Upload 52 files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- README.md +39 -0
- config.json +42 -0
- mergekit_config.yml +9 -0
- model-00001-of-00045.safetensors +3 -0
- model-00002-of-00045.safetensors +3 -0
- model-00003-of-00045.safetensors +3 -0
- model-00004-of-00045.safetensors +3 -0
- model-00005-of-00045.safetensors +3 -0
- model-00006-of-00045.safetensors +3 -0
- model-00007-of-00045.safetensors +3 -0
- model-00008-of-00045.safetensors +3 -0
- model-00009-of-00045.safetensors +3 -0
- model-00010-of-00045.safetensors +3 -0
- model-00011-of-00045.safetensors +3 -0
- model-00012-of-00045.safetensors +3 -0
- model-00013-of-00045.safetensors +3 -0
- model-00014-of-00045.safetensors +3 -0
- model-00015-of-00045.safetensors +3 -0
- model-00016-of-00045.safetensors +3 -0
- model-00017-of-00045.safetensors +3 -0
- model-00018-of-00045.safetensors +3 -0
- model-00019-of-00045.safetensors +3 -0
- model-00020-of-00045.safetensors +3 -0
- model-00021-of-00045.safetensors +3 -0
- model-00022-of-00045.safetensors +3 -0
- model-00023-of-00045.safetensors +3 -0
- model-00024-of-00045.safetensors +3 -0
- model-00025-of-00045.safetensors +3 -0
- model-00026-of-00045.safetensors +3 -0
- model-00027-of-00045.safetensors +3 -0
- model-00028-of-00045.safetensors +3 -0
- model-00029-of-00045.safetensors +3 -0
- model-00030-of-00045.safetensors +3 -0
- model-00031-of-00045.safetensors +3 -0
- model-00032-of-00045.safetensors +3 -0
- model-00033-of-00045.safetensors +3 -0
- model-00034-of-00045.safetensors +3 -0
- model-00035-of-00045.safetensors +3 -0
- model-00036-of-00045.safetensors +3 -0
- model-00037-of-00045.safetensors +3 -0
- model-00038-of-00045.safetensors +3 -0
- model-00039-of-00045.safetensors +3 -0
- model-00040-of-00045.safetensors +3 -0
- model-00041-of-00045.safetensors +3 -0
- model-00042-of-00045.safetensors +3 -0
- model-00043-of-00045.safetensors +3 -0
- model-00044-of-00045.safetensors +3 -0
- model-00045-of-00045.safetensors +3 -0
- model.safetensors.index.json +1 -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 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Sao10K/70B-L3.3-Cirrus-x1
|
4 |
+
library_name: transformers
|
5 |
+
tags:
|
6 |
+
- mergekit
|
7 |
+
- merge
|
8 |
+
|
9 |
+
---
|
10 |
+
# output
|
11 |
+
|
12 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
13 |
+
|
14 |
+
## Merge Details
|
15 |
+
### Merge Method
|
16 |
+
|
17 |
+
This model was merged using the Passthrough merge method.
|
18 |
+
|
19 |
+
### Models Merged
|
20 |
+
|
21 |
+
The following models were included in the merge:
|
22 |
+
* [Sao10K/70B-L3.3-Cirrus-x1](https://huggingface.co/Sao10K/70B-L3.3-Cirrus-x1)
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
merge_method: passthrough
|
30 |
+
slices:
|
31 |
+
- sources:
|
32 |
+
- model: Sao10K/70B-L3.3-Cirrus-x1
|
33 |
+
layer_range: [0, 62]
|
34 |
+
- sources:
|
35 |
+
- model: Sao10K/70B-L3.3-Cirrus-x1
|
36 |
+
layer_range: [19, 80]
|
37 |
+
dtype: bfloat16
|
38 |
+
|
39 |
+
```
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Sao10K/70B-L3.3-Cirrus-x1",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"head_dim": 128,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 8192,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 28672,
|
19 |
+
"max_position_embeddings": 131072,
|
20 |
+
"mlp_bias": false,
|
21 |
+
"model_type": "llama",
|
22 |
+
"num_attention_heads": 64,
|
23 |
+
"num_hidden_layers": 123,
|
24 |
+
"num_key_value_heads": 8,
|
25 |
+
"pad_token_id": 128004,
|
26 |
+
"pretraining_tp": 1,
|
27 |
+
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": {
|
29 |
+
"factor": 8.0,
|
30 |
+
"high_freq_factor": 4.0,
|
31 |
+
"low_freq_factor": 1.0,
|
32 |
+
"original_max_position_embeddings": 8192,
|
33 |
+
"rope_type": "llama3"
|
34 |
+
},
|
35 |
+
"rope_theta": 500000.0,
|
36 |
+
"tie_word_embeddings": false,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.49.0",
|
39 |
+
"unsloth_fixed": true,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 128256
|
42 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
merge_method: passthrough
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: Sao10K/70B-L3.3-Cirrus-x1
|
5 |
+
layer_range: [0, 62]
|
6 |
+
- sources:
|
7 |
+
- model: Sao10K/70B-L3.3-Cirrus-x1
|
8 |
+
layer_range: [19, 80]
|
9 |
+
dtype: bfloat16
|
model-00001-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e200e2efde09b0e7c9d0d321b2f9ffbd6b4d6ab474135df304c15fc30b6624dd
|
3 |
+
size 4806722352
|
model-00002-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a629fcafb9805df12ac5136b0e9da6bfe998430d6322b22338ca2ef0c8f8d02
|
3 |
+
size 4982901384
|
model-00003-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f08e58002332a57e810ff9197f1861a099abac5f81726091ca1e9412000dc1ce
|
3 |
+
size 4982917888
|
model-00004-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39a109ee7def8598ae45d44bf04650c03de2f8771c808af8fb74d41d77408230
|
3 |
+
size 4815179096
|
model-00005-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac97148a7f41753d9dd98a86942a88bb0c57d0d653cc01d286d1f837fe6bc5f2
|
3 |
+
size 4848733048
|
model-00006-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9b81b1a45f7de9059e8df6f97cfeba49a77c9b068fada2d776ca0dea21bca73
|
3 |
+
size 4697722080
|
model-00007-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53d358809c05c1a04af77405abadaf6a6fd307cd5fdaa8d2659505f619e32c0b
|
3 |
+
size 4831840224
|
model-00008-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e496a55f04b9a37ab0c1005c0b17f3529216e463a5c38ec4a24d561608a5ef8
|
3 |
+
size 4966190760
|
model-00009-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:037853a17d5796b9b54ef1ad50fa3f67d78692e28e962ae3bb279818944d7a7e
|
3 |
+
size 4882271208
|
model-00010-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dce6d78d9d7e8b5fc1eb80233e35fc6636980fcaec2a9e5227c9b511197cc40f
|
3 |
+
size 4815161888
|
model-00011-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00c22c8cd88d9b8155c0784e51b7bd233702ea6bfd580d461ec6d9431c4c9044
|
3 |
+
size 4932570112
|
model-00012-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:643bdab3c80be0b81b8fd25a5cdd3ab35cef52dbab1c164487234071c24c3294
|
3 |
+
size 4966190768
|
model-00013-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa7fa4210e1d4e255d9179d26ff2423a2f5736548035b34f57c38d7e4ef0baa4
|
3 |
+
size 4580264352
|
model-00014-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54e643e9e2a60abb49a68d68d5b95da7721317398d3691790cb714f3286b03d9
|
3 |
+
size 4831906216
|
model-00015-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d16488e05e0c933abdc94d7a2d4bc06e298348a6f5719c8ff927223210f0fe7
|
3 |
+
size 4915842264
|
model-00016-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:192dc66d708304817fc084905c12f2ab80c328303f558d38c3f931a24c79babc
|
3 |
+
size 4966157768
|
model-00017-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22aacf3b768f76cad78163f5a45d791693684d84df6ed1475b7415a610769c04
|
3 |
+
size 4899047840
|
model-00018-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce91145dbcecc8b33bdb8ece4cb359898c5e8b63b221df5c7f99921146804dd1
|
3 |
+
size 4764797608
|
model-00019-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31742623a48777e2e39ddd43ceda49461ea79061af8b111cfced1518cfc58a31
|
3 |
+
size 4966157752
|
model-00020-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a350e6d1f589158c70995efe032c2285af12f0c0c83c82783ebd0f039c529dc7
|
3 |
+
size 4680961248
|
model-00021-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230857fddf6947f690fdbf1277d59f7b56754dd2d6bee4bb88864ec71d6e0342
|
3 |
+
size 4982901400
|
model-00022-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08ae86b8152438cf45d1f75c7c26108a75a5cf5d8d5aacfabf56d3e6ac603e3d
|
3 |
+
size 4697737872
|
model-00023-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccfc05f88a72e9c6a5c3140f9f1943fc945560468984dfbf9d1cc6cd42d6e03f
|
3 |
+
size 4932603104
|
model-00024-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6639816c59677050e490db414bc782f2eb4c2b33ebf4ab19bcf0e20a27ac5ea
|
3 |
+
size 4697722080
|
model-00025-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed492dfae8bc591f2ee7fd2fe0fddbb4bd5173164fc9a0c1f9de8e816f19268f
|
3 |
+
size 4546660208
|
model-00026-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6135d55997c6d8bb8690009fd77c5b6af852dc062c322ac84dba3e9539a3a374
|
3 |
+
size 4949413432
|
model-00027-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43f724a31fc4f7770604d4a50041c5b8f5c93910786edec65fb571832a1939ac
|
3 |
+
size 4798401760
|
model-00028-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9036d469a3f90da0f14289255863a2320b275134d90cffbab2e4f0c9d3f11a09
|
3 |
+
size 4865460872
|
model-00029-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:753fe9c1b0245db32f19dc52a70b32e43d8b9d3bee5c912d4f44375b3c4d1e3d
|
3 |
+
size 4848667064
|
model-00030-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a14298a660ee73506217cea9a9eb1ec3a49190783ac02a72fc0908d206fc6587
|
3 |
+
size 4781640920
|
model-00031-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33237b6ccee5788b91d2901c285c1c534f5e58b71d6a6685a70d87b216d120b3
|
3 |
+
size 4932619592
|
model-00032-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef02f4d381f5296f6adb2bf3f4ebfb9a94ae14fc53c6dd3eae0eb0ec95167168
|
3 |
+
size 4899032040
|
model-00033-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae5afefc0351b6d3399170a5526b6d086ab77388f78e22e42fedb77dcd26b297
|
3 |
+
size 4815128904
|
model-00034-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7270879fc5a1dbf2d0f345541db14f536a6361c86b6e378f13a5de7966597790
|
3 |
+
size 4949413448
|
model-00035-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63a4e4b281847291f4032ea9b096a551ce8f9579f66e8ab83296dc6eec912e3a
|
3 |
+
size 4999711736
|
model-00036-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4aa5a36d61721a0524f686c1b0a213baa164757d85dfdf82bbb747acde1e3af
|
3 |
+
size 4680928256
|
model-00037-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bdd8c3541045f0a92d24746f8988cf20f90f48df28e94b24d119bd4e8ae96a4
|
3 |
+
size 4949330240
|
model-00038-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d01c177a45e4e0590550098b00538ced4addf43e0e008d89780701910618c43b
|
3 |
+
size 4680977760
|
model-00039-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b853e88e32ebff23da17eabbfdd9c9433d4b5967f5828fbec1e2c57e476b635
|
3 |
+
size 4781591456
|
model-00040-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b148cd1614cf31f5a4889378b3d93c2ede15ec70076e085d3e2e5ed012d2fba
|
3 |
+
size 4999711744
|
model-00041-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c41672a2014799ed7c8b4201f955b76376cd25856f1adf3d36456f2ab0fc7b5
|
3 |
+
