Kquant03 commited on
Commit
fb07175
·
1 Parent(s): 5c1aba9

Upload 14 files

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CultriX/MistralTrix-v1",
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": 40,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 4,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.37.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: CultriX/MistralTrix-v1
2
+ gate_mode: hidden
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: CultriX/MistralTrix-v1
6
+ positive_prompts:
7
+ - "Fantasy"
8
+ - "Exciting"
9
+ - "Interesting"
10
+ - "Setting"
11
+ - "Landscape"
12
+ - "Fantastic"
13
+ - "Magical"
14
+ - "Storywriting"
15
+ - "Roleplay"
16
+ - "Fictional"
17
+ negative_prompts:
18
+ - "Realistic"
19
+ - "Nonfiction"
20
+ - "Historical"
21
+ - "Fact"
22
+ - "Factual"
23
+ - source_model: CultriX/MistralTrix-v1
24
+ positive_prompts:
25
+ - "Cock"
26
+ - "erection"
27
+ - "lips"
28
+ - "softly"
29
+ - "orgasm"
30
+ - "cum"
31
+ - "anal"
32
+ - "fingers"
33
+ - "slowly"
34
+ - "pussy"
35
+ - "closer"
36
+ negative_prompts:
37
+ - "classy"
38
+ - "reserved"
39
+ - "off-putting"
40
+ - "SFW"
41
+ - "Professional"
42
+ - "gross"
43
+ - "vague"
44
+ - "off-putting"
45
+ - "SFW"
46
+ - "appropriate"
47
+ - source_model: CultriX/MistralTrix-v1
48
+ positive_prompts:
49
+ - "Discuss"
50
+ - "Chat"
51
+ - "engaging"
52
+ - "stimulating"
53
+ - "intense"
54
+ - "information"
55
+ negative_prompts:
56
+ - "Sorry"
57
+ - "As an AI"
58
+ - "I cannot"
59
+ - "I am not capable"
60
+ - "this request"
61
+ - source_model: CultriX/MistralTrix-v1
62
+ positive_prompts:
63
+ - "pragmatic"
64
+ - "logical"
65
+ - "helpful"
66
+ - "descriptive"
67
+ - "intelligent"
68
+ - "masterful"
69
+ - "precise"
70
+ negative_prompts:
71
+ - "unhelpful"
72
+ - "inaccurate"
73
+ - "vague"
74
+ - "nondescript"
75
+ - "improper"
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f276ab14339a4b64814c485e885ea231657f92352e0c3ffc2b331e61942bfbbd
3
+ size 9919880136
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba93e4cc0b34f26183da208ca8c04af632a9d674a233717896447d7ba1e94ea
3
+ size 9982454752
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c1bd1a0141b365fdc71c25c7b02acfe44d9dcc45a084cb0785be5c03a5edfc
3
+ size 9982454720
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b690eb0872521106853f77aaa83c1b91bd01772c17b90eb1ce7390190885a8bf
3
+ size 9982454744
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8f35e9816d3b29c66485e26e57a14421c304dd4cf2c3528e06bedd277df9e4
3
+ size 9982454736
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b04cbd8290af51cc69f49deac790544151aa8ff16b372981f0a2632e89a2ed7
3
+ size 9999578480
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d672f538641d380257f6c75c3e5e5b30cc4699143b8a0fd4936d6512a84b524d
3
+ size 403969896
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.norm.weight": "model-00001-of-00007.safetensors", "lm_head.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": true,
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": "<s>",
41
+ "padding_side": "left",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "split_special_tokens": false,
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }