Hugging Face's logo

rpDungeon
/
scatterbrain-small-experimental

Safetensors
qwen3_moe
Model card Files
xet
 Community
ToastyPigeon commited on
Commit
626802d
·
verified ·
1 Parent(s): 5fb427b

Single MoE layer extracted from Qwen/Qwen3-30B-A3B-Instruct-2507 (layer 30)

Browse files
Files changed (14) hide show
  1. .gitattributes +3 -0
  2. cache/.locks/models--Qwen--Qwen3-30B-A3B-Instruct-2507/afe775cbdefb257e1bf1d8551fb930bd4b78d74da0b10bbb651f6b6a6f67c325.lock +0 -0
  3. cache/.locks/models--Qwen--Qwen3-30B-A3B-Instruct-2507/c2bc4101cde6b7c9dda36bbdff815c2ff19541d7732e94d306d87a0806c133b3.lock +0 -0
  4. cache/.locks/models--Qwen--Qwen3-30B-A3B-Instruct-2507/fa5623e55641935f938894cc91090732452ef22da12596e857c8dff4fa71627b.lock +0 -0
  5. cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/blobs/afe775cbdefb257e1bf1d8551fb930bd4b78d74da0b10bbb651f6b6a6f67c325 +3 -0
  6. cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/blobs/c2bc4101cde6b7c9dda36bbdff815c2ff19541d7732e94d306d87a0806c133b3 +3 -0
  7. cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/blobs/fa5623e55641935f938894cc91090732452ef22da12596e857c8dff4fa71627b +3 -0
  8. cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/refs/main +1 -0
  9. cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/snapshots/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe/model-00001-of-00016.safetensors +3 -0
  10. cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/snapshots/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe/model-00010-of-00016.safetensors +3 -0
  11. cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/snapshots/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe/model-00016-of-00016.safetensors +3 -0
  12. config.json +41 -0
  13. model.safetensors +3 -0
  14. model.safetensors.index.json +404 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
+ cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/blobs/afe775cbdefb257e1bf1d8551fb930bd4b78d74da0b10bbb651f6b6a6f67c325 filter=lfs diff=lfs merge=lfs -text
37
+ cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/blobs/c2bc4101cde6b7c9dda36bbdff815c2ff19541d7732e94d306d87a0806c133b3 filter=lfs diff=lfs merge=lfs -text
38
+ cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/blobs/fa5623e55641935f938894cc91090732452ef22da12596e857c8dff4fa71627b filter=lfs diff=lfs merge=lfs -text
cache/.locks/models--Qwen--Qwen3-30B-A3B-Instruct-2507/afe775cbdefb257e1bf1d8551fb930bd4b78d74da0b10bbb651f6b6a6f67c325.lock ADDED
File without changes
cache/.locks/models--Qwen--Qwen3-30B-A3B-Instruct-2507/c2bc4101cde6b7c9dda36bbdff815c2ff19541d7732e94d306d87a0806c133b3.lock ADDED
File without changes
cache/.locks/models--Qwen--Qwen3-30B-A3B-Instruct-2507/fa5623e55641935f938894cc91090732452ef22da12596e857c8dff4fa71627b.lock ADDED
File without changes
cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/blobs/afe775cbdefb257e1bf1d8551fb930bd4b78d74da0b10bbb651f6b6a6f67c325 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe775cbdefb257e1bf1d8551fb930bd4b78d74da0b10bbb651f6b6a6f67c325
3
+ size 3998893112
cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/blobs/c2bc4101cde6b7c9dda36bbdff815c2ff19541d7732e94d306d87a0806c133b3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bc4101cde6b7c9dda36bbdff815c2ff19541d7732e94d306d87a0806c133b3
3
+ size 3999975400
cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/blobs/fa5623e55641935f938894cc91090732452ef22da12596e857c8dff4fa71627b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa5623e55641935f938894cc91090732452ef22da12596e857c8dff4fa71627b
3
+ size 1085307128
cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/refs/main ADDED
@@ -0,0 +1 @@
 
 
1
+ 0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe
cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/snapshots/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe/model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe775cbdefb257e1bf1d8551fb930bd4b78d74da0b10bbb651f6b6a6f67c325
3
+ size 3998893112
cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/snapshots/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe/model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bc4101cde6b7c9dda36bbdff815c2ff19541d7732e94d306d87a0806c133b3
3
+ size 3999975400
cache/models--Qwen--Qwen3-30B-A3B-Instruct-2507/snapshots/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe/model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa5623e55641935f938894cc91090732452ef22da12596e857c8dff4fa71627b