size 4999711752
|
model-00042-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33656b803efae3127e5e8fc18b346663efe4047e03f7990c03ed7aed180391cd
|
3 |
+
size 4798368792
|
model-00043-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca0985eac3d96ba95b3fc0b0090ea248ea5c474c381681ba98116ce70f09a46f
|
3 |
+
size 4982950920
|
model-00044-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81ea2e1ce46236ceab5a8633e3194d2cb9803cf384de36e4f4f4162d534a6165
|
3 |
+
size 4781591432
|
model-00045-of-00045.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2be2fef160394d25d41fe3364f5db9d11f073dcf308b2f78d1b88bf2cdb00460
|
3 |
+
size 1208009504
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.1.0"}, "weight_map": {"model.layers.0.mlp.down_proj.weight": "model-00001-of-00045.safetensors", "lm_head.weight": "model-00001-of-00045.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00045.safetensors", "model.embed_tokens.weight": "model-00001-of-00045.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00045.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00045.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00045.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00045.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00045.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00045.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00045.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00045.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00045.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00045.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00045.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00045.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00045.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00045.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00045.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00045.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00045.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00045.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00045.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00045.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00045.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00045.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00045.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00045.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00045.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00045.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00045.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00045.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00045.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00045.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00045.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00045.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00045.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00045.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00045.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00045.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00045.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00045.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00045.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00045.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00045.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00045.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00045.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00045.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00045.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00045.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00045.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00045.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00045.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00045.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00045.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00045.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00045.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00045.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00045.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00045.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00045.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00045.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00045.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00045.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00045.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00045.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00045.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00045.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00045.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00045.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00045.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00045.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00045.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00045.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00045.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00045.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00045.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00045.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00045.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00045.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00045.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00045.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00045.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00045.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00045.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00045.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00045.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00045.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00045.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00045.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00045.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00045.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00045.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00045.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00045.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00045.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00045.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00005-of-00045.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00045.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00045.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00045.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00045.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00045.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00005-of-00045.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00045.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00045.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00045.safetensors", "model.layers.62.input_layernorm.weight": "model-00005-of-00045.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00045.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00045.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00045.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00045.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00045.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00045.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00006-of-00045.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00006-of-00045.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00006-of-00045.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00006-of-00045.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00006-of-00045.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00045.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00045.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00045.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00006-of-00045.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00006-of-00045.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00045.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00045.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00045.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00045.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00045.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00006-of-00045.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00045.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00045.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00006-of-00045.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00045.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00045.safetensors", "model.layers.63.input_layernorm.weight": "model-00006-of-00045.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00045.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00045.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00045.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00045.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00045.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00045.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00007-of-00045.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00007-of-00045.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00045.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00007-of-00045.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00007-of-00045.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00045.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00045.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00045.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00045.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00045.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00007-of-00045.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00008-of-00045.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00045.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00045.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00045.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00045.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00045.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00045.safetensors", "model.layers.64.input_layernorm.weight": "model-00008-of-00045.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00008-of-00045.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00008-of-00045.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00008-of-00045.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00008-of-00045.