Upload folder using huggingface_hub
Browse files- README.md +54 -0
- config.json +30 -0
- huggingface-metadata.txt +53 -0
- measurement.json +0 -0
- model.safetensors.index.json +1 -0
- output-00001-of-00003.safetensors +3 -0
- output-00002-of-00003.safetensors +3 -0
- output-00003-of-00003.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- ycros/BagelMIsteryTour-v2-8x7B
|
4 |
+
- smelborp/MixtralOrochi8x7B
|
5 |
+
- cognitivecomputations/dolphin-2.7-mixtral-8x7b
|
6 |
+
library_name: transformers
|
7 |
+
tags:
|
8 |
+
- mergekit
|
9 |
+
- merge
|
10 |
+
|
11 |
+
---
|
12 |
+
# maid-yuzu-v7
|
13 |
+
|
14 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
+
|
16 |
+
I don't know anything about merges, so this may be a stupid method, but I was curious how the models would be merged if I took this approach.
|
17 |
+
|
18 |
+
## Merge Details
|
19 |
+
### Merge Method
|
20 |
+
|
21 |
+
This model was merged using the SLERP merge method.
|
22 |
+
|
23 |
+
This model is a model that first merges Model [Orochi](https://huggingface.co/smelborp/MixtralOrochi8x7B) with Model [dolphin](https://huggingface.co/cognitivecomputations/dolphin-2.7-mixtral-8x7b) with a 0.15 SLERP option, and then merges Model [BagelMIsteryTour](https://huggingface.co/ycros/BagelMIsteryTour-v2-8x7B) with a 0.2 SLERP option based on the merged model.
|
24 |
+
|
25 |
+
### Models Merged
|
26 |
+
|
27 |
+
The following models were included in the merge:
|
28 |
+
* [ycros/BagelMIsteryTour-v2-8x7B](https://huggingface.co/ycros/BagelMIsteryTour-v2-8x7B)
|
29 |
+
* ../maid-yuzu-v7-base
|
30 |
+
|
31 |
+
### Configuration
|
32 |
+
|
33 |
+
The following YAML configuration was used to produce this model:
|
34 |
+
|
35 |
+
```yaml
|
36 |
+
base_model:
|
37 |
+
model:
|
38 |
+
path: ../maid-yuzu-v7-base
|
39 |
+
dtype: bfloat16
|
40 |
+
merge_method: slerp
|
41 |
+
parameters:
|
42 |
+
t:
|
43 |
+
- value: 0.2
|
44 |
+
slices:
|
45 |
+
- sources:
|
46 |
+
- layer_range: [0, 32]
|
47 |
+
model:
|
48 |
+
model:
|
49 |
+
path: ../maid-yuzu-v7-base
|
50 |
+
- layer_range: [0, 32]
|
51 |
+
model:
|
52 |
+
model:
|
53 |
+
path: ycros/BagelMIsteryTour-v2-8x7B
|
54 |
+
```
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../maid-yuzu-v7-base",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000.0,
|
23 |
+
"router_aux_loss_coef": 0.02,
|
24 |
+
"sliding_window": null,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.37.2",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
huggingface-metadata.txt
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
url: https://huggingface.co/rhplus0831/maid-yuzu-v7
|
2 |
+
branch: main
|
3 |
+
download date: 2024-02-13 10:00:06
|
4 |
+
sha256sum:
|
5 |
+
813e8970446b7d213c7ce8d638845df66706bfac6970f29b2148bd16ccf543d4 model-00001-of-00048.safetensors
|
6 |
+
14982225bfcb30731d8a5996cc2293cd04a79da002039662eba5c2f4d2cd6ef8 model-00002-of-00048.safetensors
|
7 |
+
0e2d1f170da5a77cbf71416a21d4eba291ca01a9a78104bfd537cc8fa1035d24 model-00003-of-00048.safetensors
|
8 |
+
26be6b9a90333d8844e89340ca9799c93e08f95c86dd5ae633e3b5bab6ebf564 model-00004-of-00048.safetensors
|
9 |
+
e63a5b3cc9462ab4719ea966b9ac19125eb877a398bdeaa93589f891058dfaf7 model-00005-of-00048.safetensors
|
10 |
+
93af03d70567930d9b22b773760187fa957558425b98c40e1a25403b87ffd153 model-00006-of-00048.safetensors
|
11 |
+
39f5fc8243b91ffbc10bc5db156bdbd771848f0d80557aa9f830217423db07fd model-00007-of-00048.safetensors
|
12 |
+
044ed128c286bb19c4f883c4892c1a5cf01772f4758cc5b7231e83a90bf4fd8e model-00008-of-00048.safetensors
|
13 |
+
720fa5cd743a7e747c57aa681769026312b0ba4688ae5aede5706980da21ef1a model-00009-of-00048.safetensors
|
14 |
+
a95879226b168fbeabc912dbc9c463074dcac7a1e89fd13f8aa71f0194eb1d11 model-00010-of-00048.safetensors
|
15 |
+
51fd1f685b6def376b5e26450cd15d353c7b56fedf1c2b6e88059661217185d6 model-00011-of-00048.safetensors
|
16 |
+
1d6f3ea0b8e8f9f99a5e64550a25f27fc3a817f99d230c70d8efb24220447914 model-00012-of-00048.safetensors
|
17 |
+
5e43b4a4fee51b6b459a0665220b64d120bb53b60a5852b3e5dd9b8e3eca482c model-00013-of-00048.safetensors
|
18 |
+
a9c5d8972db5f857a55289fa068ed43e845d085d6c01a282cdf0b15228f550e0 model-00014-of-00048.safetensors
|
19 |
+
623a17b438d74d0a12570384f5b0f12962d304715e2cca2133a62cd7fdf1f79f model-00015-of-00048.safetensors
|
20 |
+
be92f7fe065fc1efcc188e69de182074df34968c1016a08e0e66949801f6cc00 model-00016-of-00048.safetensors
|
21 |
+
f8ab0c10a6524c10f33c48fcf8b20e6fe12a95bc58a51fd32f34885eec802a87 model-00017-of-00048.safetensors
|
22 |
+
369ef2165c465fa35eaba513abb0169299f985132bfbcf42cf1e8ea040ade9f6 model-00018-of-00048.safetensors
|
23 |
+
e823d6f8e805266a773f16cff34663024a9dc9deb8e70b71138d66694edd3e58 model-00019-of-00048.safetensors
|
24 |
+
037dd6806dcd2f654eec0eac4aa3523ed78f74d617d30ed0905983293b46aa8c model-00020-of-00048.safetensors
|
25 |
+
6e59f744e6e767c4807120c923074a2a81bd1397154d5ecf365c53badb74e142 model-00021-of-00048.safetensors
|
26 |
+
915accbc2e627e771a28e1e98af0dfb7c5c55c6576ec3bcd50116d57e0a7da06 model-00022-of-00048.safetensors
|
27 |
+
8563cd47cc46eae5527310a1b404d04f00b256a56eae7a18eb7ffd17d4df7660 model-00023-of-00048.safetensors
|
28 |
+
b8256faba2472f1e6f07b29da0309553954ccdc89e252f9cfaebadf0f2ecadad model-00024-of-00048.safetensors
|
29 |
+
b558cfae4f264d68e28991359f8a26e6212cccb0f42b1a18706656e2c40b20f3 model-00025-of-00048.safetensors
|
30 |
+
42b17e21f8d42129959ecfe0bf98fa763040f972803c276c6af131abf98a83e4 model-00026-of-00048.safetensors
|
31 |
+
14b720acf9ee4c56994a9b929a4f80a811bdb747010662711497b9e18fd11120 model-00027-of-00048.safetensors