3
+ size 1085307128
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "max_position_embeddings": 262144,
16
+ "max_window_layers": 48,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 768,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 32,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 1,
25
+ "num_key_value_heads": 4,
26
+ "output_router_logits": false,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000000,
30
+ "router_aux_loss_coef": 0.001,
31
+ "sliding_window": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.51.0",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936,
38
+ "_original_num_hidden_layers": 48,
39
+ "_extracted_from_layer": 30,
40
+ "_source_model": "Qwen/Qwen3-30B-A3B-Instruct-2507"
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98ee196bd24dd59e8b19be79e9c8e4c57add433acd5be25667e47f42898ce01a
3
+ size 2490953824
model.safetensors.index.json ADDED
@@ -0,0 +1,404 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1245452544,
4
+ "total_size": 2490905088
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
9
+ "model.layers.0.mlp.experts.0.down_proj.weight": "model.safetensors",
10
+ "model.layers.0.mlp.experts.0.gate_proj.weight": "model.safetensors",
11
+ "model.layers.0.mlp.experts.0.up_proj.weight": "model.safetensors",
12
+ "model.layers.0.mlp.experts.1.down_proj.weight": "model.safetensors",
13
+ "model.layers.0.mlp.experts.1.gate_proj.weight": "model.safetensors",
14
+ "model.layers.0.mlp.experts.1.up_proj.weight": "model.safetensors",
15
+ "model.layers.0.mlp.experts.10.down_proj.weight": "model.safetensors",
16
+ "model.layers.0.mlp.experts.10.gate_proj.weight": "model.safetensors",
17
+ "model.layers.0.mlp.experts.10.up_proj.weight": "model.safetensors",
18
+ "model.layers.0.mlp.experts.100.down_proj.weight": "model.safetensors",
19
+ "model.layers.0.mlp.experts.100.gate_proj.weight": "model.safetensors",
20
+ "model.layers.0.mlp.experts.100.up_proj.weight": "model.safetensors",
21
+ "model.layers.0.mlp.experts.101.down_proj.weight": "model.safetensors",
22
+ "model.layers.0.mlp.experts.101.gate_proj.weight": "model.safetensors",
23
+ "model.layers.0.mlp.experts.101.up_proj.weight": "model.safetensors",
24
+ "model.layers.0.mlp.experts.102.down_proj.weight": "model.safetensors",
25
+ "model.layers.0.mlp.experts.102.gate_proj.weight": "model.safetensors",
26
+ "model.layers.0.mlp.experts.102.up_proj.weight": "model.safetensors",
27
+ "model.layers.0.mlp.experts.103.down_proj.weight": "model.safetensors",
28
+ "model.layers.0.mlp.experts.103.gate_proj.weight": "model.safetensors",
29
+ "model.layers.0.mlp.experts.103.up_proj.weight": "model.safetensors",
30
+ "model.layers.0.mlp.experts.104.down_proj.weight": "model.safetensors",
31
+ "model.layers.0.mlp.experts.104.gate_proj.weight": "model.safetensors",
32
+ "model.layers.0.mlp.experts.104.up_proj.weight": "model.safetensors",
33
+ "model.layers.0.mlp.experts.105.down_proj.weight": "model.safetensors",
34
+ "model.layers.0.mlp.experts.105.gate_proj.weight": "model.safetensors",
35
+ "model.layers.0.mlp.experts.105.up_proj.weight": "model.safetensors",
36
+ "model.layers.0.mlp.experts.106.down_proj.weight": "model.safetensors",
37
+ "model.layers.0.mlp.experts.106.gate_proj.weight": "model.safetensors",
38
+ "model.layers.0.mlp.experts.106.up_proj.weight": "model.safetensors",
39
+ "model.layers.0.mlp.experts.107.down_proj.weight": "model.safetensors",
40
+ "model.layers.0.mlp.experts.107.gate_proj.weight": "model.safetensors",
41
+ "model.layers.0.mlp.experts.107.up_proj.weight": "model.safetensors",
42
+ "model.layers.0.mlp.experts.108.down_proj.weight": "model.safetensors",
43
+ "model.layers.0.mlp.experts.108.gate_proj.weight": "model.safetensors",
44
+ "model.layers.0.mlp.experts.108.up_proj.weight": "model.safetensors",
45
+ "model.layers.0.mlp.experts.109.down_proj.weight": "model.safetensors",
46
+ "model.layers.0.mlp.experts.109.gate_proj.weight": "model.safetensors",
47
+ "model.layers.0.mlp.experts.109.up_proj.weight": "model.safetensors",
48
+ "model.layers.0.mlp.experts.11.down_proj.weight": "model.safetensors",
49
+ "model.layers.0.mlp.experts.11.gate_proj.weight": "model.safetensors",
50
+ "model.layers.0.mlp.experts.11.up_proj.weight": "model.safetensors",
51
+ "model.layers.0.mlp.experts.110.down_proj.weight": "model.safetensors",
52
