Hugging Face's logo

omunaman
/
Open_Source_GPT_OSS_20B

Text Generation
Transformers
Safetensors
gpt_oss_like
gpt-oss
replication
20b
tinystories
FSDP
Model card Files
xet
 Community
omunaman commited on
Commit
ace7482
·
verified ·
1 Parent(s): e8c231b

Upload folder using huggingface_hub

Browse files
Files changed (31) hide show
  1. .ipynb_checkpoints/README_EXPORT-checkpoint.md +7 -0
  2. .ipynb_checkpoints/config-checkpoint.json +16 -0
  3. .ipynb_checkpoints/model.safetensors.index-checkpoint.json +418 -0
  4. README_EXPORT.md +7 -0
  5. config.json +16 -0
  6. model.safetensors.index.json +418 -0
  7. pytorch_model-00001-of-00025.safetensors +3 -0
  8. pytorch_model-00002-of-00025.safetensors +3 -0
  9. pytorch_model-00003-of-00025.safetensors +3 -0
  10. pytorch_model-00004-of-00025.safetensors +3 -0
  11. pytorch_model-00005-of-00025.safetensors +3 -0
  12. pytorch_model-00006-of-00025.safetensors +3 -0
  13. pytorch_model-00007-of-00025.safetensors +3 -0
  14. pytorch_model-00008-of-00025.safetensors +3 -0
  15. pytorch_model-00009-of-00025.safetensors +3 -0
  16. pytorch_model-00010-of-00025.safetensors +3 -0
  17. pytorch_model-00011-of-00025.safetensors +3 -0
  18. pytorch_model-00012-of-00025.safetensors +3 -0
  19. pytorch_model-00013-of-00025.safetensors +3 -0
  20. pytorch_model-00014-of-00025.safetensors +3 -0
  21. pytorch_model-00015-of-00025.safetensors +3 -0
  22. pytorch_model-00016-of-00025.safetensors +3 -0
  23. pytorch_model-00017-of-00025.safetensors +3 -0
  24. pytorch_model-00018-of-00025.safetensors +3 -0
  25. pytorch_model-00019-of-00025.safetensors +3 -0
  26. pytorch_model-00020-of-00025.safetensors +3 -0
  27. pytorch_model-00021-of-00025.safetensors +3 -0
  28. pytorch_model-00022-of-00025.safetensors +3 -0
  29. pytorch_model-00023-of-00025.safetensors +3 -0
  30. pytorch_model-00024-of-00025.safetensors +3 -0
  31. pytorch_model-00025-of-00025.safetensors +3 -0
.ipynb_checkpoints/README_EXPORT-checkpoint.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ # Exported Weights
2
+
3
+ - Source shards: out-20b-h200-stable/ckpt_rankXXXXX.pt
4
+ - Iteration: 1900
5
+ - Tokenizer hint: o200k_harmony
6
+ - max_shard_size: 5GB
7
+ - Generated: 2025-09-03T11:47:03.182090
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "gpt_oss_like",
3
+ "vocab_size": 201088,
4
+ "hidden_size": 2880,
5
+ "num_hidden_layers": 24,
6
+ "num_attention_heads": 64,
7
+ "num_key_value_heads": 8,
8
+ "max_position_embeddings": 131072,
9
+ "rms_norm_eps": 1e-05,
10
+ "rope_theta": 150000.0,
11
+ "attention_bias": true,
12
+ "tie_word_embeddings": false,
13
+ "sliding_window": 128,
14
+ "torch_dtype": "bfloat16",
15
+ "eos_token_id": null
16
+ }
.ipynb_checkpoints/model.safetensors.index-checkpoint.json ADDED
@@ -0,0 +1,418 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 83659028736
4
+ },
5
+ "weight_map": {
6
+ "embed.weight": "pytorch_model-00001-of-00025.safetensors",
7
+ "layers.0.norm1.weight": "pytorch_model-00001-of-00025.safetensors",
8
+ "layers.0.attn.sink_logit": "pytorch_model-00001-of-00025.safetensors",
9
+ "layers.0.attn.q.weight": "pytorch_model-00001-of-00025.safetensors",
10
+ "layers.0.attn.q.bias": "pytorch_model-00001-of-00025.safetensors",
11
+ "layers.0.attn.k.weight": "pytorch_model-00001-of-00025.safetensors",
12
+ "layers.0.attn.k.bias": "pytorch_model-00001-of-00025.safetensors",
13
+ "layers.0.attn.v.weight": "pytorch_model-00001-of-00025.safetensors",
14
+ "layers.0.attn.v.bias": "pytorch_model-00001-of-00025.safetensors",
15
+ "layers.0.attn.o.weight": "pytorch_model-00001-of-00025.safetensors",
16
+ "layers.0.attn.o.bias": "pytorch_model-00001-of-00025.safetensors",
17
+ "layers.0.norm2.weight": "pytorch_model-00001-of-00025.safetensors",
18
+ "layers.0.moe.W_in": "pytorch_model-00001-of-00025.safetensors",
19
+ "layers.0.moe.b_in": "pytorch_model-00001-of-00025.safetensors",
20
+ "layers.0.moe.W_out": "pytorch_model-00002-of-00025.safetensors",
21
+ "layers.0.moe.b_out": "pytorch_model-00002-of-00025.safetensors",
22
+ "layers.0.moe.router.weight": "pytorch_model-00002-of-00025.safetensors",
23
+ "layers.0.moe.router.bias": "pytorch_model-00002-of-00025.safetensors",
24
+ "layers.1.norm1.weight": "pytorch_model-00002-of-00025.safetensors",
25
+ "layers.1.attn.sink_logit": "pytorch_model-00002-of-00025.safetensors",
26
+ "layers.1.attn.q.weight": "pytorch_model-00002-of-00025.safetensors",
27
+ "layers.1.attn.q.bias": "pytorch_model-00002-of-00025.safetensors",
28
+ "layers.1.attn.k.weight": "pytorch_model-00002-of-00025.safetensors",
29
+ "layers.1.attn.k.bias": "pytorch_model-00002-of-00025.safetensors",
30
+ "layers.1.attn.v.weight": "pytorch_model-00002-of-00025.safetensors",
31
+ "layers.1.attn.v.bias": "pytorch_model-00002-of-00025.safetensors",
32
+ "layers.1.attn.o.weight": "pytorch_model-00002-of-00025.safetensors",
33
+ "layers.1.attn.o.bias": "pytorch_model-00002-of-00025.safetensors",
34
+ "layers.1.norm2.weight": "pytorch_model-00002-of-00025.safetensors",
35
+ "layers.1.moe.W_in": "pytorch_model-00002-of-00025.safetensors",
36
+ "layers.1.moe.b_in": "pytorch_model-00002-of-00025.safetensors",
37
+ "layers.1.moe.W_out": "pytorch_model-00002-of-00025.safetensors",
38
+ "layers.1.moe.b_out": "pytorch_model-00002-of-00025.safetensors",
39
+ "layers.1.moe.router.weight": "pytorch_model-00002-of-00025.safetensors",
40
+ "layers.1.moe.router.bias": "pytorch_model-00002-of-00025.safetensors",
41
+ "layers.2.norm1.weight": "pytorch_model-00002-of-00025.safetensors",
42
+ "layers.2.attn.sink_logit": "pytorch_model-00002-of-00025.safetensors",
43
+ "layers.2.attn.q.weight": "pytorch_model-00002-of-00025.safetensors",
44
+ "layers.2.attn.q.bias": "pytorch_model-00002-of-00025.safetensors",
45
+ "layers.2.attn.k.weight": "pytorch_model-00002-of-00025.safetensors",
46
+ "layers.2.attn.k.bias": "pytorch_model-00002-of-00025.safetensors",
47
+ "layers.2.attn.v.weight": "pytorch_model-00002-of-00025.safetensors",
48
+ "layers.2.attn.v.bias": "pytorch_model-00002-of-00025.safetensors",
49
+ "layers.2.attn.o.weight": "pytorch_model-00002-of-00025.safetensors",
50
+ "layers.2.attn.o.bias": "pytorch_model-00002-of-00025.safetensors",
51
+ "layers.2.norm2.weight": "pytorch_model-00002-of-00025.safetensors",
52
+ "layers.2.moe.W_in": "pytorch_model-00003-of-00025.safetensors",
53
+ "layers.2.moe.b_in": "pytorch_model-00003-of-00025.safetensors",
54
+ "layers.2.moe.W_out": "pytorch_model-00003-of-00025.safetensors",
55
+ "layers.2.moe.b_out": "pytorch_model-00003-of-00025.safetensors",
56
+ "layers.2.moe.router.weight": "pytorch_model-00003-of-00025.safetensors",
57
+ "layers.2.moe.router.bias": "pytorch_model-00003-of-00025.safetensors",
58
+ "layers.3.norm1.weight": "pytorch_model-00003-of-00025.safetensors",
59
+ "layers.3.attn.sink_logit": "pytorch_model-00003-of-00025.safetensors",
60
+ "layers.3.attn.q.weight": "pytorch_model-00003-of-00025.safetensors",
61
+ "layers.3.attn.q.bias": "pytorch_model-00003-of-00025.safetensors",
62
+ "layers.3.attn.k.weight": "pytorch_model-00003-of-00025.safetensors",
63
+ "layers.3.attn.k.bias": "pytorch_model-00003-of-00025.safetensors",
64
+ "layers.3.attn.v.weight": "pytorch_model-00003-of-00025.safetensors",
65
+ "layers.3.attn.v.bias": "pytorch_model-00003-of-00025.safetensors",
66
+ "layers.3.attn.o.weight": "pytorch_model-00003-of-00025.safetensors",
67
+ "layers.3.attn.o.bias": "pytorch_model-00003-of-00025.safetensors",
68
+ "layers.3.norm2.weight": "pytorch_model-00003-of-00025.safetensors",
69
+ "layers.3.moe.W_in": "pytorch_model-00004-of-00025.safetensors",
70
+ "layers.3.moe.b_in": "pytorch_model-00004-of-00025.safetensors",
71
+ "layers.3.moe.W_out": "pytorch_model-00004-of-00025.safetensors",
72
+ "layers.3.moe.b_out": "pytorch_model-00004-of-00025.safetensors",
73
+ "layers.3.moe.router.weight": "pytorch_model-00004-of-00025.safetensors",
74
+ "layers.3.moe.router.bias": "pytorch_model-00004-of-00025.safetensors",
75
+ "layers.4.norm1.weight": "pytorch_model-00004-of-00025.safetensors",
76
+ "layers.4.attn.sink_logit": "pytorch_model-00004-of-00025.safetensors",
77
+ "layers.4.attn.q.weight": "pytorch_model-00004-of-00025.safetensors",
78
+ "layers.4.attn.q.bias": "pytorch_model-00004-of-00025.safetensors",
79
+ "layers.4.attn.k.weight": "pytorch_model-00004-of-00025.safetensors",
80
+ "layers.4.attn.k.bias": "pytorch_model-00004-of-00025.safetensors",
81
+ "layers.4.attn.v.weight": "pytorch_model-00004-of-00025.safetensors",
82
+ "layers.4.attn.v.bias": "pytorch_model-00004-of-00025.safetensors",
83
+ "layers.4.attn.o.weight": "pytorch_model-00004-of-00025.safetensors",
84
+ "layers.4.attn.o.bias": "pytorch_model-00004-of-00025.safetensors",