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00008-of-00045.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00045.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00045.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00008-of-00045.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00045.safetensors", "model.layers.65.input_layernorm.weight": "model-00008-of-00045.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00045.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00008-of-00045.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00045.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00045.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00008-of-00045.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00045.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00008-of-00045.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00045.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00008-of-00045.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00045.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00008-of-00045.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00008-of-00045.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00045.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00008-of-00045.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00045.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00009-of-00045.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00045.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00045.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00045.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00045.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00009-of-00045.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00045.safetensors", "model.layers.66.input_layernorm.weight": "model-00009-of-00045.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00009-of-00045.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00009-of-00045.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00009-of-00045.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00045.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00009-of-00045.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00045.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00045.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00045.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00009-of-00045.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00045.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00045.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00009-of-00045.safetensors", "model.layers.67.input_layernorm.weight": "model-00009-of-00045.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00009-of-00045.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00009-of-00045.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00009-of-00045.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00045.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00045.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00045.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00045.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00010-of-00045.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00045.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00045.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00010-of-00045.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00010-of-00045.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00010-of-00045.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00045.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00010-of-00045.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00010-of-00045.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00045.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00010-of-00045.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00045.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00045.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00045.safetensors", "model.layers.68.input_layernorm.weight": "model-00010-of-00045.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00010-of-00045.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00045.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00010-of-00045.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00045.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00011-of-00045.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00045.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00011-of-00045.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00045.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00011-of-00045.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00045.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00045.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00011-of-00045.safetensors", "model.layers.69.input_layernorm.weight": "model-00011-of-00045.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00045.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00011-of-00045.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00045.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00011-of-00045.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00011-of-00045.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00045.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00011-of-00045.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00045.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00045.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00045.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00011-of-00045.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00045.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00045.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00011-of-00045.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00011-of-00045.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00011-of-00045.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00011-of-00045.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00012-of-00045.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00045.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00012-of-00045.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00045.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00012-of-00045.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00045.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00045.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00012-of-00045.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00012-of-00045.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00012-of-00045.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00012-of-00045.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00012-of-00045.safetensors", "model.layers.70.input_layernorm.weight": "model-00012-of-00045.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00045.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00045.safetensors", "model.layers.71.input_layernorm.weight": "model-00012-of-00045.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00012-of-00045.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00045.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00012-of-00045.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00045.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00012-of-00045.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00045.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00012-of-00045.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00045.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00012-of-00045.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00045.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00012-of-00045.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00045.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00012-of-00045.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00045.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00012-of-00045.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00012-of-00045.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00045.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00045.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00013-of-00045.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00045.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00045.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00045.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00013-of-00045.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00013-of-00045.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00013-of-00045.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00013-of-00045.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00013-of-00045.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00045.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00045.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00045.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00013-of-00045.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00013-of-00045.safetensors", "model.layers.3.input_layernorm.weight": "model-00013-of-00045.safetensors", "model.layers.72.input_layernorm.weight": "model-00013-of-00045.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00013-of-00045.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00045.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00013-of-00045.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00045.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00045.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00014-of-00045.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00045.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00014-of-00045.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00045.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00014-of-00045.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00014-of-00045.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00045.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00014-of-00045.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00045.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00014-of-00045.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00014-of-00045.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00014-of-00045.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00014-of-00045.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00045.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00045.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00045.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00014-of-00045.