+ "model.layers.0.mlp.experts.110.gate_proj.weight": "model.safetensors",
53
+ "model.layers.0.mlp.experts.110.up_proj.weight": "model.safetensors",
54
+ "model.layers.0.mlp.experts.111.down_proj.weight": "model.safetensors",
55
+ "model.layers.0.mlp.experts.111.gate_proj.weight": "model.safetensors",
56
+ "model.layers.0.mlp.experts.111.up_proj.weight": "model.safetensors",
57
+ "model.layers.0.mlp.experts.112.down_proj.weight": "model.safetensors",
58
+ "model.layers.0.mlp.experts.112.gate_proj.weight": "model.safetensors",
59
+ "model.layers.0.mlp.experts.112.up_proj.weight": "model.safetensors",
60
+ "model.layers.0.mlp.experts.113.down_proj.weight": "model.safetensors",
61
+ "model.layers.0.mlp.experts.113.gate_proj.weight": "model.safetensors",
62
+ "model.layers.0.mlp.experts.113.up_proj.weight": "model.safetensors",
63
+ "model.layers.0.mlp.experts.114.down_proj.weight": "model.safetensors",
64
+ "model.layers.0.mlp.experts.114.gate_proj.weight": "model.safetensors",
65
+ "model.layers.0.mlp.experts.114.up_proj.weight": "model.safetensors",
66
+ "model.layers.0.mlp.experts.115.down_proj.weight": "model.safetensors",
67
+ "model.layers.0.mlp.experts.115.gate_proj.weight": "model.safetensors",
68
+ "model.layers.0.mlp.experts.115.up_proj.weight": "model.safetensors",
69
+ "model.layers.0.mlp.experts.116.down_proj.weight": "model.safetensors",
70
+ "model.layers.0.mlp.experts.116.gate_proj.weight": "model.safetensors",
71
+ "model.layers.0.mlp.experts.116.up_proj.weight": "model.safetensors",
72
+ "model.layers.0.mlp.experts.117.down_proj.weight": "model.safetensors",
73
+ "model.layers.0.mlp.experts.117.gate_proj.weight": "model.safetensors",
74
+ "model.layers.0.mlp.experts.117.up_proj.weight": "model.safetensors",
75
+ "model.layers.0.mlp.experts.118.down_proj.weight": "model.safetensors",
76
+ "model.layers.0.mlp.experts.118.gate_proj.weight": "model.safetensors",
77
+ "model.layers.0.mlp.experts.118.up_proj.weight": "model.safetensors",
78
+ "model.layers.0.mlp.experts.119.down_proj.weight": "model.safetensors",
79
+ "model.layers.0.mlp.experts.119.gate_proj.weight": "model.safetensors",
80
+ "model.layers.0.mlp.experts.119.up_proj.weight": "model.safetensors",
81
+ "model.layers.0.mlp.experts.12.down_proj.weight": "model.safetensors",
82
+ "model.layers.0.mlp.experts.12.gate_proj.weight": "model.safetensors",
83
+ "model.layers.0.mlp.experts.12.up_proj.weight": "model.safetensors",
84
+ "model.layers.0.mlp.experts.120.down_proj.weight": "model.safetensors",
85
+ "model.layers.0.mlp.experts.120.gate_proj.weight": "model.safetensors",
86
+ "model.layers.0.mlp.experts.120.up_proj.weight": "model.safetensors",
87
+ "model.layers.0.mlp.experts.121.down_proj.weight": "model.safetensors",
88
+ "model.layers.0.mlp.experts.121.gate_proj.weight": "model.safetensors",
89
+ "model.layers.0.mlp.experts.121.up_proj.weight": "model.safetensors",
90
+ "model.layers.0.mlp.experts.122.down_proj.weight": "model.safetensors",
91
+ "model.layers.0.mlp.experts.122.gate_proj.weight": "model.safetensors",
92
+ "model.layers.0.mlp.experts.122.up_proj.weight": "model.safetensors",
93
+ "model.layers.0.mlp.experts.123.down_proj.weight": "model.safetensors",
94
+ "model.layers.0.mlp.experts.123.gate_proj.weight": "model.safetensors",
95
+ "model.layers.0.mlp.experts.123.up_proj.weight": "model.safetensors",
96
+ "model.layers.0.mlp.experts.124.down_proj.weight": "model.safetensors",
97
+ "model.layers.0.mlp.experts.124.gate_proj.weight": "model.safetensors",
98
+ "model.layers.0.mlp.experts.124.up_proj.weight": "model.safetensors",
99
+ "model.layers.0.mlp.experts.125.down_proj.weight": "model.safetensors",
100
+ "model.layers.0.mlp.experts.125.gate_proj.weight": "model.safetensors",
101
+ "model.layers.0.mlp.experts.125.up_proj.weight": "model.safetensors",
102
+ "model.layers.0.mlp.experts.126.down_proj.weight": "model.safetensors",
103
+ "model.layers.0.mlp.experts.126.gate_proj.weight": "model.safetensors",
104
+ "model.layers.0.mlp.experts.126.up_proj.weight": "model.safetensors",
105
+ "model.layers.0.mlp.experts.127.down_proj.weight": "model.safetensors",
106
+ "model.layers.0.mlp.experts.127.gate_proj.weight": "model.safetensors",
107
+ "model.layers.0.mlp.experts.127.up_proj.weight": "model.safetensors",
108
+ "model.layers.0.mlp.experts.13.down_proj.weight": "model.safetensors",
109
+ "model.layers.0.mlp.experts.13.gate_proj.weight": "model.safetensors",
110