85
+ "layers.4.norm2.weight": "pytorch_model-00004-of-00025.safetensors",
86
+ "layers.4.moe.W_in": "pytorch_model-00005-of-00025.safetensors",
87
+ "layers.4.moe.b_in": "pytorch_model-00005-of-00025.safetensors",
88
+ "layers.4.moe.W_out": "pytorch_model-00005-of-00025.safetensors",
89
+ "layers.4.moe.b_out": "pytorch_model-00005-of-00025.safetensors",
90
+ "layers.4.moe.router.weight": "pytorch_model-00005-of-00025.safetensors",
91
+ "layers.4.moe.router.bias": "pytorch_model-00005-of-00025.safetensors",
92
+ "layers.5.norm1.weight": "pytorch_model-00005-of-00025.safetensors",
93
+ "layers.5.attn.sink_logit": "pytorch_model-00005-of-00025.safetensors",
94
+ "layers.5.attn.q.weight": "pytorch_model-00005-of-00025.safetensors",
95
+ "layers.5.attn.q.bias": "pytorch_model-00005-of-00025.safetensors",
96
+ "layers.5.attn.k.weight": "pytorch_model-00005-of-00025.safetensors",
97
+ "layers.5.attn.k.bias": "pytorch_model-00005-of-00025.safetensors",
98
+ "layers.5.attn.v.weight": "pytorch_model-00005-of-00025.safetensors",
99
+ "layers.5.attn.v.bias": "pytorch_model-00005-of-00025.safetensors",
100
+ "layers.5.attn.o.weight": "pytorch_model-00005-of-00025.safetensors",
101
+ "layers.5.attn.o.bias": "pytorch_model-00005-of-00025.safetensors",
102
+ "layers.5.norm2.weight": "pytorch_model-00005-of-00025.safetensors",
103
+ "layers.5.moe.W_in": "pytorch_model-00006-of-00025.safetensors",
104
+ "layers.5.moe.b_in": "pytorch_model-00006-of-00025.safetensors",
105
+ "layers.5.moe.W_out": "pytorch_model-00006-of-00025.safetensors",
106
+ "layers.5.moe.b_out": "pytorch_model-00006-of-00025.safetensors",
107
+ "layers.5.moe.router.weight": "pytorch_model-00006-of-00025.safetensors",
108
+ "layers.5.moe.router.bias": "pytorch_model-00006-of-00025.safetensors",
109
+ "layers.6.norm1.weight": "pytorch_model-00006-of-00025.safetensors",
110
+ "layers.6.attn.sink_logit": "pytorch_model-00006-of-00025.safetensors",
111
+ "layers.6.attn.q.weight": "pytorch_model-00006-of-00025.safetensors",
112
+ "layers.6.attn.q.bias": "pytorch_model-00006-of-00025.safetensors",
113
+ "layers.6.attn.k.weight": "pytorch_model-00006-of-00025.safetensors",
114
+ "layers.6.attn.k.bias": "pytorch_model-00006-of-00025.safetensors",
115
+ "layers.6.attn.v.weight": "pytorch_model-00006-of-00025.safetensors",
116
+ "layers.6.attn.v.bias": "pytorch_model-00006-of-00025.safetensors",
117
+ "layers.6.attn.o.weight": "pytorch_model-00006-of-00025.safetensors",
118
+ "layers.6.attn.o.bias": "pytorch_model-00006-of-00025.safetensors",
119
+ "layers.6.norm2.weight": "pytorch_model-00006-of-00025.safetensors",
120
+ "layers.6.moe.W_in": "pytorch_model-00007-of-00025.safetensors",
121
+ "layers.6.moe.b_in": "pytorch_model-00007-of-00025.safetensors",
122
+ "layers.6.moe.W_out": "pytorch_model-00007-of-00025.safetensors",
123
+ "layers.6.moe.b_out": "pytorch_model-00007-of-00025.safetensors",
124
+ "layers.6.moe.router.weight": "pytorch_model-00007-of-00025.safetensors",
125
+ "layers.6.moe.router.bias": "pytorch_model-00007-of-00025.safetensors",
126
+ "layers.7.norm1.weight": "pytorch_model-00007-of-00025.safetensors",
127
+ "layers.7.attn.sink_logit": "pytorch_model-00007-of-00025.safetensors",
128
+ "layers.7.attn.q.weight": "pytorch_model-00007-of-00025.safetensors",
129
+ "layers.7.attn.q.bias": "pytorch_model-00007-of-00025.safetensors",
130
+ "layers.7.attn.k.weight": "pytorch_model-00007-of-00025.safetensors",
131
+ "layers.7.attn.k.bias": "pytorch_model-00007-of-00025.safetensors",
132
+ "layers.7.attn.v.weight": "pytorch_model-00007-of-00025.safetensors",
133
+ "layers.7.attn.v.bias": "pytorch_model-00007-of-00025.safetensors",
134
+ "layers.7.attn.o.weight": "pytorch_model-00007-of-00025.safetensors",
135
+ "layers.7.attn.o.bias": "pytorch_model-00007-of-00025.safetensors",
136
+ "layers.7.norm2.weight": "pytorch_model-00007-of-00025.safetensors",
137
+ "layers.7.moe.W_in": "pytorch_model-00008-of-00025.safetensors",
138
+ "layers.7.moe.b_in": "pytorch_model-00008-of-00025.safetensors",
139
+ "layers.7.moe.W_out": "pytorch_model-00008-of-00025.safetensors",
140
+ "layers.7.moe.b_out": "pytorch_model-00008-of-00025.safetensors",
141
+ "layers.7.moe.router.weight": "pytorch_model-00008-of-00025.safetensors",
142
+ "layers.7.moe.router.bias": "pytorch_model-00008-of-00025.safetensors",
143
+ "layers.8.norm1.weight": "pytorch_model-00008-of-00025.safetensors",
144
+ "layers.8.attn.sink_logit": "pytorch_model-00008-of-00025.safetensors",
145
+ "layers.8.attn.q.weight": "pytorch_model-00008-of-00025.safetensors",
146
+ "layers.8.attn.q.bias": "pytorch_model-00008-of-00025.safetensors",
147
+ "layers.8.attn.k.weight": "pytorch_model-00008-of-00025.safetensors",
148
+ "layers.8.attn.k.bias": "pytorch_model-00008-of-00025.safetensors",
149
+ "layers.8.attn.v.weight": "pytorch_model-00008-of-00025.safetensors",
150
+ "layers.8.attn.v.bias": "pytorch_model-00008-of-00025.safetensors",
151
+ "layers.8.attn.o.weight": "pytorch_model-00008-of-00025.safetensors",
152
+ "layers.8.attn.o.bias": "pytorch_model-00008-of-00025.safetensors",
153
+ "layers.8.norm2.weight": "pytorch_model-00008-of-00025.safetensors",
154
+ "layers.8.moe.W_in": "pytorch_model-00009-of-00025.safetensors",
155
+ "layers.8.moe.b_in": "pytorch_model-00009-of-00025.safetensors",
156
+ "layers.8.moe.W_out": "pytorch_model-00009-of-00025.safetensors",
157
+ "layers.8.moe.b_out": "pytorch_model-00009-of-00025.safetensors",
158
+ "layers.8.moe.router.weight": "pytorch_model-00009-of-00025.safetensors",
159
+ "layers.8.moe.router.bias": "pytorch_model-00009-of-00025.safetensors",
160
+ "layers.9.norm1.weight": "pytorch_model-00009-of-00025.safetensors",
161
+ "layers.9.attn.sink_logit": "pytorch_model-00009-of-00025.safetensors",
162
+ "layers.9.attn.q.weight": "pytorch_model-00009-of-00025.safetensors",
163
+ "layers.9.attn.q.bias": "pytorch_model-00009-of-00025.safetensors",
164
+ "layers.9.attn.k.weight": "pytorch_model-00009-of-00025.safetensors",
165
+ "layers.9.attn.k.bias": "pytorch_model-00009-of-00025.safetensors",
166
+ "layers.9.attn.v.weight": "pytorch_model-00009-of-00025.safetensors",
167
+ "layers.9.attn.v.bias": "pytorch_model-00009-of-00025.safetensors",
168
+ "layers.9.attn.o.weight": "pytorch_model-00009-of-00025.safetensors",
169
+ "layers.9.attn.o.bias": "pytorch_model-00009-of-00025.safetensors",
170
+ "layers.9.norm2.weight": "pytorch_model-00009-of-00025.safetensors",
171
+ "layers.9.moe.W_in": "pytorch_model-00010-of-00025.safetensors",
172
+ "layers.9.moe.b_in": "pytorch_model-00010-of-00025.safetensors",
173
+ "layers.9.moe.W_out": "pytorch_model-00010-of-00025.safetensors",
174
+ "layers.9.moe.b_out": "pytorch_model-00010-of-00025.safetensors",
175
+ "layers.9.moe.router.weight": "pytorch_model-00010-of-00025.safetensors",
176
+ "layers.9.moe.router.bias": "pytorch_model-00010-of-00025.safetensors",
177
+ "layers.10.norm1.weight": "pytorch_model-00010-of-00025.safetensors",
178
+ "layers.10.attn.sink_logit": "pytorch_model-00010-of-00025.safetensors",
179
+ "layers.10.attn.q.weight": "pytorch_model-00010-of-00025.safetensors",
180
+ "layers.10.attn.q.bias": "pytorch_model-00010-of-00025.safetensors",
181
+ "layers.10.attn.k.weight": "pytorch_model-00010-of-00025.safetensors",
182
+ "layers.10.attn.k.bias": "pytorch_model-00010-of-00025.safetensors",
183
+ "layers.10.attn.v.weight": "pytorch_model-00010-of-00025.safetensors",
184
+ "layers.10.attn.v.bias": "pytorch_model-00010-of-00025.safetensors",
185
+ "layers.10.attn.o.weight": "pytorch_model-00010-of-00025.safetensors",
186
+ "layers.10.attn.o.bias": "pytorch_model-00010-of-00025.safetensors",
187
+ "layers.10.norm2.weight": "pytorch_model-00010-of-00025.safetensors",
188
+ "layers.10.moe.W_in": "pytorch_model-00011-of-00025.safetensors",
189
+ "layers.10.moe.b_in": "pytorch_model-00011-of-00025.safetensors",
190
+ "layers.10.moe.W_out": "pytorch_model-00011-of-00025.safetensors",
191
+ "layers.10.moe.b_out": "pytorch_model-00011-of-00025.safetensors",
192
+ "layers.10.moe.router.weight": "pytorch_model-00011-of-00025.safetensors",
193
+ "layers.10.moe.router.bias": "pytorch_model-00011-of-00025.safetensors",
194
+ "layers.11.norm1.weight": "pytorch_model-00011-of-00025.safetensors",
195
+ "layers.11.attn.sink_logit": "pytorch_model-00011-of-00025.safetensors",
196
+ "layers.11.attn.q.weight": "pytorch_model-00011-of-00025.safetensors",
197
+ "layers.11.attn.q.bias": "pytorch_model-00011-of-00025.safetensors",
198
+ "layers.11.attn.k.weight": "pytorch_model-00011-of-00025.safetensors",
199
+ "layers.11.attn.k.bias": "pytorch_model-00011-of-00025.safetensors",
200
+ "layers.11.attn.v.weight": "pytorch_model-00011-of-00025.safetensors",
