Hugging Face's logo

liminerity
/
MoR-deep

Safetensors
MoR
Model card Files
xet
Community
gate369 commited on
Commit
46c8f97
·
verified ·
1 Parent(s): f7e6f23

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +13 -0
  2. model.safetensors +3 -0
  3. model.safetensors.index.json +136 -0
  4. special_tokens_map.json +6 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +44 -0
config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 10000,
3
+ "dim": 1536,
4
+ "num_layers": 6,
5
+ "num_heads": 8,
6
+ "max_recursion": 4,
7
+ "num_experts": 4,
8
+ "ffn_expansion": 4,
9
+ "max_position_embeddings": 2048,
10
+ "model_type": "MoR",
11
+ "architecture": "MixtureOfRecursions",
12
+ "hidden_act": "gelu"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffef272065914fdd8b21ddf788758a8a810a65c5c9f0892253ad765ff7296ac9
3
+ size 948001512
model.safetensors.index.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 947988512
4
+ },
5
+ "weight_map": {
6
+ "embedding.weight": "model.safetensors",
7
+ "pos_embed.weight": "model.safetensors",
8
+ "init_layers.0.q_proj.weight": "model.safetensors",
9
+ "init_layers.0.q_proj.bias": "model.safetensors",
10
+ "init_layers.0.k_proj.weight": "model.safetensors",
11
+ "init_layers.0.k_proj.bias": "model.safetensors",
12
+ "init_layers.0.v_proj.weight": "model.safetensors",
13
+ "init_layers.0.v_proj.bias": "model.safetensors",
14
+ "init_layers.0.attn_out.weight": "model.safetensors",
15
+ "init_layers.0.attn_out.bias": "model.safetensors",
16
+ "init_layers.0.ffn.0.weight": "model.safetensors",
17
+ "init_layers.0.ffn.0.bias": "model.safetensors",
18
+ "init_layers.0.ffn.2.weight": "model.safetensors",
19
+ "init_layers.0.ffn.2.bias": "model.safetensors",
20
+ "init_layers.0.norm1.weight": "model.safetensors",
21
+ "init_layers.0.norm1.bias": "model.safetensors",
22
+ "init_layers.0.norm2.weight": "model.safetensors",
23
+ "init_layers.0.norm2.bias": "model.safetensors",
24
+ "init_layers.1.q_proj.weight": "model.safetensors",
25
+ "init_layers.1.q_proj.bias": "model.safetensors",
26
+ "init_layers.1.k_proj.weight": "model.safetensors",
27
+ "init_layers.1.k_proj.bias": "model.safetensors",
28
+ "init_layers.1.v_proj.weight": "model.safetensors",
29
+ "init_layers.1.v_proj.bias": "model.safetensors",
30
+ "init_layers.1.attn_out.weight": "model.safetensors",
31
+ "init_layers.1.attn_out.bias": "model.safetensors",
32
+ "init_layers.1.ffn.0.weight": "model.safetensors",
33
+ "init_layers.1.ffn.0.bias": "model.safetensors",
34
+ "init_layers.1.ffn.2.weight": "model.safetensors",
35
+ "init_layers.1.ffn.2.bias": "model.safetensors",
36
+ "init_layers.1.norm1.weight": "model.safetensors",
37
+ "init_layers.1.norm1.bias": "model.safetensors",
38
+ "init_layers.1.norm2.weight": "model.safetensors",
39
+ "init_layers.1.norm2.bias": "model.safetensors",
40
+ "recursive_blocks.0.q_proj.weight": "model.safetensors",
41
+ "recursive_blocks.0.q_proj.bias": "model.safetensors",
42
+ "recursive_blocks.0.k_proj.weight": "model.safetensors",
43
+ "recursive_blocks.0.k_proj.bias": "model.safetensors",
44
+ "recursive_blocks.0.v_proj.weight": "model.safetensors",
45
+ "recursive_blocks.0.v_proj.bias": "model.safetensors",
46
+ "recursive_blocks.0.attn_out.weight": "model.safetensors",
47
+ "recursive_blocks.0.attn_out.bias": "model.safetensors",
48
+ "recursive_blocks.0.ffn.0.weight": "model.safetensors",
49
+ "recursive_blocks.0.ffn.0.bias": "model.safetensors",
50
+ "recursive_blocks.0.ffn.2.weight": "model.safetensors",
51
+ "recursive_blocks.0.ffn.2.bias": "model.safetensors",
52
+ "recursive_blocks.0.norm1.weight": "model.safetensors",
53
+ "recursive_blocks.0.norm1.bias": "model.safetensors",
54
+ "recursive_blocks.0.norm2.weight": "model.safetensors",
55
+ "recursive_blocks.0.norm2.bias": "model.safetensors",
56
+ "recursive_blocks.1.q_proj.weight": "model.safetensors",
57
+ "recursive_blocks.1.q_proj.bias": "model.safetensors",
58
+ "recursive_blocks.1.k_proj.weight": "model.safetensors",
59
+ "recursive_blocks.1.k_proj.bias": "model.safetensors",
60
+ "recursive_blocks.1.v_proj.weight": "model.safetensors",
61
+ "recursive_blocks.1.v_proj.bias": "model.safetensors",
62
+ "recursive_blocks.1.attn_out.weight": "model.safetensors",
63
+ "recursive_blocks.1.attn_out.bias": "model.safetensors",
64
+ "recursive_blocks.1.ffn.0.weight": "model.safetensors",
65
+ "recursive_blocks.1.ffn.0.bias": "model.safetensors",
66
+ "recursive_blocks.1.ffn.2.weight": "model.safetensors",
67