+ "model.layers.0.mlp.experts.13.up_proj.weight": "model.safetensors",
111
+ "model.layers.0.mlp.experts.14.down_proj.weight": "model.safetensors",
112
+ "model.layers.0.mlp.experts.14.gate_proj.weight": "model.safetensors",
113
+ "model.layers.0.mlp.experts.14.up_proj.weight": "model.safetensors",
114
+ "model.layers.0.mlp.experts.15.down_proj.weight": "model.safetensors",
115
+ "model.layers.0.mlp.experts.15.gate_proj.weight": "model.safetensors",
116
+ "model.layers.0.mlp.experts.15.up_proj.weight": "model.safetensors",
117
+ "model.layers.0.mlp.experts.16.down_proj.weight": "model.safetensors",
118
+ "model.layers.0.mlp.experts.16.gate_proj.weight": "model.safetensors",
119
+ "model.layers.0.mlp.experts.16.up_proj.weight": "model.safetensors",
120
+ "model.layers.0.mlp.experts.17.down_proj.weight": "model.safetensors",
121
+ "model.layers.0.mlp.experts.17.gate_proj.weight": "model.safetensors",
122
+ "model.layers.0.mlp.experts.17.up_proj.weight": "model.safetensors",
123
+ "model.layers.0.mlp.experts.18.down_proj.weight": "model.safetensors",
124
+ "model.layers.0.mlp.experts.18.gate_proj.weight": "model.safetensors",
125
+ "model.layers.0.mlp.experts.18.up_proj.weight": "model.safetensors",
126
+ "model.layers.0.mlp.experts.19.down_proj.weight": "model.safetensors",
127
+ "model.layers.0.mlp.experts.19.gate_proj.weight": "model.safetensors",
128
+ "model.layers.0.mlp.experts.19.up_proj.weight": "model.safetensors",
129
+ "model.layers.0.mlp.experts.2.down_proj.weight": "model.safetensors",
130
+ "model.layers.0.mlp.experts.2.gate_proj.weight": "model.safetensors",
131
+ "model.layers.0.mlp.experts.2.up_proj.weight": "model.safetensors",
132
+ "model.layers.0.mlp.experts.20.down_proj.weight": "model.safetensors",
133
+ "model.layers.0.mlp.experts.20.gate_proj.weight": "model.safetensors",
134
+ "model.layers.0.mlp.experts.20.up_proj.weight": "model.safetensors",
135
+ "model.layers.0.mlp.experts.21.down_proj.weight": "model.safetensors",
136
+ "model.layers.0.mlp.experts.21.gate_proj.weight": "model.safetensors",
137
+ "model.layers.0.mlp.experts.21.up_proj.weight": "model.safetensors",
138
+ "model.layers.0.mlp.experts.22.down_proj.weight": "model.safetensors",
139
+ "model.layers.0.mlp.experts.22.gate_proj.weight": "model.safetensors",
140
+ "model.layers.0.mlp.experts.22.up_proj.weight": "model.safetensors",
141
+ "model.layers.0.mlp.experts.23.down_proj.weight": "model.safetensors",
142
+ "model.layers.0.mlp.experts.23.gate_proj.weight": "model.safetensors",
143
+ "model.layers.0.mlp.experts.23.up_proj.weight": "model.safetensors",
144
+ "model.layers.0.mlp.experts.24.down_proj.weight": "model.safetensors",
145
+ "model.layers.0.mlp.experts.24.gate_proj.weight": "model.safetensors",
146
+ "model.layers.0.mlp.experts.24.up_proj.weight": "model.safetensors",
147
+ "model.layers.0.mlp.experts.25.down_proj.weight": "model.safetensors",
148
+ "model.layers.0.mlp.experts.25.gate_proj.weight": "model.safetensors",
149
+ "model.layers.0.mlp.experts.25.up_proj.weight": "model.safetensors",
150
+ "model.layers.0.mlp.experts.26.down_proj.weight": "model.safetensors",
151
+ "model.layers.0.mlp.experts.26.gate_proj.weight": "model.safetensors",
152
+ "model.layers.0.mlp.experts.26.up_proj.weight": "model.safetensors",
153
+ "model.layers.0.mlp.experts.27.down_proj.weight": "model.safetensors",
154
+ "model.layers.0.mlp.experts.27.gate_proj.weight": "model.safetensors",
155
+ "model.layers.0.mlp.experts.27.up_proj.weight": "model.safetensors",
156
+ "model.layers.0.mlp.experts.28.down_proj.weight": "model.safetensors",
157
+ "model.layers.0.mlp.experts.28.gate_proj.weight": "model.safetensors",
158
+ "model.layers.0.mlp.experts.28.up_proj.weight": "model.safetensors",
159
+ "model.layers.0.mlp.experts.29.down_proj.weight": "model.safetensors",
160
+ "model.layers.0.mlp.experts.29.gate_proj.weight": "model.safetensors",
161
+ "model.layers.0.mlp.experts.29.up_proj.weight": "model.safetensors",
162
+ "model.layers.0.mlp.experts.3.down_proj.weight": "model.safetensors",
163
+ "model.layers.0.mlp.experts.3.gate_proj.weight": "model.safetensors",
164
+ "model.layers.0.mlp.experts.3.up_proj.weight": "model.safetensors",
165
+ "model.layers.0.mlp.experts.30.down_proj.weight": "model.safetensors",
166
+ "model.layers.0.mlp.experts.30.gate_proj.weight": "model.safetensors",
167
+ "model.layers.0.mlp.experts.30.up_proj.weight": "model.safetensors",
168