201
+ "layers.11.attn.v.bias": "pytorch_model-00011-of-00025.safetensors",
202
+ "layers.11.attn.o.weight": "pytorch_model-00011-of-00025.safetensors",
203
+ "layers.11.attn.o.bias": "pytorch_model-00011-of-00025.safetensors",
204
+ "layers.11.norm2.weight": "pytorch_model-00011-of-00025.safetensors",
205
+ "layers.11.moe.W_in": "pytorch_model-00012-of-00025.safetensors",
206
+ "layers.11.moe.b_in": "pytorch_model-00012-of-00025.safetensors",
207
+ "layers.11.moe.W_out": "pytorch_model-00012-of-00025.safetensors",
208
+ "layers.11.moe.b_out": "pytorch_model-00012-of-00025.safetensors",
209
+ "layers.11.moe.router.weight": "pytorch_model-00012-of-00025.safetensors",
210
+ "layers.11.moe.router.bias": "pytorch_model-00012-of-00025.safetensors",
211
+ "layers.12.norm1.weight": "pytorch_model-00012-of-00025.safetensors",
212
+ "layers.12.attn.sink_logit": "pytorch_model-00012-of-00025.safetensors",
213
+ "layers.12.attn.q.weight": "pytorch_model-00012-of-00025.safetensors",
214
+ "layers.12.attn.q.bias": "pytorch_model-00012-of-00025.safetensors",
215
+ "layers.12.attn.k.weight": "pytorch_model-00012-of-00025.safetensors",
216
+ "layers.12.attn.k.bias": "pytorch_model-00012-of-00025.safetensors",
217
+ "layers.12.attn.v.weight": "pytorch_model-00012-of-00025.safetensors",
218
+ "layers.12.attn.v.bias": "pytorch_model-00012-of-00025.safetensors",
219
+ "layers.12.attn.o.weight": "pytorch_model-00012-of-00025.safetensors",
220
+ "layers.12.attn.o.bias": "pytorch_model-00012-of-00025.safetensors",
221
+ "layers.12.norm2.weight": "pytorch_model-00012-of-00025.safetensors",
222
+ "layers.12.moe.W_in": "pytorch_model-00013-of-00025.safetensors",
223
+ "layers.12.moe.b_in": "pytorch_model-00013-of-00025.safetensors",
224
+ "layers.12.moe.W_out": "pytorch_model-00013-of-00025.safetensors",
225
+ "layers.12.moe.b_out": "pytorch_model-00013-of-00025.safetensors",
226
+ "layers.12.moe.router.weight": "pytorch_model-00013-of-00025.safetensors",
227
+ "layers.12.moe.router.bias": "pytorch_model-00013-of-00025.safetensors",
228
+ "layers.13.norm1.weight": "pytorch_model-00013-of-00025.safetensors",
229
+ "layers.13.attn.sink_logit": "pytorch_model-00013-of-00025.safetensors",
230
+ "layers.13.attn.q.weight": "pytorch_model-00013-of-00025.safetensors",
231
+ "layers.13.attn.q.bias": "pytorch_model-00013-of-00025.safetensors",
232
+ "layers.13.attn.k.weight": "pytorch_model-00013-of-00025.safetensors",
233
+ "layers.13.attn.k.bias": "pytorch_model-00013-of-00025.safetensors",
234
+ "layers.13.attn.v.weight": "pytorch_model-00013-of-00025.safetensors",
235
+ "layers.13.attn.v.bias": "pytorch_model-00013-of-00025.safetensors",
236
+ "layers.13.attn.o.weight": "pytorch_model-00013-of-00025.safetensors",
237
+ "layers.13.attn.o.bias": "pytorch_model-00013-of-00025.safetensors",
238
+ "layers.13.norm2.weight": "pytorch_model-00013-of-00025.safetensors",
239
+ "layers.13.moe.W_in": "pytorch_model-00014-of-00025.safetensors",
240
+ "layers.13.moe.b_in": "pytorch_model-00014-of-00025.safetensors",
241
+ "layers.13.moe.W_out": "pytorch_model-00014-of-00025.safetensors",
242
+ "layers.13.moe.b_out": "pytorch_model-00014-of-00025.safetensors",
243
+ "layers.13.moe.router.weight": "pytorch_model-00014-of-00025.safetensors",
244
+ "layers.13.moe.router.bias": "pytorch_model-00014-of-00025.safetensors",
245
+ "layers.14.norm1.weight": "pytorch_model-00014-of-00025.safetensors",
246
+ "layers.14.attn.sink_logit": "pytorch_model-00014-of-00025.safetensors",
247
+ "layers.14.attn.q.weight": "pytorch_model-00014-of-00025.safetensors",
248
+ "layers.14.attn.q.bias": "pytorch_model-00014-of-00025.safetensors",
249
+ "layers.14.attn.k.weight": "pytorch_model-00014-of-00025.safetensors",
250
+ "layers.14.attn.k.bias": "pytorch_model-00014-of-00025.safetensors",
251
+ "layers.14.attn.v.weight": "pytorch_model-00014-of-00025.safetensors",
252
+ "layers.14.attn.v.bias": "pytorch_model-00014-of-00025.safetensors",
253
+ "layers.14.attn.o.weight": "pytorch_model-00014-of-00025.safetensors",
254
+ "layers.14.attn.o.bias": "pytorch_model-00014-of-00025.safetensors",
255
+ "layers.14.norm2.weight": "pytorch_model-00014-of-00025.safetensors",
256
+ "layers.14.moe.W_in": "pytorch_model-00015-of-00025.safetensors",
257
+ "layers.14.moe.b_in": "pytorch_model-00015-of-00025.safetensors",
258
+ "layers.14.moe.W_out": "pytorch_model-00015-of-00025.safetensors",
259
+ "layers.14.moe.b_out": "pytorch_model-00015-of-00025.safetensors",
260
+ "layers.14.moe.router.weight": "pytorch_model-00015-of-00025.safetensors",
261
+ "layers.14.moe.router.bias": "pytorch_model-00015-of-00025.safetensors",
262
+ "layers.15.norm1.weight": "pytorch_model-00015-of-00025.safetensors",
263
+ "layers.15.attn.sink_logit": "pytorch_model-00015-of-00025.safetensors",
264
+ "layers.15.attn.q.weight": "pytorch_model-00015-of-00025.safetensors",
265
+ "layers.15.attn.q.bias": "pytorch_model-00015-of-00025.safetensors",
266
+ "layers.15.attn.k.weight": "pytorch_model-00015-of-00025.safetensors",
267
+ "layers.15.attn.k.bias": "pytorch_model-00015-of-00025.safetensors",
268
+ "layers.15.attn.v.weight": "pytorch_model-00015-of-00025.safetensors",
269
+ "layers.15.attn.v.bias": "pytorch_model-00015-of-00025.safetensors",
270
+ "layers.15.attn.o.weight": "pytorch_model-00015-of-00025.safetensors",
271
+ "layers.15.attn.o.bias": "pytorch_model-00015-of-00025.safetensors",
272
+ "layers.15.norm2.weight": "pytorch_model-00015-of-00025.safetensors",
273
+ "layers.15.moe.W_in": "pytorch_model-00016-of-00025.safetensors",
274
+ "layers.15.moe.b_in": "pytorch_model-00016-of-00025.safetensors",
275
+ "layers.15.moe.W_out": "pytorch_model-00016-of-00025.safetensors",
276
+ "layers.15.moe.b_out": "pytorch_model-00016-of-00025.safetensors",
277
+ "layers.15.moe.router.weight": "pytorch_model-00016-of-00025.safetensors",
278
+ "layers.15.moe.router.bias": "pytorch_model-00016-of-00025.safetensors",
279
+ "layers.16.norm1.weight": "pytorch_model-00016-of-00025.safetensors",
280
+ "layers.16.attn.sink_logit": "pytorch_model-00016-of-00025.safetensors",
281
+ "layers.16.attn.q.weight": "pytorch_model-00016-of-00025.safetensors",
282
+ "layers.16.attn.q.bias": "pytorch_model-00016-of-00025.safetensors",
283
+ "layers.16.attn.k.weight": "pytorch_model-00016-of-00025.safetensors",
284
+ "layers.16.attn.k.bias": "pytorch_model-00016-of-00025.safetensors",
285
+ "layers.16.attn.v.weight": "pytorch_model-00016-of-00025.safetensors",
286
+ "layers.16.attn.v.bias": "pytorch_model-00016-of-00025.safetensors",
287
+ "layers.16.attn.o.weight": "pytorch_model-00016-of-00025.safetensors",
288
+ "layers.16.attn.o.bias": "pytorch_model-00016-of-00025.safetensors",
289
+ "layers.16.norm2.weight": "pytorch_model-00016-of-00025.safetensors",
290
+ "layers.16.moe.W_in": "pytorch_model-00017-of-00025.safetensors",
291
+ "layers.16.moe.b_in": "pytorch_model-00017-of-00025.safetensors",
292
+ "layers.16.moe.W_out": "pytorch_model-00017-of-00025.safetensors",
293
+ "layers.16.moe.b_out": "pytorch_model-00017-of-00025.safetensors",
294
+ "layers.16.moe.router.weight": "pytorch_model-00017-of-00025.safetensors",
295
+ "layers.16.moe.router.bias": "pytorch_model-00017-of-00025.safetensors",
296
+ "layers.17.norm1.weight": "pytorch_model-00017-of-00025.safetensors",
297
+ "layers.17.attn.sink_logit": "pytorch_model-00017-of-00025.safetensors",
298
+ "layers.17.attn.q.weight": "pytorch_model-00017-of-00025.safetensors",
299
+ "layers.17.attn.q.bias": "pytorch_model-00017-of-00025.safetensors",
300
+ "layers.17.attn.k.weight": "pytorch_model-00017-of-00025.safetensors",
301
+ "layers.17.attn.k.bias": "pytorch_model-00017-of-00025.safetensors",
302
+ "layers.17.attn.v.weight": "pytorch_model-00017-of-00025.safetensors",
303
+ "layers.17.attn.v.bias": "pytorch_model-00017-of-00025.safetensors",
304
+ "layers.17.attn.o.weight": "pytorch_model-00017-of-00025.safetensors",
305
+ "layers.17.attn.o.bias": "pytorch_model-00017-of-00025.safetensors",
306
+ "layers.17.norm2.weight": "pytorch_model-00017-of-00025.safetensors",
307
+ "layers.17.moe.W_in": "pytorch_model-00018-of-00025.safetensors",
308
+ "layers.17.moe.b_in": "pytorch_model-00018-of-00025.safetensors",
309
+ "layers.17.moe.W_out": "pytorch_model-00018-of-00025.safetensors",
310
+ "layers.17.moe.b_out": "pytorch_model-00018-of-00025.safetensors",
311
+ "layers.17.moe.router.weight": "pytorch_model-00018-of-00025.safetensors",
312
+ "layers.17.moe.router.bias": "pytorch_model-00018-of-00025.safetensors",
313
+ "layers.18.norm1.weight": "pytorch_model-00018-of-00025.safetensors",
314
+ "layers.18.attn.sink_logit": "pytorch_model-00018-of-00025.safetensors",
315
