Hugging Face's logo

CyanMonkey
/
Test-Subject-3

Text Generation
Transformers
Safetensors
oleander
gdn2
gated-deltanet
gqa
muon
marimo
molab
Model card Files
xet
 Community
Test-Subject-3
File size: 2,478 Bytes
1c016ea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b7d66a
1c016ea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b7d66a
1c016ea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b7d66a
 
d59ea09
0b7d66a
 
d59ea09
 
 
0b7d66a
 
 
1c016ea
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
{
  "architectures": [
    "OleanderForCausalLM"
  ],
  "model_type": "oleander",
  "vocab_size": 32770,
  "hidden_size": 576,
  "num_hidden_layers": 28,
  "oleander_layer_types": [
    "gdn2",
    "gdn2",
    "gdn2",
    "gqa",
    "gdn2",
    "gdn2",
    "gdn2",
    "gqa",
    "gdn2",
    "gdn2",
    "gdn2",
    "gqa",
    "gdn2",
    "gdn2",
    "gdn2",
    "gqa",
    "gdn2",
    "gdn2",
    "gdn2",
    "gqa",
    "gdn2",
    "gdn2",
    "gdn2",
    "gqa",
    "gdn2",
    "gdn2",
    "gdn2",
    "gqa"
  ],
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention"
  ],
  "intermediate_size": 1600,
  "max_position_embeddings": 1024,
  "rms_norm_eps": 1e-06,
  "num_attention_heads": 9,
  "num_key_value_heads": 3,
  "head_dim": 64,
  "tie_word_embeddings": true,
  "use_cache": false,
  "attn_implementation": "sdpa",
  "oleander": {
    "arch_name": "OleanderForCausalLM",
    "vocab_size": 32770,
    "hidden_size": 576,
    "num_groups": 7,
    "group_pattern": [
      "gdn2",
      "gdn2",
      "gdn2",
      "gqa"
    ],
    "mlp_hidden": 1600,
    "max_seq_len": 1024,
    "norm_eps": 1e-06,
    "init_std": 0.02,
    "tie_embeddings": true,
    "attn_res": true,
    "residual_dtype": "bfloat16",
    "gdn2": {
      "heads": 9,
      "head_dim": 64,
      "conv_size": 4,
      "norm_eps": 1e-05,
      "allow_neg_eigval": false,
      "gate_in_kernel": false
    },
    "gqa": {
      "q_heads": 9,
      "kv_heads": 3,
      "head_dim": 64,
      "rotary_dim": 32,
      "rope_theta": 100000.0,
      "qk_norm": true,
      "value_residual": true
    }
  },
  "model_name": "Oleander-150M",
  "training": {
    "step": 1500,
    "kind": "export",
    "max_steps": 28820,
    "percent_complete": 5.205,
    "tokens_seen": 5058330624,
    "compute_tokens_seen": 843055104
  },
  "transformers_version": "5.14.1",
  "torch_dtype": "float32"
}