+ "model.layers.0.mlp.experts.31.down_proj.weight": "model.safetensors",
169
+ "model.layers.0.mlp.experts.31.gate_proj.weight": "model.safetensors",
170
+ "model.layers.0.mlp.experts.31.up_proj.weight": "model.safetensors",
171
+ "model.layers.0.mlp.experts.32.down_proj.weight": "model.safetensors",
172
+ "model.layers.0.mlp.experts.32.gate_proj.weight": "model.safetensors",
173
+ "model.layers.0.mlp.experts.32.up_proj.weight": "model.safetensors",
174
+ "model.layers.0.mlp.experts.33.down_proj.weight": "model.safetensors",
175
+ "model.layers.0.mlp.experts.33.gate_proj.weight": "model.safetensors",
176
+ "model.layers.0.mlp.experts.33.up_proj.weight": "model.safetensors",
177
+ "model.layers.0.mlp.experts.34.down_proj.weight": "model.safetensors",
178
+ "model.layers.0.mlp.experts.34.gate_proj.weight": "model.safetensors",
179
+ "model.layers.0.mlp.experts.34.up_proj.weight": "model.safetensors",
180
+ "model.layers.0.mlp.experts.35.down_proj.weight": "model.safetensors",
181
+ "model.layers.0.mlp.experts.35.gate_proj.weight": "model.safetensors",
182
+ "model.layers.0.mlp.experts.35.up_proj.weight": "model.safetensors",
183
+ "model.layers.0.mlp.experts.36.down_proj.weight": "model.safetensors",
184
+ "model.layers.0.mlp.experts.36.gate_proj.weight": "model.safetensors",
185
+ "model.layers.0.mlp.experts.36.up_proj.weight": "model.safetensors",
186
+ "model.layers.0.mlp.experts.37.down_proj.weight": "model.safetensors",
187
+ "model.layers.0.mlp.experts.37.gate_proj.weight": "model.safetensors",
188
+ "model.layers.0.mlp.experts.37.up_proj.weight": "model.safetensors",
189
+ "model.layers.0.mlp.experts.38.down_proj.weight": "model.safetensors",
190
+ "model.layers.0.mlp.experts.38.gate_proj.weight": "model.safetensors",
191
+ "model.layers.0.mlp.experts.38.up_proj.weight": "model.safetensors",
192
+ "model.layers.0.mlp.experts.39.down_proj.weight": "model.safetensors",
193
+ "model.layers.0.mlp.experts.39.gate_proj.weight": "model.safetensors",
194
+ "model.layers.0.mlp.experts.39.up_proj.weight": "model.safetensors",
195
+ "model.layers.0.mlp.experts.4.down_proj.weight": "model.safetensors",
196
+ "model.layers.0.mlp.experts.4.gate_proj.weight": "model.safetensors",
197
+ "model.layers.0.mlp.experts.4.up_proj.weight": "model.safetensors",
198
+ "model.layers.0.mlp.experts.40.down_proj.weight": "model.safetensors",
199
+ "model.layers.0.mlp.experts.40.gate_proj.weight": "model.safetensors",
200
+ "model.layers.0.mlp.experts.40.up_proj.weight": "model.safetensors",
201
+ "model.layers.0.mlp.experts.41.down_proj.weight": "model.safetensors",
202
+ "model.layers.0.mlp.experts.41.gate_proj.weight": "model.safetensors",
203
+ "model.layers.0.mlp.experts.41.up_proj.weight": "model.safetensors",
204
+ "model.layers.0.mlp.experts.42.down_proj.weight": "model.safetensors",
205
+ "model.layers.0.mlp.experts.42.gate_proj.weight": "model.safetensors",
206
+ "model.layers.0.mlp.experts.42.up_proj.weight": "model.safetensors",
207
+ "model.layers.0.mlp.experts.43.down_proj.weight": "model.safetensors",
208
+ "model.layers.0.mlp.experts.43.gate_proj.weight": "model.safetensors",
209
+ "model.layers.0.mlp.experts.43.up_proj.weight": "model.safetensors",
210
+ "model.layers.0.mlp.experts.44.down_proj.weight": "model.safetensors",
211
+ "model.layers.0.mlp.experts.44.gate_proj.weight": "model.safetensors",
212
+ "model.layers.0.mlp.experts.44.up_proj.weight": "model.safetensors",
213
+ "model.layers.0.mlp.experts.45.down_proj.weight": "model.safetensors",
214
+ "model.layers.0.mlp.experts.45.gate_proj.weight": "model.safetensors",
215
+ "model.layers.0.mlp.experts.45.up_proj.weight": "model.safetensors",
216
+ "model.layers.0.mlp.experts.46.down_proj.weight": "model.safetensors",
217
+ "model.layers.0.mlp.experts.46.gate_proj.weight": "model.safetensors",
218
+ "model.layers.0.mlp.experts.46.up_proj.weight": "model.safetensors",
219
+ "model.layers.0.mlp.experts.47.down_proj.weight": "model.safetensors",
220
+ "model.layers.0.mlp.experts.47.gate_proj.weight": "model.safetensors",
221
+ "model.layers.0.mlp.experts.47.up_proj.weight": "model.safetensors",
222
+ "model.layers.0.mlp.experts.48.down_proj.weight": "model.safetensors",
223
+ "model.layers.0.mlp.experts.48.gate_proj.weight": "model.safetensors",
224
+ "model.layers.0.mlp.experts.48.up_proj.weight": "model.safetensors",
225
+ "model.layers.0.mlp.experts.49.down_proj.weight": "model.safetensors",
226