|
32 |
+
ead52e2bf857b91fce7219234f5fff61a82c5a1b5d593eec3f3ca021f04bfbfa model-00028-of-00048.safetensors
|
33 |
+
e2c6035ad8a067f53eb5935ad7a7d0b0ca05d229c38b2803fba381b23e954be9 model-00029-of-00048.safetensors
|
34 |
+
cd167bb90d336a780d5cebb0744b21a25582a09250b2c7fd21e35094b0e36566 model-00030-of-00048.safetensors
|
35 |
+
1c12215c615d07e3cc31c8ed56151ebb11e932a6280da1be157d7cedc27a6e28 model-00031-of-00048.safetensors
|
36 |
+
6de82bc33eeed201ab3ac82ca12f7a05ab190d3f7a4dfbc9da0d7e0838039e96 model-00032-of-00048.safetensors
|
37 |
+
8cdc1887f805e311eb3e7ed50560c036ee3853f9b391150974f4c5fdf92e3b7b model-00033-of-00048.safetensors
|
38 |
+
e62ce7de257c0e5fef544fcc9f4099f56510c3b338fdc743970a0577708661f4 model-00034-of-00048.safetensors
|
39 |
+
1c826da0b6c0af5076a26e34754229bbd3e1129ae66ce392b60902f202a8a0dd model-00035-of-00048.safetensors
|
40 |
+
6a1fe966ed46c8503ca34d403b358b09e70a2239259b0dd4ea347bbe80e6fb45 model-00036-of-00048.safetensors
|
41 |
+
0321da3b56603b4240de4a10d6ca7cd0633159101db2f6e2446b54395b57182f model-00037-of-00048.safetensors
|
42 |
+
64e684298e77c1831b367661cfccbbef04098ffebd37d9475228ffec90e5e730 model-00038-of-00048.safetensors
|
43 |
+
043a7db835d8e45fb5a14872140dd7e5d4dadc1419b551ef50f0fb8a8cbde069 model-00039-of-00048.safetensors
|
44 |
+
90c52a440da74ae65e7ee990327db73b109b05df650a70f198817f2c37b9b24d model-00040-of-00048.safetensors
|
45 |
+
f620a086ba80d0f5a7585b61777e3744341749995245ab4cec4bbc6302196824 model-00041-of-00048.safetensors
|
46 |
+
bc3f6c8baeb7a2f880795b848ba94045208ae3c3a04248aef4a170e5f0809a05 model-00042-of-00048.safetensors
|
47 |
+
8ef40fa7c0394019f2bd5e490592bf39217c591e35604cf1ac0510205ad6f803 model-00043-of-00048.safetensors
|
48 |
+
f711cd3b67be3fc27a0bd717113537caf1d5695d42e00ce1a6900bed99945c00 model-00044-of-00048.safetensors
|
49 |
+
af0c7812a6293f8cce8c2eb0f9a6785a3b0a5cdcdbbfbb7f39b7f8c9ce1e72ea model-00045-of-00048.safetensors
|
50 |
+
babb3d2c182af5d4354fa1bce0a2f5ed8a84eb8285164bc5648796ba498b186c model-00046-of-00048.safetensors
|
51 |
+
3adcf4f5e575b97c171cbbd55b77d79f4f4dd4af32e89a30d805aeeaa6de4385 model-00047-of-00048.safetensors
|
52 |
+
d45cc7d920d4a10dff3625e705f5e3bd535f60027d2e9ab1fcf7deef570e81fe model-00048-of-00048.safetensors
|
53 |
+
dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 tokenizer.model
|
measurement.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00048.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00048.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00048.safetensors", "model.embed_tokens.weight": "model-00003-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00048.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00048.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00048.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00048.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00048.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00048.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00048.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00048.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00048.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00048.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00048.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00048.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00048.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00048.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00048.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00048.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00048.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00048.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00048.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00048.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00048.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00048.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00048.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00048.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00012-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00048.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00048.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00048.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00048.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00048.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00048.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00048.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00048.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00048.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00048.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00048.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00048.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00048.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00048.safetensors", "model.layers.9.input_layernorm.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00048.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00015-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00048.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", "model.layers.8.input_layernorm.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00048.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00017-of-00048.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00017-of-00048.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00017-of-00048.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00048.