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00014-of-00045.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00045.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00045.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00015-of-00045.safetensors", "model.layers.30.input_layernorm.weight": "model-00015-of-00045.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00045.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00045.safetensors", "model.layers.74.input_layernorm.weight": "model-00015-of-00045.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00015-of-00045.safetensors", "model.layers.73.input_layernorm.weight": "model-00015-of-00045.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00015-of-00045.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00045.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00015-of-00045.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00045.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00045.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00015-of-00045.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00045.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00045.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00015-of-00045.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00015-of-00045.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00015-of-00045.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00015-of-00045.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00045.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00045.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00015-of-00045.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00015-of-00045.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00015-of-00045.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00045.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00015-of-00045.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00015-of-00045.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00016-of-00045.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00016-of-00045.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00045.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00016-of-00045.safetensors", "model.layers.33.input_layernorm.weight": "model-00016-of-00045.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00016-of-00045.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00016-of-00045.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00016-of-00045.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00016-of-00045.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00016-of-00045.safetensors", "model.layers.76.input_layernorm.weight": "model-00016-of-00045.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00016-of-00045.safetensors", "model.layers.32.input_layernorm.weight": "model-00016-of-00045.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00016-of-00045.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00045.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00045.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00045.safetensors", "model.layers.75.input_layernorm.weight": "model-00016-of-00045.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00016-of-00045.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00016-of-00045.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00016-of-00045.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00016-of-00045.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00045.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00016-of-00045.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00016-of-00045.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00016-of-00045.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00045.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00016-of-00045.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00045.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00016-of-00045.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00017-of-00045.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00017-of-00045.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00045.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00017-of-00045.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00017-of-00045.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00017-of-00045.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00017-of-00045.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00017-of-00045.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00017-of-00045.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00017-of-00045.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00017-of-00045.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00017-of-00045.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00045.safetensors", "model.layers.35.input_layernorm.weight": "model-00017-of-00045.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00017-of-00045.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00017-of-00045.safetensors", "model.layers.78.input_layernorm.weight": "model-00017-of-00045.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00017-of-00045.safetensors", "model.layers.34.input_layernorm.weight": "model-00017-of-00045.safetensors", "model.layers.77.input_layernorm.weight": "model-00017-of-00045.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00045.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00018-of-00045.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00045.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00018-of-00045.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00018-of-00045.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00045.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00018-of-00045.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00018-of-00045.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00018-of-00045.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00018-of-00045.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00018-of-00045.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00018-of-00045.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00045.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00018-of-00045.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00045.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00018-of-00045.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00018-of-00045.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00018-of-00045.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00018-of-00045.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00045.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00018-of-00045.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00018-of-00045.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00018-of-00045.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00045.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00019-of-00045.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00045.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00045.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00019-of-00045.safetensors", "model.layers.37.input_layernorm.weight": "model-00019-of-00045.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00019-of-00045.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00019-of-00045.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00019-of-00045.safetensors", "model.layers.80.input_layernorm.weight": "model-00019-of-00045.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00045.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00019-of-00045.safetensors", "model.layers.36.input_layernorm.weight": "model-00019-of-00045.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00045.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00019-of-00045.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00045.safetensors", "model.layers.79.input_layernorm.weight": "model-00019-of-00045.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00019-of-00045.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00045.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00019-of-00045.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00045.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00019-of-00045.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00019-of-00045.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00045.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00019-of-00045.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00019-of-00045.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00019-of-00045.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00019-of-00045.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00019-of-00045.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00019-of-00045.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00019-of-00045.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00020-of-00045.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00045.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00020-of-00045.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00020-of-00045.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00020-of-00045.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00045.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00020-of-00045.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00045.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00020-of-00045.safetensors", "model.layers.39.input_layernorm.weight": "model-00020-of-00045.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00020-of-00045.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00020-of-00045.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00020-of-00045.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00020-of-00045.safetensors", "model.layers.82.input_layernorm.weight": "model-00020-of-00045.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00045.safetensors", "model.layers.38.input_layernorm.weight": "model-00020-of-00045.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00020-of-00045.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00020-of-00045.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00020-of-00045.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00045.safetensors", "model.layers.81.input_layernorm.weight": "model-00020-of-00045.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00045.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00045.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00020-of-00045.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00020-of-00045.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00020-of-00045.