+ "model.layers.0.mlp.experts.49.gate_proj.weight": "model.safetensors",
227
+ "model.layers.0.mlp.experts.49.up_proj.weight": "model.safetensors",
228
+ "model.layers.0.mlp.experts.5.down_proj.weight": "model.safetensors",
229
+ "model.layers.0.mlp.experts.5.gate_proj.weight": "model.safetensors",
230
+ "model.layers.0.mlp.experts.5.up_proj.weight": "model.safetensors",
231
+ "model.layers.0.mlp.experts.50.down_proj.weight": "model.safetensors",
232
+ "model.layers.0.mlp.experts.50.gate_proj.weight": "model.safetensors",
233
+ "model.layers.0.mlp.experts.50.up_proj.weight": "model.safetensors",
234
+ "model.layers.0.mlp.experts.51.down_proj.weight": "model.safetensors",
235
+ "model.layers.0.mlp.experts.51.gate_proj.weight": "model.safetensors",
236
+ "model.layers.0.mlp.experts.51.up_proj.weight": "model.safetensors",
237
+ "model.layers.0.mlp.experts.52.down_proj.weight": "model.safetensors",
238
+ "model.layers.0.mlp.experts.52.gate_proj.weight": "model.safetensors",
239
+ "model.layers.0.mlp.experts.52.up_proj.weight": "model.safetensors",
240
+ "model.layers.0.mlp.experts.53.down_proj.weight": "model.safetensors",
241
+ "model.layers.0.mlp.experts.53.gate_proj.weight": "model.safetensors",
242
+ "model.layers.0.mlp.experts.53.up_proj.weight": "model.safetensors",
243
+ "model.layers.0.mlp.experts.54.down_proj.weight": "model.safetensors",
244
+ "model.layers.0.mlp.experts.54.gate_proj.weight": "model.safetensors",
245
+ "model.layers.0.mlp.experts.54.up_proj.weight": "model.safetensors",
246
+ "model.layers.0.mlp.experts.55.down_proj.weight": "model.safetensors",
247
+ "model.layers.0.mlp.experts.55.gate_proj.weight": "model.safetensors",
248
+ "model.layers.0.mlp.experts.55.up_proj.weight": "model.safetensors",
249
+ "model.layers.0.mlp.experts.56.down_proj.weight": "model.safetensors",
250
+ "model.layers.0.mlp.experts.56.gate_proj.weight": "model.safetensors",
251
+ "model.layers.0.mlp.experts.56.up_proj.weight": "model.safetensors",
252
+ "model.layers.0.mlp.experts.57.down_proj.weight": "model.safetensors",
253
+ "model.layers.0.mlp.experts.57.gate_proj.weight": "model.safetensors",
254
+ "model.layers.0.mlp.experts.57.up_proj.weight": "model.safetensors",
255
+ "model.layers.0.mlp.experts.58.down_proj.weight": "model.safetensors",
256
+ "model.layers.0.mlp.experts.58.gate_proj.weight": "model.safetensors",
257
+ "model.layers.0.mlp.experts.58.up_proj.weight": "model.safetensors",
258
+ "model.layers.0.mlp.experts.59.down_proj.weight": "model.safetensors",
259
+ "model.layers.0.mlp.experts.59.gate_proj.weight": "model.safetensors",
260
+ "model.layers.0.mlp.experts.59.up_proj.weight": "model.safetensors",
261
+ "model.layers.0.mlp.experts.6.down_proj.weight": "model.safetensors",
262
+ "model.layers.0.mlp.experts.6.gate_proj.weight": "model.safetensors",
263
+ "model.layers.0.mlp.experts.6.up_proj.weight": "model.safetensors",
264
+ "model.layers.0.mlp.experts.60.down_proj.weight": "model.safetensors",
265
+ "model.layers.0.mlp.experts.60.gate_proj.weight": "model.safetensors",
266
+ "model.layers.0.mlp.experts.60.up_proj.weight": "model.safetensors",
267
+ "model.layers.0.mlp.experts.61.down_proj.weight": "model.safetensors",
268
+ "model.layers.0.mlp.experts.61.gate_proj.weight": "model.safetensors",
269
+ "model.layers.0.mlp.experts.61.up_proj.weight": "model.safetensors",
270
+ "model.layers.0.mlp.experts.62.down_proj.weight": "model.safetensors",
271
+ "model.layers.0.mlp.experts.62.gate_proj.weight": "model.safetensors",
272
+ "model.layers.0.mlp.experts.62.up_proj.weight": "model.safetensors",
273
+ "model.layers.0.mlp.experts.63.down_proj.weight": "model.safetensors",
274
+ "model.layers.0.mlp.experts.63.gate_proj.weight": "model.safetensors",
275
+ "model.layers.0.mlp.experts.63.up_proj.weight": "model.safetensors",
276
+ "model.layers.0.mlp.experts.64.down_proj.weight": "model.safetensors",
277
+ "model.layers.0.mlp.experts.64.gate_proj.weight": "model.safetensors",
278
+ "model.layers.0.mlp.experts.64.up_proj.weight": "model.safetensors",
279
+ "model.layers.0.mlp.experts.65.down_proj.weight": "model.safetensors",
280
+ "model.layers.0.mlp.experts.65.gate_proj.weight": "model.safetensors",
281
+ "model.layers.0.mlp.experts.65.up_proj.weight": "model.safetensors",
282
+ "model.layers.0.mlp.experts.66.down_proj.weight": "model.safetensors",
283
+ "model.layers.0.mlp.experts.66.gate_proj.weight": "model.safetensors",
284