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00017-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00048.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", "model.layers.10.input_layernorm.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00048.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00048.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00048.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00048.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00020-of-00048.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00020-of-00048.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00020-of-00048.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.12.input_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00048.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00020-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00048.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00021-of-00048.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00021-of-00048.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00021-of-00048.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00021-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00048.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00021-of-00048.safetensors", "model.layers.11.input_layernorm.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00022-of-00048.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00022-of-00048.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00022-of-00048.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00022-of-00048.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.14.input_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00048.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00022-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00023-of-00048.safetensors", "model.layers.13.input_layernorm.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00024-of-00048.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00024-of-00048.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00024-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00048.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00025-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00048.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00026-of-00048.safetensors", "model.layers.15.input_layernorm.weight": "model-00026-of-00048.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00027-of-00048.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00027-of-00048.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00048.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00027-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00048.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00028-of-00048.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00028-of-00048.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00028-of-00048.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00028-of-00048.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00028-of-00048.safetensors", "model.layers.17.input_layernorm.weight": "model-00028-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00028-of-00048.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00028-of-00048.safetensors", "model.layers.16.input_layernorm.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00048.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00029-of-00048.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00029-of-00048.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00048.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00030-of-00048.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00030-of-00048.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00030-of-00048.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00030-of-00048.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00030-of-00048.safetensors", "model.layers.19.input_layernorm.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00048.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00030-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00048.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00031-of-00048.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00031-of-00048.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00048.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00031-of-00048.safetensors", "model.layers.18.input_layernorm.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00048.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00032-of-00048.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00032-of-00048.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00032-of-00048.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00032-of-00048.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00032-of-00048.safetensors", "model.layers.21.input_layernorm.weight": "model-00032-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00032-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00032-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00032-of-00048.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00032-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00048.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00033-of-00048.safetensors", "model.layers.20.input_layernorm.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00034-of-00048.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00034-of-00048.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00034-of-00048.