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00045.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00045.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00021-of-00045.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00021-of-00045.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00045.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00045.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00045.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00021-of-00045.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00021-of-00045.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00021-of-00045.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00045.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00045.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00021-of-00045.safetensors", "model.layers.83.input_layernorm.weight": "model-00021-of-00045.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00021-of-00045.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00021-of-00045.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00021-of-00045.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00021-of-00045.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00045.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00045.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00021-of-00045.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00045.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00021-of-00045.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00045.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00022-of-00045.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00022-of-00045.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00022-of-00045.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00022-of-00045.safetensors", "model.layers.4.input_layernorm.weight": "model-00022-of-00045.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00045.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00022-of-00045.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00022-of-00045.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00022-of-00045.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00045.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00022-of-00045.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00022-of-00045.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00045.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00022-of-00045.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00045.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00022-of-00045.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00022-of-00045.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00022-of-00045.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00045.safetensors", "model.layers.42.input_layernorm.weight": "model-00022-of-00045.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00022-of-00045.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00022-of-00045.safetensors", "model.layers.85.input_layernorm.weight": "model-00022-of-00045.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00023-of-00045.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00023-of-00045.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00023-of-00045.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00023-of-00045.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00023-of-00045.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00023-of-00045.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00023-of-00045.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00023-of-00045.safetensors", "model.layers.41.input_layernorm.weight": "model-00023-of-00045.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00023-of-00045.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00023-of-00045.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00023-of-00045.safetensors", "model.layers.84.input_layernorm.weight": "model-00023-of-00045.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00023-of-00045.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00023-of-00045.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00023-of-00045.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00023-of-00045.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00023-of-00045.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00023-of-00045.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00023-of-00045.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00023-of-00045.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00023-of-00045.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00023-of-00045.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00023-of-00045.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00023-of-00045.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00023-of-00045.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00023-of-00045.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00023-of-00045.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00024-of-00045.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00024-of-00045.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00024-of-00045.safetensors", "model.layers.44.input_layernorm.weight": "model-00024-of-00045.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00024-of-00045.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00024-of-00045.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00024-of-00045.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00024-of-00045.safetensors", "model.layers.87.input_layernorm.weight": "model-00024-of-00045.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00024-of-00045.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00024-of-00045.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00024-of-00045.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00024-of-00045.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00024-of-00045.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00024-of-00045.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00024-of-00045.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00024-of-00045.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00024-of-00045.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00024-of-00045.safetensors", "model.layers.43.input_layernorm.weight": "model-00024-of-00045.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00024-of-00045.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00024-of-00045.safetensors", "model.layers.86.input_layernorm.weight": "model-00024-of-00045.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00024-of-00045.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00024-of-00045.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00024-of-00045.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00024-of-00045.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00024-of-00045.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00025-of-00045.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00025-of-00045.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00045.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00025-of-00045.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00025-of-00045.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00025-of-00045.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00025-of-00045.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00025-of-00045.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00025-of-00045.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00025-of-00045.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00025-of-00045.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00025-of-00045.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00025-of-00045.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00025-of-00045.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00025-of-00045.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00025-of-00045.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00026-of-00045.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00026-of-00045.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00026-of-00045.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00026-of-00045.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00026-of-00045.safetensors", "model.layers.46.input_layernorm.weight": "model-00026-of-00045.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00026-of-00045.safetensors", "model.layers.45.input_layernorm.weight": "model-00026-of-00045.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00026-of-00045.safetensors", "model.layers.89.input_layernorm.weight": "model-00026-of-00045.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00026-of-00045.safetensors", "model.layers.88.input_layernorm.weight": "model-00026-of-00045.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00026-of-00045.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00026-of-00045.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00026-of-00045.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00026-of-00045.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00026-of-00045.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00026-of-00045.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00026-of-00045.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00026-of-00045.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00026-of-00045.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00026-of-00045.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00026-of-00045.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00026-of-00045.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00026-of-00045.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00026-of-00045.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00026-of-00045.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00026-of-00045.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00026-of-00045.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00026-of-00045.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00026-of-00045.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00027-of-00045.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00027-of-00045.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00027-of-00045.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00027-of-00045.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00027-of-00045.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00027-of-00045.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00027-of-00045.