+ "layers.18.attn.q.weight": "pytorch_model-00018-of-00025.safetensors",
316
+ "layers.18.attn.q.bias": "pytorch_model-00018-of-00025.safetensors",
317
+ "layers.18.attn.k.weight": "pytorch_model-00018-of-00025.safetensors",
318
+ "layers.18.attn.k.bias": "pytorch_model-00018-of-00025.safetensors",
319
+ "layers.18.attn.v.weight": "pytorch_model-00018-of-00025.safetensors",
320
+ "layers.18.attn.v.bias": "pytorch_model-00018-of-00025.safetensors",
321
+ "layers.18.attn.o.weight": "pytorch_model-00018-of-00025.safetensors",
322
+ "layers.18.attn.o.bias": "pytorch_model-00018-of-00025.safetensors",
323
+ "layers.18.norm2.weight": "pytorch_model-00018-of-00025.safetensors",
324
+ "layers.18.moe.W_in": "pytorch_model-00019-of-00025.safetensors",
325
+ "layers.18.moe.b_in": "pytorch_model-00019-of-00025.safetensors",
326
+ "layers.18.moe.W_out": "pytorch_model-00019-of-00025.safetensors",
327
+ "layers.18.moe.b_out": "pytorch_model-00019-of-00025.safetensors",
328
+ "layers.18.moe.router.weight": "pytorch_model-00019-of-00025.safetensors",
329
+ "layers.18.moe.router.bias": "pytorch_model-00019-of-00025.safetensors",
330
+ "layers.19.norm1.weight": "pytorch_model-00019-of-00025.safetensors",
331
+ "layers.19.attn.sink_logit": "pytorch_model-00019-of-00025.safetensors",
332
+ "layers.19.attn.q.weight": "pytorch_model-00019-of-00025.safetensors",
333
+ "layers.19.attn.q.bias": "pytorch_model-00019-of-00025.safetensors",
334
+ "layers.19.attn.k.weight": "pytorch_model-00019-of-00025.safetensors",
335
+ "layers.19.attn.k.bias": "pytorch_model-00019-of-00025.safetensors",
336
+ "layers.19.attn.v.weight": "pytorch_model-00019-of-00025.safetensors",
337
+ "layers.19.attn.v.bias": "pytorch_model-00019-of-00025.safetensors",
338
+ "layers.19.attn.o.weight": "pytorch_model-00019-of-00025.safetensors",
339
+ "layers.19.attn.o.bias": "pytorch_model-00019-of-00025.safetensors",
340
+ "layers.19.norm2.weight": "pytorch_model-00019-of-00025.safetensors",
341
+ "layers.19.moe.W_in": "pytorch_model-00020-of-00025.safetensors",
342
+ "layers.19.moe.b_in": "pytorch_model-00020-of-00025.safetensors",
343
+ "layers.19.moe.W_out": "pytorch_model-00020-of-00025.safetensors",
344
+ "layers.19.moe.b_out": "pytorch_model-00020-of-00025.safetensors",
345
+ "layers.19.moe.router.weight": "pytorch_model-00020-of-00025.safetensors",
346
+ "layers.19.moe.router.bias": "pytorch_model-00020-of-00025.safetensors",
347
+ "layers.20.norm1.weight": "pytorch_model-00020-of-00025.safetensors",
348
+ "layers.20.attn.sink_logit": "pytorch_model-00020-of-00025.safetensors",
349
+ "layers.20.attn.q.weight": "pytorch_model-00020-of-00025.safetensors",
350
+ "layers.20.attn.q.bias": "pytorch_model-00020-of-00025.safetensors",
351
+ "layers.20.attn.k.weight": "pytorch_model-00020-of-00025.safetensors",
352
+ "layers.20.attn.k.bias": "pytorch_model-00020-of-00025.safetensors",
353
+ "layers.20.attn.v.weight": "pytorch_model-00020-of-00025.safetensors",
354
+ "layers.20.attn.v.bias": "pytorch_model-00020-of-00025.safetensors",
355
+ "layers.20.attn.o.weight": "pytorch_model-00020-of-00025.safetensors",
356
+ "layers.20.attn.o.bias": "pytorch_model-00020-of-00025.safetensors",
357
+ "layers.20.norm2.weight": "pytorch_model-00020-of-00025.safetensors",
358
+ "layers.20.moe.W_in": "pytorch_model-00021-of-00025.safetensors",
359
+ "layers.20.moe.b_in": "pytorch_model-00021-of-00025.safetensors",
360
+ "layers.20.moe.W_out": "pytorch_model-00021-of-00025.safetensors",
361
+ "layers.20.moe.b_out": "pytorch_model-00021-of-00025.safetensors",
362
+ "layers.20.moe.router.weight": "pytorch_model-00021-of-00025.safetensors",
363
+ "layers.20.moe.router.bias": "pytorch_model-00021-of-00025.safetensors",
364
+ "layers.21.norm1.weight": "pytorch_model-00021-of-00025.safetensors",
365
+ "layers.21.attn.sink_logit": "pytorch_model-00021-of-00025.safetensors",
366
+ "layers.21.attn.q.weight": "pytorch_model-00021-of-00025.safetensors",
367
+ "layers.21.attn.q.bias": "pytorch_model-00021-of-00025.safetensors",
368
+ "layers.21.attn.k.weight": "pytorch_model-00021-of-00025.safetensors",
369
+ "layers.21.attn.k.bias": "pytorch_model-00021-of-00025.safetensors",
370
+ "layers.21.attn.v.weight": "pytorch_model-00021-of-00025.safetensors",
371
+ "layers.21.attn.v.bias": "pytorch_model-00021-of-00025.safetensors",
372
+ "layers.21.attn.o.weight": "pytorch_model-00021-of-00025.safetensors",
373
+ "layers.21.attn.o.bias": "pytorch_model-00021-of-00025.safetensors",
374
+ "layers.21.norm2.weight": "pytorch_model-00021-of-00025.safetensors",
375
+ "layers.21.moe.W_in": "pytorch_model-00022-of-00025.safetensors",
376
+ "layers.21.moe.b_in": "pytorch_model-00022-of-00025.safetensors",
377
+ "layers.21.moe.W_out": "pytorch_model-00022-of-00025.safetensors",
378
+ "layers.21.moe.b_out": "pytorch_model-00022-of-00025.safetensors",
379
+ "layers.21.moe.router.weight": "pytorch_model-00022-of-00025.safetensors",
380
+ "layers.21.moe.router.bias": "pytorch_model-00022-of-00025.safetensors",
381
+ "layers.22.norm1.weight": "pytorch_model-00022-of-00025.safetensors",
382
+ "layers.22.attn.sink_logit": "pytorch_model-00022-of-00025.safetensors",
383
+ "layers.22.attn.q.weight": "pytorch_model-00022-of-00025.safetensors",
384
+ "layers.22.attn.q.bias": "pytorch_model-00022-of-00025.safetensors",
385
+ "layers.22.attn.k.weight": "pytorch_model-00022-of-00025.safetensors",
386
+ "layers.22.attn.k.bias": "pytorch_model-00022-of-00025.safetensors",
387
+ "layers.22.attn.v.weight": "pytorch_model-00022-of-00025.safetensors",
388
+ "layers.22.attn.v.bias": "pytorch_model-00022-of-00025.safetensors",
389
+ "layers.22.attn.o.weight": "pytorch_model-00022-of-00025.safetensors",
390
+ "layers.22.attn.o.bias": "pytorch_model-00022-of-00025.safetensors",
391
+ "layers.22.norm2.weight": "pytorch_model-00022-of-00025.safetensors",
392
+ "layers.22.moe.W_in": "pytorch_model-00023-of-00025.safetensors",
393
+ "layers.22.moe.b_in": "pytorch_model-00023-of-00025.safetensors",
394
+ "layers.22.moe.W_out": "pytorch_model-00023-of-00025.safetensors",
395
+ "layers.22.moe.b_out": "pytorch_model-00023-of-00025.safetensors",
396
+ "layers.22.moe.router.weight": "pytorch_model-00023-of-00025.safetensors",
397
+ "layers.22.moe.router.bias": "pytorch_model-00023-of-00025.safetensors",
398
+ "layers.23.norm1.weight": "pytorch_model-00023-of-00025.safetensors",
399
+ "layers.23.attn.sink_logit": "pytorch_model-00023-of-00025.safetensors",
400
+ "layers.23.attn.q.weight": "pytorch_model-00023-of-00025.safetensors",
401
+ "layers.23.attn.q.bias": "pytorch_model-00023-of-00025.safetensors",
402
+ "layers.23.attn.k.weight": "pytorch_model-00023-of-00025.safetensors",
403
+ "layers.23.attn.k.bias": "pytorch_model-00023-of-00025.safetensors",
404
+ "layers.23.attn.v.weight": "pytorch_model-00023-of-00025.safetensors",
405
+ "layers.23.attn.v.bias": "pytorch_model-00023-of-00025.safetensors",
406
+ "layers.23.attn.o.weight": "pytorch_model-00023-of-00025.safetensors",
407
+ "layers.23.attn.o.bias": "pytorch_model-00023-of-00025.safetensors",
408
+ "layers.23.norm2.weight": "pytorch_model-00023-of-00025.safetensors",
409
+ "layers.23.moe.W_in": "pytorch_model-00024-of-00025.safetensors",
410
+ "layers.23.moe.b_in": "pytorch_model-00024-of-00025.safetensors",
411
+ "layers.23.moe.W_out": "pytorch_model-00024-of-00025.safetensors",
412
+ "layers.23.moe.b_out": "pytorch_model-00024-of-00025.safetensors",
413
+ "layers.23.moe.router.weight": "pytorch_model-00024-of-00025.safetensors",
414
+ "layers.23.moe.router.bias": "pytorch_model-00024-of-00025.safetensors",
415
+ "norm_f.weight": "pytorch_model-00024-of-00025.safetensors",
416
+ "lm_head.weight": "pytorch_model-00025-of-00025.safetensors"
417
+ }
418
+ }
README_EXPORT.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ # Exported Weights
2
+
3
+ - Source shards: out-20b-h200-stable/ckpt_rankXXXXX.pt
4
+ - Iteration: 1900
5
+ - Tokenizer hint: o200k_harmony
6
+ - max_shard_size: 5GB
7
+ - Generated: 2025-09-03T11:47:03.182090
config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "gpt_oss_like",
3
+ "vocab_size": 201088,
4
+ "hidden_size": 2880,
5
+ "num_hidden_layers": 24,
6
+ "num_attention_heads": 64,
7
+ "num_key_value_heads": 8,
8
+ "max_position_embeddings": 131072,
9
+ "rms_norm_eps": 1e-05,
10
+ "rope_theta": 150000.0,
11
+ "attention_bias": true,
12
+ "tie_word_embeddings": false,
13
+ "sliding_window": 128,
14
+ "torch_dtype": "bfloat16",
15
+ "eos_token_id": null
16
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,418 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 83659028736
4
+ },
5
+ "weight_map": {
6
+ "embed.weight": "pytorch_model-00001-of-00025.safetensors",
7
