4848716576
|
model-00008-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf86f048912ec99b2aa3a0d7687c86e811f20166f6520222bcaf4a8b6865d059
|
3 |
+
size 4932552920
|
model-00009-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7083ad1b85887d8340c88bcefb2675ba028cfbed1185ebd79b3ac12fee0893c
|
3 |
+
size 4781641664
|
model-00010-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1299ef1392b0e84055fd596168314134257f3e56a2a170bc3775dc341200387
|
3 |
+
size 4714465712
|
model-00011-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98529b7d089da4572537be0887b2ae68ee8fa44716fa20760612edf585863760
|
3 |
+
size 4848716560
|
model-00012-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f8b3919d6a55f37efab96b480912fc5c81d52dfe69c11af1c9743cd2b5018fc
|
3 |
+
size 4831956432
|
model-00013-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18e6fb81bbf476ea3942368413f08af5fc61cf1f49da005adb0bed3931e9baa2
|
3 |
+
size 4630579736
|
model-00014-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74f1ab22cc468f486fb06f32f1c872b8486a26826ae60537cefc44e06e971968
|
3 |
+
size 4982950896
|
model-00015-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:512db0371b65a20a8be48fb4e4abfdc0fcdf2b9fe4d27f411f36da53a45ad4d3
|
3 |
+
size 4647357072
|
model-00016-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2f15f118c4735244bd251b7a755cfbef325a65de61ba469ad8306b6301691a3
|
3 |
+
size 4882287720
|
model-00017-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:888e00817df881629d9d3726573c71dfae8a1ce5f0f8e826637b355e99b1b6a4
|
3 |
+
size 4915809256
|
model-00018-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3456a697d0bb14e4e5468b4801bf1ecc11f2cce90cd3421480344ffc11cb7cc0
|
3 |
+
size 4999711728
|
model-00019-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:793241140b25398af924ddecd9b83b0d8861851dfd4c8b5f641ba6fed55c49a4
|
3 |
+
size 4546743408
|
model-00020-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:435728d3f9eb55e4379faa32e9ef4f2e40375a7b7a0bed14c1357de4786cb67d
|
3 |
+
size 4781574928
|
model-00021-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf2eacdf974ec9b23a1c197fd71e3e4e0e03907bef20fe91393f373449637652
|
3 |
+
size 4848716536
|
model-00022-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d009dbb50b999888eaaf42704864aa39b724ccf5aabb8060328dc02995b93d2
|
3 |
+
size 4999728232
|
model-00023-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72e27725786f005a93f8e3c8bf0af40e6c7a431ca92a9da88358e4c497f792a7
|
3 |
+
size 4932553608
|
model-00024-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cf4bcc94fa1936432767455460b05cfed0068e6efa32e19828f04ad609986fd
|
3 |
+
size 4865543376
|
model-00025-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c77b3a309e676c20f55a46febeaeba2af98137cfd4d09a0519eb4021aa4cc506
|
3 |
+
size 4865427768
|
model-00026-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af6f566ade41051935cfcf9ce6b44a53c26c06f799efad98af4d6f8f7cc1429d
|
3 |
+
size 4932636216
|
model-00027-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80a7358ac011b317c0c8746b16e85139e15ae29e6651cd8894e81d2296df2575
|
3 |
+
size 4613785912
|
model-00028-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c01952b3bf612bc1793eb83e4f406389778c310bf565decde91257c7f246fc86
|
3 |
+
size 4546743392
|
model-00029-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e0de00b869092369dbf264f15dc8d8d28d315d7ce4e3e1ff842d1925b13d9e9
|
3 |
+
size 4982950888
|
model-00030-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b031a93910db3e1ab257a6dc9071b41ab8198e177b9abf1e94f57f2552ddf51
|
3 |
+
size 4982884912
|
model-00031-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93d696afe910326beeae1985de3a875f627b4ce9fe5a3fa248b5b3c1c16c05c2
|
3 |
+
size 4966223768
|
model-00032-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9987a7fff87ede71faece8c51f37939f6b150ff72286d32d8a30cb7b9186cab
|
3 |
+
size 4630563240
|
model-00033-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebcf7f586319eaf89e97af15856707df5a7212176ade5284522d8bd0a7466d87
|
3 |
+
size 4848716552
|
model-00034-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb52be4189c791c2cdc2301edfcac1b78dae1ed0d48aae3e284e72b7ebe23a1c
|
3 |
+
size 4781574928
|
model-00035-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:449ea33c1218df47cbaa6a2abf1af4b02c1d1268101446c862c5c51828b7c6ea
|
3 |
+
size 4664183904
|
model-00036-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ea900d22964f6b659542dad6dfe75a4a42561bd732e7a9f2271b42d95d6ebcf
|
3 |
+
size 4882287704
|
model-00037-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c28aa9ee487afc47bdef5fa0d5a7a54132a37ff1ed3cdfad07cffc9ab9cb0920
|
3 |
+
size 4999678744
|
model-00038-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2451f3b60e3944a99f0f483cb7cca0c8f621353fd7e2ef39551e3ea0a96dc9c1
|
3 |
+
size 4815179088
|
model-00039-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:958a32f562f36e9aa84158a53172229134f4d0b57478905d3e47326e9131591a
|
3 |
+
size 4613802416
|
model-00040-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cab2a6a5aad6658924228bc22c0ce2b97367ba5b294b79ecb0d574bc8ec72d8
|
3 |
+
size 4882287712
|
model-00041-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb5b30caf5b3e78c3bed38b1feb8446ac5a111174b33bd8eca8dcaa2633e232e
|
3 |
+
size 4781558424
|
model-00042-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0537e030e2b6e30ecd5784b2bb03649ebbfc7288b7526f6d37679e006ecc74ee
|
3 |
+
size 4982967392
|
model-00043-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b19533d00c7ac5caa7492a46d5eb325d1d125700550f638cf09bd00966ac8235
|
3 |
+
size 4680944736
|
model-00044-of-00044.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdef3637f67f25ec0654d799292a9fd46e4e3be108540bcd40207fe39885e878
|
3 |
+
size 2315289872
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"model.layers.0.post_attention_layernorm.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.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00044.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "lm_head.weight": "model-00002-of-00044.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.102.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.103.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.104.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.embed_tokens.weight": "model-00003-of-00044.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.100.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.104.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.105.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.q_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.106.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.109.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.111.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.112.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.113.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.mlp.down_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.112.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.114.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.11.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.115.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.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.116.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.117.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.12.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.14.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.119.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.input_layernorm.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.18.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.o_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.20.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.15.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.gate_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.24.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.25.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.20.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.27.mlp.gate_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.27.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.mlp.down_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.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.30.input_layernorm.weight": "model-00016-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.30.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.33.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.34.input_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.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.3.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.36.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.42.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.40.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.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.35.self_attn.o_proj.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-00021-of-00044.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.43.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.39.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.44.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.44.self_attn.q_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-00023-of-00044.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.47.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.49.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.self_attn.o_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.49.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.5.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.51.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.50.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.52.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.53.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.48.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.55.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.58.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.up_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.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.60.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.6.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.61.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.62.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.63.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.57.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.64.input_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.58.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.64.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.59.mlp.gate_proj.weight": "model-00030-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.66.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.65.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.68.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.69.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.7.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.70.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.71.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.72.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.66.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.73.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.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.78.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.77.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.8.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.80.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.81.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.75.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.83.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.85.input_layernorm.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.83.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.87.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.86.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.88.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.89.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.84.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.90.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.92.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.96.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.95.input_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.93.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.97.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.98.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.99.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.93.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.norm.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00044-of-00044.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|