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00027-of-00045.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00027-of-00045.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00027-of-00045.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00027-of-00045.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00027-of-00045.safetensors", "model.layers.48.input_layernorm.weight": "model-00027-of-00045.safetensors", "model.layers.47.input_layernorm.weight": "model-00027-of-00045.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00027-of-00045.safetensors", "model.layers.91.input_layernorm.weight": "model-00027-of-00045.safetensors", "model.layers.90.input_layernorm.weight": "model-00027-of-00045.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00027-of-00045.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00027-of-00045.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00027-of-00045.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00027-of-00045.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00027-of-00045.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00027-of-00045.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00027-of-00045.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00027-of-00045.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00027-of-00045.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00027-of-00045.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00027-of-00045.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00028-of-00045.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00028-of-00045.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00028-of-00045.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00028-of-00045.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00028-of-00045.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00028-of-00045.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00028-of-00045.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00028-of-00045.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00028-of-00045.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00028-of-00045.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00028-of-00045.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00028-of-00045.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00028-of-00045.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00028-of-00045.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00028-of-00045.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00028-of-00045.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00028-of-00045.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00028-of-00045.safetensors", "model.layers.5.input_layernorm.weight": "model-00028-of-00045.safetensors", "model.layers.49.input_layernorm.weight": "model-00028-of-00045.safetensors", "model.layers.92.input_layernorm.weight": "model-00028-of-00045.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00028-of-00045.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00028-of-00045.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00029-of-00045.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00029-of-00045.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00029-of-00045.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00029-of-00045.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00045.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00029-of-00045.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00029-of-00045.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00029-of-00045.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00029-of-00045.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00029-of-00045.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00029-of-00045.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00029-of-00045.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00029-of-00045.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00029-of-00045.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00029-of-00045.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00029-of-00045.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00029-of-00045.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00029-of-00045.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00029-of-00045.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00029-of-00045.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00029-of-00045.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00030-of-00045.safetensors", "model.layers.50.input_layernorm.weight": "model-00030-of-00045.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00030-of-00045.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00030-of-00045.safetensors", "model.layers.51.input_layernorm.weight": "model-00030-of-00045.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00030-of-00045.safetensors", "model.layers.93.input_layernorm.weight": "model-00030-of-00045.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00030-of-00045.safetensors", "model.layers.94.input_layernorm.weight": "model-00030-of-00045.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00030-of-00045.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00030-of-00045.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00030-of-00045.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00030-of-00045.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00030-of-00045.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00030-of-00045.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00030-of-00045.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00045.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00030-of-00045.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00030-of-00045.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00030-of-00045.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00030-of-00045.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00030-of-00045.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00030-of-00045.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00030-of-00045.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00030-of-00045.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00030-of-00045.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00030-of-00045.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00030-of-00045.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00031-of-00045.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00031-of-00045.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00031-of-00045.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00031-of-00045.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00031-of-00045.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00031-of-00045.safetensors", "model.layers.52.input_layernorm.weight": "model-00031-of-00045.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00031-of-00045.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00031-of-00045.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00031-of-00045.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00031-of-00045.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00031-of-00045.safetensors", "model.layers.95.input_layernorm.weight": "model-00031-of-00045.safetensors", "model.layers.53.input_layernorm.weight": "model-00031-of-00045.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00031-of-00045.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00045.safetensors", "model.layers.96.input_layernorm.weight": "model-00031-of-00045.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00031-of-00045.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00031-of-00045.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00031-of-00045.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00031-of-00045.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00031-of-00045.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00031-of-00045.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00031-of-00045.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00031-of-00045.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00031-of-00045.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00031-of-00045.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00031-of-00045.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00031-of-00045.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00032-of-00045.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00032-of-00045.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00032-of-00045.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00032-of-00045.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00032-of-00045.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00032-of-00045.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00032-of-00045.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00032-of-00045.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00032-of-00045.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00032-of-00045.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00032-of-00045.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00032-of-00045.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00032-of-00045.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00032-of-00045.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00032-of-00045.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00032-of-00045.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00032-of-00045.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00032-of-00045.safetensors", "model.layers.54.input_layernorm.weight": "model-00032-of-00045.safetensors", "model.layers.97.input_layernorm.weight": "model-00032-of-00045.safetensors", "model.layers.55.input_layernorm.weight": "model-00032-of-00045.safetensors", "model.layers.98.input_layernorm.weight": "model-00032-of-00045.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00032-of-00045.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00032-of-00045.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00032-of-00045.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00032-of-00045.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00033-of-00045.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00045.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00033-of-00045.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00033-of-00045.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00033-of-00045.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00033-of-00045.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00033-of-00045.