Hugging Face's logo

liminerity
/
MoR-TC-v2.3.1-ts

Safetensors
MoR
Model card Files Community
gate369 commited on
Commit
bfe541b
·
verified ·
1 Parent(s): 58e5f1e

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +15 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. model.safetensors.index.json +116 -0
  5. special_tokens_map.json +6 -0
  6. tokenizer_config.json +8 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 50257,
3
+ "dim": 1024,
4
+ "num_layers": 6,
5
+ "num_heads": 16,
6
+ "max_recursion": 4,
7
+ "ffn_expansion": 4,
8
+ "max_position_embeddings": 1024,
9
+ "balancing_weight": 0.01,
10
+ "temperature": 1.0,
11
+ "window_size": 512,
12
+ "model_type": "MoR",
13
+ "architecture": "MixtureOfRecursions",
14
+ "hidden_act": "gelu"
15
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f898c50488071bb2e17bd89a47a3be701a5cb1a48d0a1cc2bdabc0e23b3152
3
+ size 724542240
model.safetensors.index.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 724531216
4
+ },
5
+ "weight_map": {
6
+ "embed.weight": "model.safetensors",
7
+ "pos_embed.weight": "model.safetensors",
8
+ "first_layer.0.weight": "model.safetensors",
9
+ "first_layer.0.bias": "model.safetensors",
10
+ "first_layer.2.weight": "model.safetensors",
11
+ "first_layer.2.bias": "model.safetensors",
12
+ "recursive_layers.0.w_q.weight": "model.safetensors",
13
+ "recursive_layers.0.w_q.bias": "model.safetensors",
14
+ "recursive_layers.0.w_k.weight": "model.safetensors",
15
+ "recursive_layers.0.w_k.bias": "model.safetensors",
16
+ "recursive_layers.0.w_v.weight": "model.safetensors",
17
+ "recursive_layers.0.w_v.bias": "model.safetensors",
18
+ "recursive_layers.0.attn_out.weight": "model.safetensors",
19
+ "recursive_layers.0.attn_out.bias": "model.safetensors",
20
+ "recursive_layers.0.ffn.0.weight": "model.safetensors",
21
+ "recursive_layers.0.ffn.0.bias": "model.safetensors",
22
+ "recursive_layers.0.ffn.2.weight": "model.safetensors",
23
+ "recursive_layers.0.ffn.2.bias": "model.safetensors",
24
+ "recursive_layers.0.norm1.weight": "model.safetensors",
25
+ "recursive_layers.0.norm1.bias": "model.safetensors",
26
+ "recursive_layers.0.norm2.weight": "model.safetensors",
27
+ "recursive_layers.0.norm2.bias": "model.safetensors",
28
+ "recursive_layers.1.w_q.weight": "model.safetensors",
29
+ "recursive_layers.1.w_q.bias": "model.safetensors",
30
+ "recursive_layers.1.w_k.weight": "model.safetensors",
31
+ "recursive_layers.1.w_k.bias": "model.safetensors",
32
+ "recursive_layers.1.w_v.weight": "model.safetensors",
33
+ "recursive_layers.1.w_v.bias": "model.safetensors",
34
+ "recursive_layers.1.attn_out.weight": "model.safetensors",
35
+ "recursive_layers.1.attn_out.bias": "model.safetensors",
36
+ "recursive_layers.1.ffn.0.weight": "model.safetensors",
37
+ "recursive_layers.1.ffn.0.bias": "model.safetensors",
38
+ "recursive_layers.1.ffn.2.weight": "model.safetensors",
39
+ "recursive_layers.1.ffn.2.bias": "model.safetensors",
40
+ "recursive_layers.1.norm1.weight": "model.safetensors",
41
+ "recursive_layers.1.norm1.bias": "model.safetensors",
42
+ "recursive_layers.1.norm2.weight": "model.safetensors",
43
+ "recursive_layers.1.norm2.bias": "model.safetensors",
44
+ "recursive_layers.2.w_q.weight": "model.safetensors",
45
+ "recursive_layers.2.w_q.bias": "model.safetensors",
46
+ "recursive_layers.2.w_k.weight": "model.safetensors",
47
+ "recursive_layers.2.w_k.bias": "model.safetensors",
48
+ "recursive_layers.2.w_v.weight": "model.safetensors",
49
+ "recursive_layers.2.w_v.bias": "model.safetensors",
50
+ "recursive_layers.2.attn_out.weight": "model.safetensors",
51
+ "recursive_layers.2.attn_out.bias": "model.safetensors",
52
+ "recursive_layers.2.ffn.0.weight": "model.safetensors",
53
+ "recursive_layers.2.ffn.0.bias": "model.safetensors",
54
+ "recursive_layers.2.ffn.2.weight": "model.safetensors",