+ "layers.0.norm1.weight": "pytorch_model-00001-of-00025.safetensors",
8
+ "layers.0.attn.sink_logit": "pytorch_model-00001-of-00025.safetensors",
9
+ "layers.0.attn.q.weight": "pytorch_model-00001-of-00025.safetensors",
10
+ "layers.0.attn.q.bias": "pytorch_model-00001-of-00025.safetensors",
11
+ "layers.0.attn.k.weight": "pytorch_model-00001-of-00025.safetensors",
12
+ "layers.0.attn.k.bias": "pytorch_model-00001-of-00025.safetensors",
13
+ "layers.0.attn.v.weight": "pytorch_model-00001-of-00025.safetensors",
14
+ "layers.0.attn.v.bias": "pytorch_model-00001-of-00025.safetensors",
15
+ "layers.0.attn.o.weight": "pytorch_model-00001-of-00025.safetensors",
16
+ "layers.0.attn.o.bias": "pytorch_model-00001-of-00025.safetensors",
17
+ "layers.0.norm2.weight": "pytorch_model-00001-of-00025.safetensors",
18
+ "layers.0.moe.W_in": "pytorch_model-00001-of-00025.safetensors",
19
+ "layers.0.moe.b_in": "pytorch_model-00001-of-00025.safetensors",
20
+ "layers.0.moe.W_out": "pytorch_model-00002-of-00025.safetensors",
21
+ "layers.0.moe.b_out": "pytorch_model-00002-of-00025.safetensors",
22
+ "layers.0.moe.router.weight": "pytorch_model-00002-of-00025.safetensors",
23
+ "layers.0.moe.router.bias": "pytorch_model-00002-of-00025.safetensors",
24
+ "layers.1.norm1.weight": "pytorch_model-00002-of-00025.safetensors",
25
+ "layers.1.attn.sink_logit": "pytorch_model-00002-of-00025.safetensors",
26
+ "layers.1.attn.q.weight": "pytorch_model-00002-of-00025.safetensors",
27
+ "layers.1.attn.q.bias": "pytorch_model-00002-of-00025.safetensors",
28
+ "layers.1.attn.k.weight": "pytorch_model-00002-of-00025.safetensors",
29
+ "layers.1.attn.k.bias": "pytorch_model-00002-of-00025.safetensors",
30
+ "layers.1.attn.v.weight": "pytorch_model-00002-of-00025.safetensors",
31
+ "layers.1.attn.v.bias": "pytorch_model-00002-of-00025.safetensors",
32
+ "layers.1.attn.o.weight": "pytorch_model-00002-of-00025.safetensors",
33
+ "layers.1.attn.o.bias": "pytorch_model-00002-of-00025.safetensors",
34
+ "layers.1.norm2.weight": "pytorch_model-00002-of-00025.safetensors",
35
+ "layers.1.moe.W_in": "pytorch_model-00002-of-00025.safetensors",
36
+ "layers.1.moe.b_in": "pytorch_model-00002-of-00025.safetensors",
37
+ "layers.1.moe.W_out": "pytorch_model-00002-of-00025.safetensors",
38
+ "layers.1.moe.b_out": "pytorch_model-00002-of-00025.safetensors",
39
+ "layers.1.moe.router.weight": "pytorch_model-00002-of-00025.safetensors",
40
+ "layers.1.moe.router.bias": "pytorch_model-00002-of-00025.safetensors",
41
+ "layers.2.norm1.weight": "pytorch_model-00002-of-00025.safetensors",
42
+ "layers.2.attn.sink_logit": "pytorch_model-00002-of-00025.safetensors",
43
+ "layers.2.attn.q.weight": "pytorch_model-00002-of-00025.safetensors",
44
+ "layers.2.attn.q.bias": "pytorch_model-00002-of-00025.safetensors",
45
+ "layers.2.attn.k.weight": "pytorch_model-00002-of-00025.safetensors",
46
+ "layers.2.attn.k.bias": "pytorch_model-00002-of-00025.safetensors",
47
+ "layers.2.attn.v.weight": "pytorch_model-00002-of-00025.safetensors",
48
+ "layers.2.attn.v.bias": "pytorch_model-00002-of-00025.safetensors",
49
+ "layers.2.attn.o.weight": "pytorch_model-00002-of-00025.safetensors",
50
+ "layers.2.attn.o.bias": "pytorch_model-00002-of-00025.safetensors",
51
+ "layers.2.norm2.weight": "pytorch_model-00002-of-00025.safetensors",
52
+ "layers.2.moe.W_in": "pytorch_model-00003-of-00025.safetensors",
53
+ "layers.2.moe.b_in": "pytorch_model-00003-of-00025.safetensors",
54
+ "layers.2.moe.W_out": "pytorch_model-00003-of-00025.safetensors",
55
+ "layers.2.moe.b_out": "pytorch_model-00003-of-00025.safetensors",
56
+ "layers.2.moe.router.weight": "pytorch_model-00003-of-00025.safetensors",
57
+ "layers.2.moe.router.bias": "pytorch_model-00003-of-00025.safetensors",
58
+ "layers.3.norm1.weight": "pytorch_model-00003-of-00025.safetensors",
59
+ "layers.3.attn.sink_logit": "pytorch_model-00003-of-00025.safetensors",
60
+ "layers.3.attn.q.weight": "pytorch_model-00003-of-00025.safetensors",
61
+ "layers.3.attn.q.bias": "pytorch_model-00003-of-00025.safetensors",
62
+ "layers.3.attn.k.weight": "pytorch_model-00003-of-00025.safetensors",
63
+ "layers.3.attn.k.bias": "pytorch_model-00003-of-00025.safetensors",
64
+ "layers.3.attn.v.weight": "pytorch_model-00003-of-00025.safetensors",
65
+ "layers.3.attn.v.bias": "pytorch_model-00003-of-00025.safetensors",
66
+ "layers.3.attn.o.weight": "pytorch_model-00003-of-00025.safetensors",
67
+ "layers.3.attn.o.bias": "pytorch_model-00003-of-00025.safetensors",
68
+ "layers.3.norm2.weight": "pytorch_model-00003-of-00025.safetensors",
69
+ "layers.3.moe.W_in": "pytorch_model-00004-of-00025.safetensors",
70
+ "layers.3.moe.b_in": "pytorch_model-00004-of-00025.safetensors",
71
+ "layers.3.moe.W_out": "pytorch_model-00004-of-00025.safetensors",
72
+ "layers.3.moe.b_out": "pytorch_model-00004-of-00025.safetensors",
73
+ "layers.3.moe.router.weight": "pytorch_model-00004-of-00025.safetensors",
74
+ "layers.3.moe.router.bias": "pytorch_model-00004-of-00025.safetensors",
75
+ "layers.4.norm1.weight": "pytorch_model-00004-of-00025.safetensors",
76
+ "layers.4.attn.sink_logit": "pytorch_model-00004-of-00025.safetensors",
77
+ "layers.4.attn.q.weight": "pytorch_model-00004-of-00025.safetensors",
78
+ "layers.4.attn.q.bias": "pytorch_model-00004-of-00025.safetensors",
79
+ "layers.4.attn.k.weight": "pytorch_model-00004-of-00025.safetensors",
80
+ "layers.4.attn.k.bias": "pytorch_model-00004-of-00025.safetensors",
81
+ "layers.4.attn.v.weight": "pytorch_model-00004-of-00025.safetensors",
82
+ "layers.4.attn.v.bias": "pytorch_model-00004-of-00025.safetensors",
83
+ "layers.4.attn.o.weight": "pytorch_model-00004-of-00025.safetensors",
84
+ "layers.4.attn.o.bias": "pytorch_model-00004-of-00025.safetensors",
85
+ "layers.4.norm2.weight": "pytorch_model-00004-of-00025.safetensors",
86
+ "layers.4.moe.W_in": "pytorch_model-00005-of-00025.safetensors",
87
+ "layers.4.moe.b_in": "pytorch_model-00005-of-00025.safetensors",
88
+ "layers.4.moe.W_out": "pytorch_model-00005-of-00025.safetensors",
89
+ "layers.4.moe.b_out": "pytorch_model-00005-of-00025.safetensors",
90
+ "layers.4.moe.router.weight": "pytorch_model-00005-of-00025.safetensors",
91
+ "layers.4.moe.router.bias": "pytorch_model-00005-of-00025.safetensors",
92
+ "layers.5.norm1.weight": "pytorch_model-00005-of-00025.safetensors",
93
+ "layers.5.attn.sink_logit": "pytorch_model-00005-of-00025.safetensors",
94
+ "layers.5.attn.q.weight": "pytorch_model-00005-of-00025.safetensors",
95
+ "layers.5.attn.q.bias": "pytorch_model-00005-of-00025.safetensors",
96
+ "layers.5.attn.k.weight": "pytorch_model-00005-of-00025.safetensors",
97
+ "layers.5.attn.k.bias": "pytorch_model-00005-of-00025.safetensors",
98
+ "layers.5.attn.v.weight": "pytorch_model-00005-of-00025.safetensors",
99
+ "layers.5.attn.v.bias": "pytorch_model-00005-of-00025.safetensors",
100
+ "layers.5.attn.o.weight": "pytorch_model-00005-of-00025.safetensors",
101
+ "layers.5.attn.o.bias": "pytorch_model-00005-of-00025.safetensors",
102
+ "layers.5.norm2.weight": "pytorch_model-00005-of-00025.safetensors",
103
+ "layers.5.moe.W_in": "pytorch_model-00006-of-00025.safetensors",
104
+ "layers.5.moe.b_in": "pytorch_model-00006-of-00025.safetensors",
105
+ "layers.5.moe.W_out": "pytorch_model-00006-of-00025.safetensors",
106
+ "layers.5.moe.b_out": "pytorch_model-00006-of-00025.safetensors",
107
+ "layers.5.moe.router.weight": "pytorch_model-00006-of-00025.safetensors",
108
+ "layers.5.moe.router.bias": "pytorch_model-00006-of-00025.safetensors",
109
+ "layers.6.norm1.weight": "pytorch_model-00006-of-00025.safetensors",
110
+ "layers.6.attn.sink_logit": "pytorch_model-00006-of-00025.safetensors",
111
+ "layers.6.attn.q.weight": "pytorch_model-00006-of-00025.safetensors",
112
+ "layers.6.attn.q.bias": "pytorch_model-00006-of-00025.safetensors",
113
+ "layers.6.attn.k.weight": "pytorch_model-00006-of-00025.safetensors",
114
+ "layers.6.attn.k.bias": "pytorch_model-00006-of-00025.safetensors",
115
+ "layers.6.attn.v.weight": "pytorch_model-00006-of-00025.safetensors",
116
+ "layers.6.attn.v.bias": "pytorch_model-00006-of-00025.safetensors",
117
+ "layers.6.attn.o.weight": "pytorch_model-00006-of-00025.safetensors",
118
+ "layers.6.attn.o.bias": "pytorch_model-00006-of-00025.safetensors",
119
+ "layers.6.norm2.weight": "pytorch_model-00006-of-00025.safetensors",
120
+ "layers.6.moe.W_in": "pytorch_model-00007-of-00025.safetensors",
121
+ "layers.6.moe.b_in": "pytorch_model-00007-of-00025.safetensors",
122
+ "layers.6.moe.W_out": "pytorch_model-00007-of-00025.safetensors",
123
+ "layers.6.moe.b_out": "pytorch_model-00007-of-00025.safetensors",
124
+ "layers.6.moe.router.weight": "pytorch_model-00007-of-00025.safetensors",