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00033-of-00045.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00033-of-00045.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00033-of-00045.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00033-of-00045.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00033-of-00045.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00033-of-00045.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00033-of-00045.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00033-of-00045.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00033-of-00045.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00033-of-00045.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00033-of-00045.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00033-of-00045.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00045.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00034-of-00045.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00034-of-00045.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00045.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00034-of-00045.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00034-of-00045.safetensors", "model.layers.56.input_layernorm.weight": "model-00034-of-00045.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00034-of-00045.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00034-of-00045.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00034-of-00045.safetensors", "model.layers.57.input_layernorm.weight": "model-00034-of-00045.safetensors", "model.layers.99.input_layernorm.weight": "model-00034-of-00045.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00034-of-00045.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00034-of-00045.safetensors", "model.layers.100.input_layernorm.weight": "model-00034-of-00045.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00034-of-00045.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00034-of-00045.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00034-of-00045.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00034-of-00045.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00045.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00034-of-00045.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00034-of-00045.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00034-of-00045.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00034-of-00045.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00034-of-00045.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00034-of-00045.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00034-of-00045.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00034-of-00045.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00034-of-00045.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00034-of-00045.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00034-of-00045.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00034-of-00045.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00035-of-00045.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00035-of-00045.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00035-of-00045.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00035-of-00045.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00035-of-00045.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00035-of-00045.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00035-of-00045.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00035-of-00045.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00035-of-00045.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00035-of-00045.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00035-of-00045.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00035-of-00045.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00035-of-00045.safetensors", "model.layers.58.input_layernorm.weight": "model-00035-of-00045.safetensors", "model.layers.59.input_layernorm.weight": "model-00035-of-00045.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00035-of-00045.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00035-of-00045.safetensors", "model.layers.101.input_layernorm.weight": "model-00035-of-00045.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00035-of-00045.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00045.safetensors", "model.layers.102.input_layernorm.weight": "model-00035-of-00045.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00035-of-00045.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00035-of-00045.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00035-of-00045.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00035-of-00045.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00035-of-00045.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00036-of-00045.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00036-of-00045.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00036-of-00045.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00036-of-00045.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00036-of-00045.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00036-of-00045.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00036-of-00045.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00036-of-00045.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00036-of-00045.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00036-of-00045.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00036-of-00045.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00036-of-00045.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00036-of-00045.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00036-of-00045.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00036-of-00045.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00036-of-00045.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00036-of-00045.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00036-of-00045.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00036-of-00045.safetensors", "model.layers.6.input_layernorm.weight": "model-00036-of-00045.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00036-of-00045.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00036-of-00045.safetensors", "model.layers.60.input_layernorm.weight": "model-00036-of-00045.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00036-of-00045.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00036-of-00045.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00036-of-00045.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00037-of-00045.safetensors", "model.layers.103.input_layernorm.weight": "model-00037-of-00045.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00037-of-00045.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00037-of-00045.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00037-of-00045.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00037-of-00045.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00037-of-00045.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00037-of-00045.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00037-of-00045.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00037-of-00045.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00037-of-00045.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00037-of-00045.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00037-of-00045.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00037-of-00045.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00037-of-00045.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00037-of-00045.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00037-of-00045.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00037-of-00045.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00037-of-00045.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00037-of-00045.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00038-of-00045.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00038-of-00045.safetensors", "model.layers.61.input_layernorm.weight": "model-00038-of-00045.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00038-of-00045.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00038-of-00045.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00038-of-00045.safetensors", "model.layers.105.input_layernorm.weight": "model-00038-of-00045.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00038-of-00045.safetensors", "model.layers.104.input_layernorm.weight": "model-00038-of-00045.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00038-of-00045.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00038-of-00045.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00038-of-00045.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00038-of-00045.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00038-of-00045.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00038-of-00045.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00038-of-00045.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00038-of-00045.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00038-of-00045.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00038-of-00045.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00038-of-00045.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00038-of-00045.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00038-of-00045.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00038-of-00045.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00038-of-00045.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00038-of-00045.safetensors", "model.layers.107.input_layernorm.weight": "model-00038-of-00045.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00038-of-00045.safetensors", "model.layers.106.input_layernorm.weight": "model-00038-of-00045.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00038-of-00045.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00039-of-00045.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00039-of-00045.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00039-of-00045.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00039-of-00045.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00039-of-00045.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00039-of-00045.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00039-of-00045.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00039-of-00045.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00039-of-00045.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00039-of-00045.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00039-of-00045.