+ "recursive_blocks.1.ffn.2.bias": "model.safetensors",
68
+ "recursive_blocks.1.norm1.weight": "model.safetensors",
69
+ "recursive_blocks.1.norm1.bias": "model.safetensors",
70
+ "recursive_blocks.1.norm2.weight": "model.safetensors",
71
+ "recursive_blocks.1.norm2.bias": "model.safetensors",
72
+ "recursive_blocks.2.q_proj.weight": "model.safetensors",
73
+ "recursive_blocks.2.q_proj.bias": "model.safetensors",
74
+ "recursive_blocks.2.k_proj.weight": "model.safetensors",
75
+ "recursive_blocks.2.k_proj.bias": "model.safetensors",
76
+ "recursive_blocks.2.v_proj.weight": "model.safetensors",
77
+ "recursive_blocks.2.v_proj.bias": "model.safetensors",
78
+ "recursive_blocks.2.attn_out.weight": "model.safetensors",
79
+ "recursive_blocks.2.attn_out.bias": "model.safetensors",
80
+ "recursive_blocks.2.ffn.0.weight": "model.safetensors",
81
+ "recursive_blocks.2.ffn.0.bias": "model.safetensors",
82
+ "recursive_blocks.2.ffn.2.weight": "model.safetensors",
83
+ "recursive_blocks.2.ffn.2.bias": "model.safetensors",
84
+ "recursive_blocks.2.norm1.weight": "model.safetensors",
85
+ "recursive_blocks.2.norm1.bias": "model.safetensors",
86
+ "recursive_blocks.2.norm2.weight": "model.safetensors",
87
+ "recursive_blocks.2.norm2.bias": "model.safetensors",
88
+ "recursion_routers.0.router.0.weight": "model.safetensors",
89
+ "recursion_routers.0.router.0.bias": "model.safetensors",
90
+ "recursion_routers.0.router.2.weight": "model.safetensors",
91
+ "recursion_routers.0.router.2.bias": "model.safetensors",
92
+ "recursion_routers.1.router.0.weight": "model.safetensors",
93
+ "recursion_routers.1.router.0.bias": "model.safetensors",
94
+ "recursion_routers.1.router.2.weight": "model.safetensors",
95
+ "recursion_routers.1.router.2.bias": "model.safetensors",
96
+ "expert_routers.0.gate.weight": "model.safetensors",
97
+ "expert_routers.1.gate.weight": "model.safetensors",
98
+ "expert_routers.2.gate.weight": "model.safetensors",
99
+ "expert_routers.3.gate.weight": "model.safetensors",
100
+ "final_layers.0.q_proj.weight": "model.safetensors",
101
+ "final_layers.0.q_proj.bias": "model.safetensors",
102
+ "final_layers.0.k_proj.weight": "model.safetensors",
103
+ "final_layers.0.k_proj.bias": "model.safetensors",
104
+ "final_layers.0.v_proj.weight": "model.safetensors",
105
+ "final_layers.0.v_proj.bias": "model.safetensors",
106
+ "final_layers.0.attn_out.weight": "model.safetensors",
107
+ "final_layers.0.attn_out.bias": "model.safetensors",
108
+ "final_layers.0.ffn.0.weight": "model.safetensors",
109
+ "final_layers.0.ffn.0.bias": "model.safetensors",
110
+ "final_layers.0.ffn.2.weight": "model.safetensors",
111
+ "final_layers.0.ffn.2.bias": "model.safetensors",
112
+ "final_layers.0.norm1.weight": "model.safetensors",
113
+ "final_layers.0.norm1.bias": "model.safetensors",
114
+ "final_layers.0.norm2.weight": "model.safetensors",
115
+ "final_layers.0.norm2.bias": "model.safetensors",
116
+ "final_layers.1.q_proj.weight": "model.safetensors",
117
+ "final_layers.1.q_proj.bias": "model.safetensors",
118
+ "final_layers.1.k_proj.weight": "model.safetensors",
119
+ "final_layers.1.k_proj.bias": "model.safetensors",
120
+ "final_layers.1.v_proj.weight": "model.safetensors",
121
+ "final_layers.1.v_proj.bias": "model.safetensors",
122
+ "final_layers.1.attn_out.weight": "model.safetensors",
123
+ "final_layers.1.attn_out.bias": "model.safetensors",
124
+ "final_layers.1.ffn.0.weight": "model.safetensors",
125
+ "final_layers.1.ffn.0.bias": "model.safetensors",
126
+ "final_layers.1.ffn.2.weight": "model.safetensors",
127
+ "final_layers.1.ffn.2.bias": "model.safetensors",
128
+ "final_layers.1.norm1.weight": "model.safetensors",
129
+ "final_layers.1.norm1.bias": "model.safetensors",
130
+ "final_layers.1.norm2.weight": "model.safetensors",
131
+ "final_layers.1.norm2.bias": "model.safetensors",
132
+ "ln_f.weight": "model.safetensors",
133
+ "ln_f.bias": "model.safetensors",
134
+ "head.weight": "model.safetensors"
135
+ }
136
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[BOS]",
3
+ "eos_token": "[EOS]",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[BOS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[EOS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "[BOS]",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "[EOS]",
39
+ "extra_special_tokens": {},
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "tokenizer_class": "PreTrainedTokenizerFast",
43
+ "unk_token": "[UNK]"
44
+ }