125
+ "layers.6.moe.router.bias": "pytorch_model-00007-of-00025.safetensors",
126
+ "layers.7.norm1.weight": "pytorch_model-00007-of-00025.safetensors",
127
+ "layers.7.attn.sink_logit": "pytorch_model-00007-of-00025.safetensors",
128
+ "layers.7.attn.q.weight": "pytorch_model-00007-of-00025.safetensors",
129
+ "layers.7.attn.q.bias": "pytorch_model-00007-of-00025.safetensors",
130
+ "layers.7.attn.k.weight": "pytorch_model-00007-of-00025.safetensors",
131
+ "layers.7.attn.k.bias": "pytorch_model-00007-of-00025.safetensors",
132
+ "layers.7.attn.v.weight": "pytorch_model-00007-of-00025.safetensors",
133
+ "layers.7.attn.v.bias": "pytorch_model-00007-of-00025.safetensors",
134
+ "layers.7.attn.o.weight": "pytorch_model-00007-of-00025.safetensors",
135
+ "layers.7.attn.o.bias": "pytorch_model-00007-of-00025.safetensors",
136
+ "layers.7.norm2.weight": "pytorch_model-00007-of-00025.safetensors",
137
+ "layers.7.moe.W_in": "pytorch_model-00008-of-00025.safetensors",
138
+ "layers.7.moe.b_in": "pytorch_model-00008-of-00025.safetensors",
139
+ "layers.7.moe.W_out": "pytorch_model-00008-of-00025.safetensors",
140
+ "layers.7.moe.b_out": "pytorch_model-00008-of-00025.safetensors",
141
+ "layers.7.moe.router.weight": "pytorch_model-00008-of-00025.safetensors",
142
+ "layers.7.moe.router.bias": "pytorch_model-00008-of-00025.safetensors",
143
+ "layers.8.norm1.weight": "pytorch_model-00008-of-00025.safetensors",
144
+ "layers.8.attn.sink_logit": "pytorch_model-00008-of-00025.safetensors",
145
+ "layers.8.attn.q.weight": "pytorch_model-00008-of-00025.safetensors",
146
+ "layers.8.attn.q.bias": "pytorch_model-00008-of-00025.safetensors",
147
+ "layers.8.attn.k.weight": "pytorch_model-00008-of-00025.safetensors",
148
+ "layers.8.attn.k.bias": "pytorch_model-00008-of-00025.safetensors",
149
+ "layers.8.attn.v.weight": "pytorch_model-00008-of-00025.safetensors",
150
+ "layers.8.attn.v.bias": "pytorch_model-00008-of-00025.safetensors",
151
+ "layers.8.attn.o.weight": "pytorch_model-00008-of-00025.safetensors",
152
+ "layers.8.attn.o.bias": "pytorch_model-00008-of-00025.safetensors",
153
+ "layers.8.norm2.weight": "pytorch_model-00008-of-00025.safetensors",
154
+ "layers.8.moe.W_in": "pytorch_model-00009-of-00025.safetensors",
155
+ "layers.8.moe.b_in": "pytorch_model-00009-of-00025.safetensors",
156
+ "layers.8.moe.W_out": "pytorch_model-00009-of-00025.safetensors",
157
+ "layers.8.moe.b_out": "pytorch_model-00009-of-00025.safetensors",
158
+ "layers.8.moe.router.weight": "pytorch_model-00009-of-00025.safetensors",
159
+ "layers.8.moe.router.bias": "pytorch_model-00009-of-00025.safetensors",
160
+ "layers.9.norm1.weight": "pytorch_model-00009-of-00025.safetensors",
161
+ "layers.9.attn.sink_logit": "pytorch_model-00009-of-00025.safetensors",
162
+ "layers.9.attn.q.weight": "pytorch_model-00009-of-00025.safetensors",
163
+ "layers.9.attn.q.bias": "pytorch_model-00009-of-00025.safetensors",
164
+ "layers.9.attn.k.weight": "pytorch_model-00009-of-00025.safetensors",
165
+ "layers.9.attn.k.bias": "pytorch_model-00009-of-00025.safetensors",
166
+ "layers.9.attn.v.weight": "pytorch_model-00009-of-00025.safetensors",
167
+ "layers.9.attn.v.bias": "pytorch_model-00009-of-00025.safetensors",
168
+ "layers.9.attn.o.weight": "pytorch_model-00009-of-00025.safetensors",
169
+ "layers.9.attn.o.bias": "pytorch_model-00009-of-00025.safetensors",
170
+ "layers.9.norm2.weight": "pytorch_model-00009-of-00025.safetensors",
171
+ "layers.9.moe.W_in": "pytorch_model-00010-of-00025.safetensors",
172
+ "layers.9.moe.b_in": "pytorch_model-00010-of-00025.safetensors",
173
+ "layers.9.moe.W_out": "pytorch_model-00010-of-00025.safetensors",
174
+ "layers.9.moe.b_out": "pytorch_model-00010-of-00025.safetensors",
175
+ "layers.9.moe.router.weight": "pytorch_model-00010-of-00025.safetensors",
176
+ "layers.9.moe.router.bias": "pytorch_model-00010-of-00025.safetensors",
177
+ "layers.10.norm1.weight": "pytorch_model-00010-of-00025.safetensors",
178
+ "layers.10.attn.sink_logit": "pytorch_model-00010-of-00025.safetensors",
179
+ "layers.10.attn.q.weight": "pytorch_model-00010-of-00025.safetensors",
180
+ "layers.10.attn.q.bias": "pytorch_model-00010-of-00025.safetensors",
181
+ "layers.10.attn.k.weight": "pytorch_model-00010-of-00025.safetensors",
182
+ "layers.10.attn.k.bias": "pytorch_model-00010-of-00025.safetensors",
183
+ "layers.10.attn.v.weight": "pytorch_model-00010-of-00025.safetensors",
184
+ "layers.10.attn.v.bias": "pytorch_model-00010-of-00025.safetensors",
185
+ "layers.10.attn.o.weight": "pytorch_model-00010-of-00025.safetensors",
186
+ "layers.10.attn.o.bias": "pytorch_model-00010-of-00025.safetensors",
187
+ "layers.10.norm2.weight": "pytorch_model-00010-of-00025.safetensors",
188
+ "layers.10.moe.W_in": "pytorch_model-00011-of-00025.safetensors",
189
+ "layers.10.moe.b_in": "pytorch_model-00011-of-00025.safetensors",
190
+ "layers.10.moe.W_out": "pytorch_model-00011-of-00025.safetensors",
191
+ "layers.10.moe.b_out": "pytorch_model-00011-of-00025.safetensors",
192
+ "layers.10.moe.router.weight": "pytorch_model-00011-of-00025.safetensors",
193
+ "layers.10.moe.router.bias": "pytorch_model-00011-of-00025.safetensors",
194
+ "layers.11.norm1.weight": "pytorch_model-00011-of-00025.safetensors",
195
+ "layers.11.attn.sink_logit": "pytorch_model-00011-of-00025.safetensors",
196
+ "layers.11.attn.q.weight": "pytorch_model-00011-of-00025.safetensors",
197
+ "layers.11.attn.q.bias": "pytorch_model-00011-of-00025.safetensors",
198
+ "layers.11.attn.k.weight": "pytorch_model-00011-of-00025.safetensors",
199
+ "layers.11.attn.k.bias": "pytorch_model-00011-of-00025.safetensors",
200
+ "layers.11.attn.v.weight": "pytorch_model-00011-of-00025.safetensors",
201
+ "layers.11.attn.v.bias": "pytorch_model-00011-of-00025.safetensors",
202
+ "layers.11.attn.o.weight": "pytorch_model-00011-of-00025.safetensors",
203
+ "layers.11.attn.o.bias": "pytorch_model-00011-of-00025.safetensors",
204
+ "layers.11.norm2.weight": "pytorch_model-00011-of-00025.safetensors",
205
+ "layers.11.moe.W_in": "pytorch_model-00012-of-00025.safetensors",
206
+ "layers.11.moe.b_in": "pytorch_model-00012-of-00025.safetensors",
207
+ "layers.11.moe.W_out": "pytorch_model-00012-of-00025.safetensors",
208
+ "layers.11.moe.b_out": "pytorch_model-00012-of-00025.safetensors",
209
+ "layers.11.moe.router.weight": "pytorch_model-00012-of-00025.safetensors",
210
+ "layers.11.moe.router.bias": "pytorch_model-00012-of-00025.safetensors",
211
+ "layers.12.norm1.weight": "pytorch_model-00012-of-00025.safetensors",
212
+ "layers.12.attn.sink_logit": "pytorch_model-00012-of-00025.safetensors",
213
+ "layers.12.attn.q.weight": "pytorch_model-00012-of-00025.safetensors",
214
+ "layers.12.attn.q.bias": "pytorch_model-00012-of-00025.safetensors",
215
+ "layers.12.attn.k.weight": "pytorch_model-00012-of-00025.safetensors",
216
+ "layers.12.attn.k.bias": "pytorch_model-00012-of-00025.safetensors",
217
+ "layers.12.attn.v.weight": "pytorch_model-00012-of-00025.safetensors",
218
+ "layers.12.attn.v.bias": "pytorch_model-00012-of-00025.safetensors",
219
+ "layers.12.attn.o.weight": "pytorch_model-00012-of-00025.safetensors",
220
+ "layers.12.attn.o.bias": "pytorch_model-00012-of-00025.safetensors",
221
+ "layers.12.norm2.weight": "pytorch_model-00012-of-00025.safetensors",
222
+ "layers.12.moe.W_in": "pytorch_model-00013-of-00025.safetensors",
223
+ "layers.12.moe.b_in": "pytorch_model-00013-of-00025.safetensors",
224
+ "layers.12.moe.W_out": "pytorch_model-00013-of-00025.safetensors",
225
+ "layers.12.moe.b_out": "pytorch_model-00013-of-00025.safetensors",
226
+ "layers.12.moe.router.weight": "pytorch_model-00013-of-00025.safetensors",
227
+ "layers.12.moe.router.bias": "pytorch_model-00013-of-00025.safetensors",
228
+ "layers.13.norm1.weight": "pytorch_model-00013-of-00025.safetensors",
229
+ "layers.13.attn.sink_logit": "pytorch_model-00013-of-00025.safetensors",
230
+ "layers.13.attn.q.weight": "pytorch_model-00013-of-00025.safetensors",
231
+ "layers.13.attn.q.bias": "pytorch_model-00013-of-00025.safetensors",
232
+ "layers.13.attn.k.weight": "pytorch_model-00013-of-00025.safetensors",
233
+ "layers.13.attn.k.bias": "pytorch_model-00013-of-00025.safetensors",
234
+ "layers.13.attn.v.weight": "pytorch_model-00013-of-00025.safetensors",
235
+ "layers.13.attn.v.bias": "pytorch_model-00013-of-00025.safetensors",
236
+ "layers.13.attn.o.weight": "pytorch_model-00013-of-00025.safetensors",
237
+ "layers.13.attn.o.bias": "pytorch_model-00013-of-00025.safetensors",
238
+ "layers.13.norm2.weight": "pytorch_model-00013-of-00025.safetensors",
239
+ "layers.13.moe.W_in": "pytorch_model-00014-of-00025.safetensors",