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00039-of-00045.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00039-of-00045.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00039-of-00045.safetensors", "model.layers.109.input_layernorm.weight": "model-00039-of-00045.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00039-of-00045.safetensors", "model.layers.108.input_layernorm.weight": "model-00039-of-00045.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00039-of-00045.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00039-of-00045.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00039-of-00045.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00039-of-00045.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00039-of-00045.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00039-of-00045.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00039-of-00045.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00039-of-00045.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00040-of-00045.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00040-of-00045.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00040-of-00045.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00040-of-00045.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00040-of-00045.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00040-of-00045.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00040-of-00045.safetensors", "model.layers.111.input_layernorm.weight": "model-00040-of-00045.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00040-of-00045.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00040-of-00045.safetensors", "model.layers.110.input_layernorm.weight": "model-00040-of-00045.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00040-of-00045.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00040-of-00045.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00040-of-00045.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00040-of-00045.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00040-of-00045.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00040-of-00045.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00040-of-00045.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00040-of-00045.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00040-of-00045.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00040-of-00045.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00040-of-00045.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00040-of-00045.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00040-of-00045.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00040-of-00045.safetensors", "model.layers.7.input_layernorm.weight": "model-00040-of-00045.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00041-of-00045.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00041-of-00045.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00041-of-00045.safetensors", "model.layers.112.input_layernorm.weight": "model-00041-of-00045.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00041-of-00045.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00041-of-00045.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00041-of-00045.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00041-of-00045.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00041-of-00045.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00041-of-00045.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00041-of-00045.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00041-of-00045.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00041-of-00045.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00041-of-00045.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00041-of-00045.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00041-of-00045.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00041-of-00045.safetensors", "model.layers.114.input_layernorm.weight": "model-00041-of-00045.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00041-of-00045.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00041-of-00045.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00041-of-00045.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00041-of-00045.safetensors", "model.layers.113.input_layernorm.weight": "model-00041-of-00045.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00041-of-00045.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00041-of-00045.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00041-of-00045.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00042-of-00045.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00042-of-00045.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00042-of-00045.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00042-of-00045.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00042-of-00045.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00042-of-00045.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00042-of-00045.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00042-of-00045.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00042-of-00045.safetensors", "model.layers.116.input_layernorm.weight": "model-00042-of-00045.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00042-of-00045.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00042-of-00045.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00042-of-00045.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00042-of-00045.safetensors", "model.layers.115.input_layernorm.weight": "model-00042-of-00045.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00042-of-00045.safetensors", "model.layers.120.mlp.gate_proj.weight": "model-00042-of-00045.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00042-of-00045.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00042-of-00045.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00042-of-00045.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00042-of-00045.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00042-of-00045.safetensors", "model.layers.120.self_attn.v_proj.weight": "model-00042-of-00045.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00042-of-00045.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00042-of-00045.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00042-of-00045.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00043-of-00045.safetensors", "model.layers.118.input_layernorm.weight": "model-00043-of-00045.safetensors", "model.layers.121.self_attn.k_proj.weight": "model-00043-of-00045.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00043-of-00045.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00043-of-00045.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00043-of-00045.safetensors", "model.layers.117.input_layernorm.weight": "model-00043-of-00045.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00043-of-00045.safetensors", "model.layers.122.mlp.gate_proj.weight": "model-00043-of-00045.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00043-of-00045.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00043-of-00045.safetensors", "model.layers.120.mlp.down_proj.weight": "model-00043-of-00045.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00043-of-00045.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00043-of-00045.safetensors", "model.layers.122.self_attn.v_proj.weight": "model-00043-of-00045.safetensors", "model.layers.120.self_attn.k_proj.weight": "model-00043-of-00045.safetensors", "model.layers.120.post_attention_layernorm.weight": "model-00043-of-00045.safetensors", "model.layers.120.self_attn.q_proj.weight": "model-00043-of-00045.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00043-of-00045.safetensors", "model.layers.120.input_layernorm.weight": "model-00043-of-00045.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00043-of-00045.safetensors", "model.layers.121.mlp.gate_proj.weight": "model-00043-of-00045.safetensors", "model.layers.121.mlp.down_proj.weight": "model-00043-of-00045.safetensors", "model.layers.121.post_attention_layernorm.weight": "model-00043-of-00045.safetensors", "model.layers.119.input_layernorm.weight": "model-00043-of-00045.safetensors", "model.layers.120.self_attn.o_proj.weight": "model-00043-of-00045.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00044-of-00045.safetensors", "model.layers.121.self_attn.v_proj.weight": "model-00044-of-00045.safetensors", "model.layers.121.self_attn.q_proj.weight": "model-00044-of-00045.safetensors", "model.layers.122.mlp.down_proj.weight": "model-00044-of-00045.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00044-of-00045.safetensors", "model.layers.121.mlp.up_proj.weight": "model-00044-of-00045.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00044-of-00045.safetensors", "model.layers.122.self_attn.k_proj.weight": "model-00044-of-00045.safetensors", "model.layers.122.post_attention_layernorm.weight": "model-00044-of-00045.safetensors", "model.layers.122.self_attn.q_proj.weight": "model-00044-of-00045.safetensors", "model.layers.120.mlp.up_proj.weight": "model-00044-of-00045.safetensors", "model.layers.122.input_layernorm.weight": "model-00044-of-00045.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00044-of-00045.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00044-of-00045.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00044-of-00045.safetensors", "model.layers.121.input_layernorm.weight": "model-00044-of-00045.safetensors", "model.layers.122.self_attn.o_proj.weight": "model-00044-of-00045.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00044-of-00045.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00044-of-00045.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00044-of-00045.safetensors", "model.layers.121.self_attn.o_proj.weight": "model-00044-of-00045.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00044-of-00045.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00044-of-00045.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00044-of-00045.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00044-of-00045.safetensors", "model.layers.122.mlp.up_proj.weight": "model-00045-of-00045.safetensors", "model.layers.9.input_layernorm.weight": "model-00045-of-00045.safetensors", "model.layers.8.input_layernorm.weight": "model-00045-of-00045.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00045-of-00045.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00045-of-00045.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00045-of-00045.safetensors", "model.norm.weight": "model-00045-of-00045.safetensors"}}
|