+ "model.layers.0.mlp.experts.66.up_proj.weight": "model.safetensors",
285
+ "model.layers.0.mlp.experts.67.down_proj.weight": "model.safetensors",
286
+ "model.layers.0.mlp.experts.67.gate_proj.weight": "model.safetensors",
287
+ "model.layers.0.mlp.experts.67.up_proj.weight": "model.safetensors",
288
+ "model.layers.0.mlp.experts.68.down_proj.weight": "model.safetensors",
289
+ "model.layers.0.mlp.experts.68.gate_proj.weight": "model.safetensors",
290
+ "model.layers.0.mlp.experts.68.up_proj.weight": "model.safetensors",
291
+ "model.layers.0.mlp.experts.69.down_proj.weight": "model.safetensors",
292
+ "model.layers.0.mlp.experts.69.gate_proj.weight": "model.safetensors",
293
+ "model.layers.0.mlp.experts.69.up_proj.weight": "model.safetensors",
294
+ "model.layers.0.mlp.experts.7.down_proj.weight": "model.safetensors",
295
+ "model.layers.0.mlp.experts.7.gate_proj.weight": "model.safetensors",
296
+ "model.layers.0.mlp.experts.7.up_proj.weight": "model.safetensors",
297
+ "model.layers.0.mlp.experts.70.down_proj.weight": "model.safetensors",
298
+ "model.layers.0.mlp.experts.70.gate_proj.weight": "model.safetensors",
299
+ "model.layers.0.mlp.experts.70.up_proj.weight": "model.safetensors",
300
+ "model.layers.0.mlp.experts.71.down_proj.weight": "model.safetensors",
301
+ "model.layers.0.mlp.experts.71.gate_proj.weight": "model.safetensors",
302
+ "model.layers.0.mlp.experts.71.up_proj.weight": "model.safetensors",
303
+ "model.layers.0.mlp.experts.72.down_proj.weight": "model.safetensors",
304
+ "model.layers.0.mlp.experts.72.gate_proj.weight": "model.safetensors",
305
+ "model.layers.0.mlp.experts.72.up_proj.weight": "model.safetensors",
306
+ "model.layers.0.mlp.experts.73.down_proj.weight": "model.safetensors",
307
+ "model.layers.0.mlp.experts.73.gate_proj.weight": "model.safetensors",
308
+ "model.layers.0.mlp.experts.73.up_proj.weight": "model.safetensors",
309
+ "model.layers.0.mlp.experts.74.down_proj.weight": "model.safetensors",
310
+ "model.layers.0.mlp.experts.74.gate_proj.weight": "model.safetensors",
311
+ "model.layers.0.mlp.experts.74.up_proj.weight": "model.safetensors",
312
+ "model.layers.0.mlp.experts.75.down_proj.weight": "model.safetensors",
313
+ "model.layers.0.mlp.experts.75.gate_proj.weight": "model.safetensors",
314
+ "model.layers.0.mlp.experts.75.up_proj.weight": "model.safetensors",
315
+ "model.layers.0.mlp.experts.76.down_proj.weight": "model.safetensors",
316
+ "model.layers.0.mlp.experts.76.gate_proj.weight": "model.safetensors",
317
+ "model.layers.0.mlp.experts.76.up_proj.weight": "model.safetensors",
318
+ "model.layers.0.mlp.experts.77.down_proj.weight": "model.safetensors",
319
+ "model.layers.0.mlp.experts.77.gate_proj.weight": "model.safetensors",
320
+ "model.layers.0.mlp.experts.77.up_proj.weight": "model.safetensors",
321
+ "model.layers.0.mlp.experts.78.down_proj.weight": "model.safetensors",
322
+ "model.layers.0.mlp.experts.78.gate_proj.weight": "model.safetensors",
323
+ "model.layers.0.mlp.experts.78.up_proj.weight": "model.safetensors",
324
+ "model.layers.0.mlp.experts.79.down_proj.weight": "model.safetensors",
325
+ "model.layers.0.mlp.experts.79.gate_proj.weight": "model.safetensors",
326
+ "model.layers.0.mlp.experts.79.up_proj.weight": "model.safetensors",
327
+ "model.layers.0.mlp.experts.8.down_proj.weight": "model.safetensors",
328
+ "model.layers.0.mlp.experts.8.gate_proj.weight": "model.safetensors",
329
+ "model.layers.0.mlp.experts.8.up_proj.weight": "model.safetensors",
330
+ "model.layers.0.mlp.experts.80.down_proj.weight": "model.safetensors",
331
+ "model.layers.0.mlp.experts.80.gate_proj.weight": "model.safetensors",
332
+ "model.layers.0.mlp.experts.80.up_proj.weight": "model.safetensors",
333
+ "model.layers.0.mlp.experts.81.down_proj.weight": "model.safetensors",
334
+ "model.layers.0.mlp.experts.81.gate_proj.weight": "model.safetensors",
335
+ "model.layers.0.mlp.experts.81.up_proj.weight": "model.safetensors",
336
+ "model.layers.0.mlp.experts.82.down_proj.weight": "model.safetensors",
337
+ "model.layers.0.mlp.experts.82.gate_proj.weight": "model.safetensors",
338
+ "model.layers.0.mlp.experts.82.up_proj.weight": "model.safetensors",
339
+ "model.layers.0.mlp.experts.83.down_proj.weight": "model.safetensors",
340
+ "model.layers.0.mlp.experts.83.gate_proj.weight": "model.safetensors",
341
+ "model.layers.0.mlp.experts.83.up_proj.weight": "model.safetensors",
342
+ "model.layers.0.mlp.experts.84.down_proj.weight": "model.safetensors",