240
+ "layers.13.moe.b_in": "pytorch_model-00014-of-00025.safetensors",
241
+ "layers.13.moe.W_out": "pytorch_model-00014-of-00025.safetensors",
242
+ "layers.13.moe.b_out": "pytorch_model-00014-of-00025.safetensors",
243
+ "layers.13.moe.router.weight": "pytorch_model-00014-of-00025.safetensors",
244
+ "layers.13.moe.router.bias": "pytorch_model-00014-of-00025.safetensors",
245
+ "layers.14.norm1.weight": "pytorch_model-00014-of-00025.safetensors",
246
+ "layers.14.attn.sink_logit": "pytorch_model-00014-of-00025.safetensors",
247
+ "layers.14.attn.q.weight": "pytorch_model-00014-of-00025.safetensors",
248
+ "layers.14.attn.q.bias": "pytorch_model-00014-of-00025.safetensors",
249
+ "layers.14.attn.k.weight": "pytorch_model-00014-of-00025.safetensors",
250
+ "layers.14.attn.k.bias": "pytorch_model-00014-of-00025.safetensors",
251
+ "layers.14.attn.v.weight": "pytorch_model-00014-of-00025.safetensors",
252
+ "layers.14.attn.v.bias": "pytorch_model-00014-of-00025.safetensors",
253
+ "layers.14.attn.o.weight": "pytorch_model-00014-of-00025.safetensors",
254
+ "layers.14.attn.o.bias": "pytorch_model-00014-of-00025.safetensors",
255
+ "layers.14.norm2.weight": "pytorch_model-00014-of-00025.safetensors",
256
+ "layers.14.moe.W_in": "pytorch_model-00015-of-00025.safetensors",
257
+ "layers.14.moe.b_in": "pytorch_model-00015-of-00025.safetensors",
258
+ "layers.14.moe.W_out": "pytorch_model-00015-of-00025.safetensors",
259
+ "layers.14.moe.b_out": "pytorch_model-00015-of-00025.safetensors",
260
+ "layers.14.moe.router.weight": "pytorch_model-00015-of-00025.safetensors",
261
+ "layers.14.moe.router.bias": "pytorch_model-00015-of-00025.safetensors",
262
+ "layers.15.norm1.weight": "pytorch_model-00015-of-00025.safetensors",
263
+ "layers.15.attn.sink_logit": "pytorch_model-00015-of-00025.safetensors",
264
+ "layers.15.attn.q.weight": "pytorch_model-00015-of-00025.safetensors",
265
+ "layers.15.attn.q.bias": "pytorch_model-00015-of-00025.safetensors",
266
+ "layers.15.attn.k.weight": "pytorch_model-00015-of-00025.safetensors",
267
+ "layers.15.attn.k.bias": "pytorch_model-00015-of-00025.safetensors",
268
+ "layers.15.attn.v.weight": "pytorch_model-00015-of-00025.safetensors",
269
+ "layers.15.attn.v.bias": "pytorch_model-00015-of-00025.safetensors",
270
+ "layers.15.attn.o.weight": "pytorch_model-00015-of-00025.safetensors",
271
+ "layers.15.attn.o.bias": "pytorch_model-00015-of-00025.safetensors",
272
+ "layers.15.norm2.weight": "pytorch_model-00015-of-00025.safetensors",
273
+ "layers.15.moe.W_in": "pytorch_model-00016-of-00025.safetensors",
274
+ "layers.15.moe.b_in": "pytorch_model-00016-of-00025.safetensors",
275
+ "layers.15.moe.W_out": "pytorch_model-00016-of-00025.safetensors",
276
+ "layers.15.moe.b_out": "pytorch_model-00016-of-00025.safetensors",
277
+ "layers.15.moe.router.weight": "pytorch_model-00016-of-00025.safetensors",
278
+ "layers.15.moe.router.bias": "pytorch_model-00016-of-00025.safetensors",
279
+ "layers.16.norm1.weight": "pytorch_model-00016-of-00025.safetensors",
280
+ "layers.16.attn.sink_logit": "pytorch_model-00016-of-00025.safetensors",
281
+ "layers.16.attn.q.weight": "pytorch_model-00016-of-00025.safetensors",
282
+ "layers.16.attn.q.bias": "pytorch_model-00016-of-00025.safetensors",
283
+ "layers.16.attn.k.weight": "pytorch_model-00016-of-00025.safetensors",
284
+ "layers.16.attn.k.bias": "pytorch_model-00016-of-00025.safetensors",
285
+ "layers.16.attn.v.weight": "pytorch_model-00016-of-00025.safetensors",
286
+ "layers.16.attn.v.bias": "pytorch_model-00016-of-00025.safetensors",
287
+ "layers.16.attn.o.weight": "pytorch_model-00016-of-00025.safetensors",
288
+ "layers.16.attn.o.bias": "pytorch_model-00016-of-00025.safetensors",
289
+ "layers.16.norm2.weight": "pytorch_model-00016-of-00025.safetensors",
290
+ "layers.16.moe.W_in": "pytorch_model-00017-of-00025.safetensors",
291
+ "layers.16.moe.b_in": "pytorch_model-00017-of-00025.safetensors",
292
+ "layers.16.moe.W_out": "pytorch_model-00017-of-00025.safetensors",
293
+ "layers.16.moe.b_out": "pytorch_model-00017-of-00025.safetensors",
294
+ "layers.16.moe.router.weight": "pytorch_model-00017-of-00025.safetensors",
295
+ "layers.16.moe.router.bias": "pytorch_model-00017-of-00025.safetensors",
296
+ "layers.17.norm1.weight": "pytorch_model-00017-of-00025.safetensors",
297
+ "layers.17.attn.sink_logit": "pytorch_model-00017-of-00025.safetensors",
298
+ "layers.17.attn.q.weight": "pytorch_model-00017-of-00025.safetensors",
299
+ "layers.17.attn.q.bias": "pytorch_model-00017-of-00025.safetensors",
300
+ "layers.17.attn.k.weight": "pytorch_model-00017-of-00025.safetensors",
301
+ "layers.17.attn.k.bias": "pytorch_model-00017-of-00025.safetensors",
302
+ "layers.17.attn.v.weight": "pytorch_model-00017-of-00025.safetensors",
303
+ "layers.17.attn.v.bias": "pytorch_model-00017-of-00025.safetensors",
304
+ "layers.17.attn.o.weight": "pytorch_model-00017-of-00025.safetensors",
305
+ "layers.17.attn.o.bias": "pytorch_model-00017-of-00025.safetensors",
306
+ "layers.17.norm2.weight": "pytorch_model-00017-of-00025.safetensors",
307
+ "layers.17.moe.W_in": "pytorch_model-00018-of-00025.safetensors",
308
+ "layers.17.moe.b_in": "pytorch_model-00018-of-00025.safetensors",
309
+ "layers.17.moe.W_out": "pytorch_model-00018-of-00025.safetensors",
310
+ "layers.17.moe.b_out": "pytorch_model-00018-of-00025.safetensors",
311
+ "layers.17.moe.router.weight": "pytorch_model-00018-of-00025.safetensors",
312
+ "layers.17.moe.router.bias": "pytorch_model-00018-of-00025.safetensors",
313
+ "layers.18.norm1.weight": "pytorch_model-00018-of-00025.safetensors",
314
+ "layers.18.attn.sink_logit": "pytorch_model-00018-of-00025.safetensors",
315
+ "layers.18.attn.q.weight": "pytorch_model-00018-of-00025.safetensors",
316
+ "layers.18.attn.q.bias": "pytorch_model-00018-of-00025.safetensors",
317
+ "layers.18.attn.k.weight": "pytorch_model-00018-of-00025.safetensors",
318
+ "layers.18.attn.k.bias": "pytorch_model-00018-of-00025.safetensors",
319
+ "layers.18.attn.v.weight": "pytorch_model-00018-of-00025.safetensors",
320
+ "layers.18.attn.v.bias": "pytorch_model-00018-of-00025.safetensors",
321
+ "layers.18.attn.o.weight": "pytorch_model-00018-of-00025.safetensors",
322
+ "layers.18.attn.o.bias": "pytorch_model-00018-of-00025.safetensors",
323
+ "layers.18.norm2.weight": "pytorch_model-00018-of-00025.safetensors",
324
+ "layers.18.moe.W_in": "pytorch_model-00019-of-00025.safetensors",
325
+ "layers.18.moe.b_in": "pytorch_model-00019-of-00025.safetensors",
326
+ "layers.18.moe.W_out": "pytorch_model-00019-of-00025.safetensors",
327
+ "layers.18.moe.b_out": "pytorch_model-00019-of-00025.safetensors",
328
+ "layers.18.moe.router.weight": "pytorch_model-00019-of-00025.safetensors",
329
+ "layers.18.moe.router.bias": "pytorch_model-00019-of-00025.safetensors",
330
+ "layers.19.norm1.weight": "pytorch_model-00019-of-00025.safetensors",
331
+ "layers.19.attn.sink_logit": "pytorch_model-00019-of-00025.safetensors",
332
+ "layers.19.attn.q.weight": "pytorch_model-00019-of-00025.safetensors",
333
+ "layers.19.attn.q.bias": "pytorch_model-00019-of-00025.safetensors",
334
+ "layers.19.attn.k.weight": "pytorch_model-00019-of-00025.safetensors",
335
+ "layers.19.attn.k.bias": "pytorch_model-00019-of-00025.safetensors",
336
+ "layers.19.attn.v.weight": "pytorch_model-00019-of-00025.safetensors",
337
+ "layers.19.attn.v.bias": "pytorch_model-00019-of-00025.safetensors",
338
+ "layers.19.attn.o.weight": "pytorch_model-00019-of-00025.safetensors",
339
+ "layers.19.attn.o.bias": "pytorch_model-00019-of-00025.safetensors",
340
+ "layers.19.norm2.weight": "pytorch_model-00019-of-00025.safetensors",
341
+ "layers.19.moe.W_in": "pytorch_model-00020-of-00025.safetensors",
342
+ "layers.19.moe.b_in": "pytorch_model-00020-of-00025.safetensors",
343
+ "layers.19.moe.W_out": "pytorch_model-00020-of-00025.safetensors",
344
+ "layers.19.moe.b_out": "pytorch_model-00020-of-00025.safetensors",
345
+ "layers.19.moe.router.weight": "pytorch_model-00020-of-00025.safetensors",
346
+ "layers.19.moe.router.bias": "pytorch_model-00020-of-00025.safetensors",
347
+ "layers.20.norm1.weight": "pytorch_model-00020-of-00025.safetensors",
348
+ "layers.20.attn.sink_logit": "pytorch_model-00020-of-00025.safetensors",
349
+ "layers.20.attn.q.weight": "pytorch_model-00020-of-00025.safetensors",
350
+ "layers.20.attn.q.bias": "pytorch_model-00020-of-00025.safetensors",
351
+ "layers.20.attn.k.weight": "pytorch_model-00020-of-00025.safetensors",
352
+ "layers.20.attn.k.bias": "pytorch_model-00020-of-00025.safetensors",
353
+ "layers.20.attn.v.weight": "pytorch_model-00020-of-00025.safetensors",
354