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00034-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00048.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00035-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00048.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00036-of-00048.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00036-of-00048.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00036-of-00048.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00036-of-00048.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00036-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00048.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00036-of-00048.safetensors", "model.layers.22.input_layernorm.weight": "model-00036-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00048.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00037-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00048.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00038-of-00048.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00038-of-00048.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00038-of-00048.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00048.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00038-of-00048.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00038-of-00048.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00038-of-00048.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.24.input_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00048.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.23.input_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00040-of-00048.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00040-of-00048.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00040-of-00048.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00040-of-00048.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00040-of-00048.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00040-of-00048.safetensors", "model.layers.26.input_layernorm.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00040-of-00048.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00040-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00041-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00041-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00041-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00041-of-00048.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00041-of-00048.safetensors", "model.layers.25.input_layernorm.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00042-of-00048.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00042-of-00048.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00042-of-00048.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00042-of-00048.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00042-of-00048.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00042-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00043-of-00048.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00043-of-00048.safetensors", "model.layers.27.input_layernorm.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00044-of-00048.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00044-of-00048.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00044-of-00048.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00044-of-00048.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00045-of-00048.safetensors", "lm_head.weight": "model-00046-of-00048.safetensors", "model.norm.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00046-of-00048.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00046-of-00048.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00046-of-00048.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00046-of-00048.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00046-of-00048.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.29.input_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00046-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00046-of-00048.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.28.input_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00047-of-00048.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00047-of-00048.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00047-of-00048.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00047-of-00048.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00047-of-00048.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00047-of-00048.safetensors", "model.layers.31.input_layernorm.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00048-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00048-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00048-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00048-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00048-of-00048.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00048-of-00048.safetensors", "model.layers.30.input_layernorm.weight": "model-00048-of-00048.safetensors"}}
|
output-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea48deb514c69bf794ad38e0037e11c515338c1764bdf58fcc3671cff2b2d0aa
|
3 |
+
size 8584205128
|
output-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a01eb60f6354aed89d555efe92f6b09d098303c82280c8a8019d36e1a2ac80d5
|
3 |
+
size 8589762344
|
output-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa0b5823b486a00048e71c417420bb3fbaf4fb0a3ba327105093f7a89f2e13fc
|
3 |
+
size 3538636336
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|