343
+ "model.layers.0.mlp.experts.84.gate_proj.weight": "model.safetensors",
344
+ "model.layers.0.mlp.experts.84.up_proj.weight": "model.safetensors",
345
+ "model.layers.0.mlp.experts.85.down_proj.weight": "model.safetensors",
346
+ "model.layers.0.mlp.experts.85.gate_proj.weight": "model.safetensors",
347
+ "model.layers.0.mlp.experts.85.up_proj.weight": "model.safetensors",
348
+ "model.layers.0.mlp.experts.86.down_proj.weight": "model.safetensors",
349
+ "model.layers.0.mlp.experts.86.gate_proj.weight": "model.safetensors",
350
+ "model.layers.0.mlp.experts.86.up_proj.weight": "model.safetensors",
351
+ "model.layers.0.mlp.experts.87.down_proj.weight": "model.safetensors",
352
+ "model.layers.0.mlp.experts.87.gate_proj.weight": "model.safetensors",
353
+ "model.layers.0.mlp.experts.87.up_proj.weight": "model.safetensors",
354
+ "model.layers.0.mlp.experts.88.down_proj.weight": "model.safetensors",
355
+ "model.layers.0.mlp.experts.88.gate_proj.weight": "model.safetensors",
356
+ "model.layers.0.mlp.experts.88.up_proj.weight": "model.safetensors",
357
+ "model.layers.0.mlp.experts.89.down_proj.weight": "model.safetensors",
358
+ "model.layers.0.mlp.experts.89.gate_proj.weight": "model.safetensors",
359
+ "model.layers.0.mlp.experts.89.up_proj.weight": "model.safetensors",
360
+ "model.layers.0.mlp.experts.9.down_proj.weight": "model.safetensors",
361
+ "model.layers.0.mlp.experts.9.gate_proj.weight": "model.safetensors",
362
+ "model.layers.0.mlp.experts.9.up_proj.weight": "model.safetensors",
363
+ "model.layers.0.mlp.experts.90.down_proj.weight": "model.safetensors",
364
+ "model.layers.0.mlp.experts.90.gate_proj.weight": "model.safetensors",
365
+ "model.layers.0.mlp.experts.90.up_proj.weight": "model.safetensors",
366
+ "model.layers.0.mlp.experts.91.down_proj.weight": "model.safetensors",
367
+ "model.layers.0.mlp.experts.91.gate_proj.weight": "model.safetensors",
368
+ "model.layers.0.mlp.experts.91.up_proj.weight": "model.safetensors",
369
+ "model.layers.0.mlp.experts.92.down_proj.weight": "model.safetensors",
370
+ "model.layers.0.mlp.experts.92.gate_proj.weight": "model.safetensors",
371
+ "model.layers.0.mlp.experts.92.up_proj.weight": "model.safetensors",
372
+ "model.layers.0.mlp.experts.93.down_proj.weight": "model.safetensors",
373
+ "model.layers.0.mlp.experts.93.gate_proj.weight": "model.safetensors",
374
+ "model.layers.0.mlp.experts.93.up_proj.weight": "model.safetensors",
375
+ "model.layers.0.mlp.experts.94.down_proj.weight": "model.safetensors",
376
+ "model.layers.0.mlp.experts.94.gate_proj.weight": "model.safetensors",
377
+ "model.layers.0.mlp.experts.94.up_proj.weight": "model.safetensors",
378
+ "model.layers.0.mlp.experts.95.down_proj.weight": "model.safetensors",
379
+ "model.layers.0.mlp.experts.95.gate_proj.weight": "model.safetensors",
380
+ "model.layers.0.mlp.experts.95.up_proj.weight": "model.safetensors",
381
+ "model.layers.0.mlp.experts.96.down_proj.weight": "model.safetensors",
382
+ "model.layers.0.mlp.experts.96.gate_proj.weight": "model.safetensors",
383
+ "model.layers.0.mlp.experts.96.up_proj.weight": "model.safetensors",
384
+ "model.layers.0.mlp.experts.97.down_proj.weight": "model.safetensors",
385
+ "model.layers.0.mlp.experts.97.gate_proj.weight": "model.safetensors",
386
+ "model.layers.0.mlp.experts.97.up_proj.weight": "model.safetensors",
387
+ "model.layers.0.mlp.experts.98.down_proj.weight": "model.safetensors",
388
+ "model.layers.0.mlp.experts.98.gate_proj.weight": "model.safetensors",
389
+ "model.layers.0.mlp.experts.98.up_proj.weight": "model.safetensors",
390
+ "model.layers.0.mlp.experts.99.down_proj.weight": "model.safetensors",
391
+ "model.layers.0.mlp.experts.99.gate_proj.weight": "model.safetensors",
392
+ "model.layers.0.mlp.experts.99.up_proj.weight": "model.safetensors",
393
+ "model.layers.0.mlp.gate.weight": "model.safetensors",
394
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
395
+ "model.layers.0.self_attn.k_norm.weight": "model.safetensors",
396
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
397
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
398
+ "model.layers.0.self_attn.q_norm.weight": "model.safetensors",
399
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
400
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
401
+ "lm_head.weight": "model.safetensors",
402
+ "model.norm.weight": "model.safetensors"
403
+ }
404
+ }