+ "layers.20.attn.v.bias": "pytorch_model-00020-of-00025.safetensors",
355
+ "layers.20.attn.o.weight": "pytorch_model-00020-of-00025.safetensors",
356
+ "layers.20.attn.o.bias": "pytorch_model-00020-of-00025.safetensors",
357
+ "layers.20.norm2.weight": "pytorch_model-00020-of-00025.safetensors",
358
+ "layers.20.moe.W_in": "pytorch_model-00021-of-00025.safetensors",
359
+ "layers.20.moe.b_in": "pytorch_model-00021-of-00025.safetensors",
360
+ "layers.20.moe.W_out": "pytorch_model-00021-of-00025.safetensors",
361
+ "layers.20.moe.b_out": "pytorch_model-00021-of-00025.safetensors",
362
+ "layers.20.moe.router.weight": "pytorch_model-00021-of-00025.safetensors",
363
+ "layers.20.moe.router.bias": "pytorch_model-00021-of-00025.safetensors",
364
+ "layers.21.norm1.weight": "pytorch_model-00021-of-00025.safetensors",
365
+ "layers.21.attn.sink_logit": "pytorch_model-00021-of-00025.safetensors",
366
+ "layers.21.attn.q.weight": "pytorch_model-00021-of-00025.safetensors",
367
+ "layers.21.attn.q.bias": "pytorch_model-00021-of-00025.safetensors",
368
+ "layers.21.attn.k.weight": "pytorch_model-00021-of-00025.safetensors",
369
+ "layers.21.attn.k.bias": "pytorch_model-00021-of-00025.safetensors",
370
+ "layers.21.attn.v.weight": "pytorch_model-00021-of-00025.safetensors",
371
+ "layers.21.attn.v.bias": "pytorch_model-00021-of-00025.safetensors",
372
+ "layers.21.attn.o.weight": "pytorch_model-00021-of-00025.safetensors",
373
+ "layers.21.attn.o.bias": "pytorch_model-00021-of-00025.safetensors",
374
+ "layers.21.norm2.weight": "pytorch_model-00021-of-00025.safetensors",
375
+ "layers.21.moe.W_in": "pytorch_model-00022-of-00025.safetensors",
376
+ "layers.21.moe.b_in": "pytorch_model-00022-of-00025.safetensors",
377
+ "layers.21.moe.W_out": "pytorch_model-00022-of-00025.safetensors",
378
+ "layers.21.moe.b_out": "pytorch_model-00022-of-00025.safetensors",
379
+ "layers.21.moe.router.weight": "pytorch_model-00022-of-00025.safetensors",
380
+ "layers.21.moe.router.bias": "pytorch_model-00022-of-00025.safetensors",
381
+ "layers.22.norm1.weight": "pytorch_model-00022-of-00025.safetensors",
382
+ "layers.22.attn.sink_logit": "pytorch_model-00022-of-00025.safetensors",
383
+ "layers.22.attn.q.weight": "pytorch_model-00022-of-00025.safetensors",
384
+ "layers.22.attn.q.bias": "pytorch_model-00022-of-00025.safetensors",
385
+ "layers.22.attn.k.weight": "pytorch_model-00022-of-00025.safetensors",
386
+ "layers.22.attn.k.bias": "pytorch_model-00022-of-00025.safetensors",
387
+ "layers.22.attn.v.weight": "pytorch_model-00022-of-00025.safetensors",
388
+ "layers.22.attn.v.bias": "pytorch_model-00022-of-00025.safetensors",
389
+ "layers.22.attn.o.weight": "pytorch_model-00022-of-00025.safetensors",
390
+ "layers.22.attn.o.bias": "pytorch_model-00022-of-00025.safetensors",
391
+ "layers.22.norm2.weight": "pytorch_model-00022-of-00025.safetensors",
392
+ "layers.22.moe.W_in": "pytorch_model-00023-of-00025.safetensors",
393
+ "layers.22.moe.b_in": "pytorch_model-00023-of-00025.safetensors",
394
+ "layers.22.moe.W_out": "pytorch_model-00023-of-00025.safetensors",
395
+ "layers.22.moe.b_out": "pytorch_model-00023-of-00025.safetensors",
396
+ "layers.22.moe.router.weight": "pytorch_model-00023-of-00025.safetensors",
397
+ "layers.22.moe.router.bias": "pytorch_model-00023-of-00025.safetensors",
398
+ "layers.23.norm1.weight": "pytorch_model-00023-of-00025.safetensors",
399
+ "layers.23.attn.sink_logit": "pytorch_model-00023-of-00025.safetensors",
400
+ "layers.23.attn.q.weight": "pytorch_model-00023-of-00025.safetensors",
401
+ "layers.23.attn.q.bias": "pytorch_model-00023-of-00025.safetensors",
402
+ "layers.23.attn.k.weight": "pytorch_model-00023-of-00025.safetensors",
403
+ "layers.23.attn.k.bias": "pytorch_model-00023-of-00025.safetensors",
404
+ "layers.23.attn.v.weight": "pytorch_model-00023-of-00025.safetensors",
405
+ "layers.23.attn.v.bias": "pytorch_model-00023-of-00025.safetensors",
406
+ "layers.23.attn.o.weight": "pytorch_model-00023-of-00025.safetensors",
407
+ "layers.23.attn.o.bias": "pytorch_model-00023-of-00025.safetensors",
408
+ "layers.23.norm2.weight": "pytorch_model-00023-of-00025.safetensors",
409
+ "layers.23.moe.W_in": "pytorch_model-00024-of-00025.safetensors",
410
+ "layers.23.moe.b_in": "pytorch_model-00024-of-00025.safetensors",
411
+ "layers.23.moe.W_out": "pytorch_model-00024-of-00025.safetensors",
412
+ "layers.23.moe.b_out": "pytorch_model-00024-of-00025.safetensors",
413
+ "layers.23.moe.router.weight": "pytorch_model-00024-of-00025.safetensors",
414
+ "layers.23.moe.router.bias": "pytorch_model-00024-of-00025.safetensors",
415
+ "norm_f.weight": "pytorch_model-00024-of-00025.safetensors",
416
+ "lm_head.weight": "pytorch_model-00025-of-00025.safetensors"
417
+ }
418
+ }
pytorch_model-00001-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7304cab966f4fbf176044d1eca017100b4e6033d2be0352007f130dec33a175
3
+ size 4546862392
pytorch_model-00002-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3258474d3bc1406c60d9d51eb572e33d2bf7f5c2b5b6ee1f6fc7073bad35d93c
3
+ size 4461395208
pytorch_model-00003-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384b517b5a6348822e8acdd8d214f90fc86677e8dadbc47dbc0fb96cde4f848a
3
+ size 3292749536
pytorch_model-00004-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df785715013a1bc5dc3b8c7a7bff012865d15325336fcc42c72e68b77b3f63b1
3
+ size 3292749536
pytorch_model-00005-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cceba6e7b10f73028ed4fd90aa264b0c12725acf8c042e452d2624315d6bcbb0
3
+ size 3292749536
pytorch_model-00006-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e375cb2ba7accbb0e449584458230a595e1a37ab0a8bd9f31ec8f9ba3885c1e
3
+ size 3292749536
pytorch_model-00007-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8423eec59724ebb1f17d8f37365df9ee5014d2c707b9b669eb007e960d0325
3
+ size 3292749536
pytorch_model-00008-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014b5273efab46130635cba49a47358c2c907c2f8372c7711a7307b72bf1047a
3
+ size 3292749536
pytorch_model-00009-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4ef6add2faf97b80e6e205ad7887a81bd62647b40952e33fe9286d612bf073
3
+ size 3292749536
pytorch_model-00010-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1be1abdf86b1ab0400d0576e9ec4f787ca6f7f0f0186faf17fc9ccaf77ce76a
3
+ size 3292749504
pytorch_model-00011-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a893fd452f95857f139af73abda018fb9adac0dc6e8bee107e45af20595a04d
3
+ size 3292749560
pytorch_model-00012-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff78d4af0082b234b4ae607701ce20011241d5e24e7d2c4858ac4fefb076e82
3
+ size 3292749560
pytorch_model-00013-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bef68e2cde634a1da62ff40f028a25b06ae9ef63e9763bef651e58ff91459f9
3
+ size 3292749560
pytorch_model-00014-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c777d88b3fb638c6b6bd88160d4ae17ba596b6e857fcaee94f80c5e80cb5f85c
3
+ size 3292749560
pytorch_model-00015-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4cebab3c4bbcc6933bb16a10744662fef77e401cb3dd036bf95eef3bdb8d7f6
3
+ size 3292749560
pytorch_model-00016-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f9877ac0a0a3ca881779b194e654ee5aaae992e8badd5444e10d508536d7d4
3
+ size 3292749560
pytorch_model-00017-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d265d67a83108d4f23a20eda24d53594b1f1d9e149f66626d8d433e63a0c09
3
+ size 3292749560
pytorch_model-00018-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b294a82e6a2f21304da98f73cbb0abdab0b3d44ffe37ee58e09e6b92086d5f
3
+ size 3292749560
pytorch_model-00019-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1806a45f0d631c964d4b52f6f439cd3dba98c5d39650473fc89125966062ec7b
3
+ size 3292749560
pytorch_model-00020-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5be084cc55b7964e63a9d116a9f05d4c32e16d9c1587664e229905b758de182
3
+ size 3292749560
pytorch_model-00021-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd2a1b6faf5e1509645bd0c630bc2ddfa49bad40d9ac8d9879f982e5d3764bf
3
+ size 3292749560
pytorch_model-00022-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64007dfd79b4cc2248edb5517d8fe22a8b0d8d3f56e63c01a3d53cd766c6c3e7
3
+ size 3292749560
pytorch_model-00023-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d2b575343fb63c01f98d0cee6505fa0ac117556bd7b05fd89925b7aaa4c01e
3
+ size 3292749560
pytorch_model-00024-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1caba23470a91debf9f3b42615025095573cb0bce0d7c35580f6c818efbc1b13
3
+ size 3186536488
pytorch_model-00025-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a9b40c3cd701ed524391f774ddb5940047e84f15009a1903fe37d3fe4697e6f
3
+ size 2316533856