55
+ "recursive_layers.2.ffn.2.bias": "model.safetensors",
56
+ "recursive_layers.2.norm1.weight": "model.safetensors",
57
+ "recursive_layers.2.norm1.bias": "model.safetensors",
58
+ "recursive_layers.2.norm2.weight": "model.safetensors",
59
+ "recursive_layers.2.norm2.bias": "model.safetensors",
60
+ "recursive_layers.3.w_q.weight": "model.safetensors",
61
+ "recursive_layers.3.w_q.bias": "model.safetensors",
62
+ "recursive_layers.3.w_k.weight": "model.safetensors",
63
+ "recursive_layers.3.w_k.bias": "model.safetensors",
64
+ "recursive_layers.3.w_v.weight": "model.safetensors",
65
+ "recursive_layers.3.w_v.bias": "model.safetensors",
66
+ "recursive_layers.3.attn_out.weight": "model.safetensors",
67
+ "recursive_layers.3.attn_out.bias": "model.safetensors",
68
+ "recursive_layers.3.ffn.0.weight": "model.safetensors",
69
+ "recursive_layers.3.ffn.0.bias": "model.safetensors",
70
+ "recursive_layers.3.ffn.2.weight": "model.safetensors",
71
+ "recursive_layers.3.ffn.2.bias": "model.safetensors",
72
+ "recursive_layers.3.norm1.weight": "model.safetensors",
73
+ "recursive_layers.3.norm1.bias": "model.safetensors",
74
+ "recursive_layers.3.norm2.weight": "model.safetensors",
75
+ "recursive_layers.3.norm2.bias": "model.safetensors",
76
+ "recursive_layers.4.w_q.weight": "model.safetensors",
77
+ "recursive_layers.4.w_q.bias": "model.safetensors",
78
+ "recursive_layers.4.w_k.weight": "model.safetensors",
79
+ "recursive_layers.4.w_k.bias": "model.safetensors",
80
+ "recursive_layers.4.w_v.weight": "model.safetensors",
81
+ "recursive_layers.4.w_v.bias": "model.safetensors",
82
+ "recursive_layers.4.attn_out.weight": "model.safetensors",
83
+ "recursive_layers.4.attn_out.bias": "model.safetensors",
84
+ "recursive_layers.4.ffn.0.weight": "model.safetensors",
85
+ "recursive_layers.4.ffn.0.bias": "model.safetensors",
86
+ "recursive_layers.4.ffn.2.weight": "model.safetensors",
87
+ "recursive_layers.4.ffn.2.bias": "model.safetensors",
88
+ "recursive_layers.4.norm1.weight": "model.safetensors",
89
+ "recursive_layers.4.norm1.bias": "model.safetensors",
90
+ "recursive_layers.4.norm2.weight": "model.safetensors",
91
+ "recursive_layers.4.norm2.bias": "model.safetensors",
92
+ "recursive_layers.5.w_q.weight": "model.safetensors",
93
+ "recursive_layers.5.w_q.bias": "model.safetensors",
94
+ "recursive_layers.5.w_k.weight": "model.safetensors",
95
+ "recursive_layers.5.w_k.bias": "model.safetensors",
96
+ "recursive_layers.5.w_v.weight": "model.safetensors",
97
+ "recursive_layers.5.w_v.bias": "model.safetensors",
98
+ "recursive_layers.5.attn_out.weight": "model.safetensors",
99
+ "recursive_layers.5.attn_out.bias": "model.safetensors",
100
+ "recursive_layers.5.ffn.0.weight": "model.safetensors",
101
+ "recursive_layers.5.ffn.0.bias": "model.safetensors",
102
+ "recursive_layers.5.ffn.2.weight": "model.safetensors",
103
+ "recursive_layers.5.ffn.2.bias": "model.safetensors",
104
+ "recursive_layers.5.norm1.weight": "model.safetensors",
105
+ "recursive_layers.5.norm1.bias": "model.safetensors",
106
+ "recursive_layers.5.norm2.weight": "model.safetensors",
107
+ "recursive_layers.5.norm2.bias": "model.safetensors",
108
+ "router.linear.0.weight": "model.safetensors",
109
+ "router.linear.0.bias": "model.safetensors",
110
+ "router.linear.2.weight": "model.safetensors",
111
+ "router.linear.2.bias": "model.safetensors",
112
+ "final_norm.weight": "model.safetensors",
113
+ "final_norm.bias": "model.safetensors",
114
+ "head.weight": "model.safetensors"
115
+ }
116
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>",
5
+ "pad_token": null
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "GPT2Tokenizer",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>",
6
+ "pad_token": null,
7
+ "model_max_length": 1024
8
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff