Troy-Codes commited on
Commit
ecca1a6
·
verified ·
1 Parent(s): 6689bf5

BlackSheep

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,43 @@
1
- ---
2
- license: artistic-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # MoE-Evil
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the [Linear](https://arxiv.org/abs/2203.05482) merge method using examples/MoE-UAI as a base.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * examples/MoE-BASE_MOST_UNHINGED
22
+
23
+ ### Configuration
24
+
25
+ The following YAML configuration was used to produce this model:
26
+
27
+ ```yaml
28
+ models:
29
+ - model: examples/MoE-BASE_MOST_UNHINGED
30
+ parameters:
31
+ weight: 1
32
+ density: 1
33
+ merge_method: linear
34
+ base_model: examples/MoE-UAI
35
+ parameters:
36
+ weight: 1
37
+ density: 1
38
+ normalize: true
39
+ int8_mask: true
40
+ tokenizer_source: examples/MoE-UAI
41
+ dtype: bfloat16
42
+
43
+ ```
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "examples/MoE-UAI",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 40,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 4,
21
+ "output_router_logits": false,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_theta": 1000000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "router_jitter_noise": 0.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.48.3",
30
+ "use_cache": true,
31
+ "vocab_size": 131072
32
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: examples/MoE-BASE_MOST_UNHINGED
3
+ parameters:
4
+ weight: 1
5
+ density: 1
6
+ merge_method: linear
7
+ base_model: examples/MoE-UAI
8
+ parameters:
9
+ weight: 1
10
+ density: 1
11
+ normalize: true
12
+ int8_mask: true
13
+ tokenizer_source: examples/MoE-UAI
14
+ dtype: bfloat16
model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac55868b44f6ece0734256607d55805a60fa674e91637a3549b5f40a41ea9ab
3
+ size 4991286216
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b7982f3c6062a932e145667e69c1af08cf29e442323a6c624f7f82693e461c1
3
+ size 4907464440
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d05cfc5207cbd62578fb4fa1eee0771ab0d708a0e37bceaa03fa08466fe0b96c
3
+ size 4865583536
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f019e5c3e57da18768ae88e561d4cd81e84343455522fa6aa0690b93c4b82c3e
3
+ size 4865583536
model-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0830e342681af58d60dc45a7d6a457fbb0e9501ba362660a1cb53b8f37d2ae96
3
+ size 4907464456
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7539b0b1dd22906eaf7eb63ac89647b19774c6adcb4067725e70933a6c5c4260
3
+ size 4865583520
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68246c57f76dfca10fb35df2fe133bd2a2fcbacb0212a35378831535fee7155b
3
+ size 4959955288
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace0db2151470f264e24785441b8ee92778fb1afa1407ecbd53dad419d8c8b49
3
+ size 4959893488
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1ed1eaa63297c5e2b669039f4d3f4b48a9a014f8c782fd3c97ab2ad8a73192
3
+ size 4865583536
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db07d97cee3181d219f386e18b0cc53551839fa44f5ca719fc632a8126c18c98
3
+ size 4907464440
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727df015d681b121310ecc118185f684ab88d2bd7baf0bcd9d89c3fa4b24938a
3
+ size 4865583536
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb478f3ab65764942593be5ab10af08a30990f983e6fcb6a88f8a1df613a8d3
3
+ size 4865583536
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440ace58888862dca6a5f4fd13a2eb7b0eb11b5516a9860f04de081543517c93
3
+ size 4907464456
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881a57a475b0d950e8fc2bc5553889147a2a92b35b0ec37a7cf1c8189c1d5291
3
+ size 4865583512
model-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197c9de909c2aa760cd342ecf0f6b28295f3688122d1728016167672f7a5b3a2
3
+ size 4959955232
model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:081fa71766e42888035feeaf56b32108669d9472b973d7e478a2f7d15d2140b8
3
+ size 3785497600
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.1.0"}, "weight_map": {"lm_head.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00005-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00009-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00009-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00010-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00010-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00011-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00011-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00011-of-00016.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00012-of-00016.safetensors", "model.layers.33.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00012-of-00016.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00012-of-00016.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00013-of-00016.safetensors", "model.layers.36.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00013-of-00016.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00014-of-00016.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00014-of-00016.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00014-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00015-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00015-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00015-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a046b64b5eda8178d73f3a3b5c9ff1278e6c55b2ff2628dc20bee39b3371ab7
3
+ size 17078444
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff