Hugging Face's logo

heegyu
/
kogemma-tiny-test

Text Generation
Transformers
Safetensors
gemma
text-generation-inference
Model card Files
xet
Community
kogemma-tiny-test
File size: 1,783 Bytes
342a902
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "architectures": [
    "GemmaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_partition_spec": [
    [
      "dp",
      "fsdp"
    ],
    "sp",
    "tp",
    null
  ],
  "attn_mechanism": "normal",
  "axis_dims": [
    1,
    -1,
    1,
    1
  ],
  "axis_names": [
    "dp",
    "fsdp",
    "tp",
    "sp"
  ],
  "backend": null,
  "bias_partition_spec": [
    [
      "dp",
      "fsdp"
    ],
    null,
    null,
    null
  ],
  "bits": null,
  "block_b": 1,
  "block_k": 128,
  "block_k_dkv": 128,
  "block_k_dq": 128,
  "block_k_major": 128,
  "block_k_major_dkv": 128,
  "block_k_major_dq": 128,
  "block_q": 128,
  "block_q_dkv": 128,
  "block_q_dq": 128,
  "block_q_major_dkv": 128,
  "bos_token_id": 2,
  "easy_method": "train",
  "eos_token_id": 1,
  "head_dim": 32,
  "hidden_act": "gelu",
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 256,
  "key_partition_spec": [
    [
      "dp",
      "fsdp"
    ],
    "sp",
    "tp",
    null
  ],
  "max_position_embeddings": 8192,
  "model_type": "gemma",
  "num_attention_heads": 2,
  "num_hidden_layers": 2,
  "num_key_value_heads": 2,
  "pad_token_id": 0,
  "query_partition_spec": [
    [
      "dp",
      "fsdp"
    ],
    "sp",
    "tp",
    null
  ],
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "scan_attention_layers": false,
  "scan_layers": false,
  "scan_mlp_chunk_size": 1024,
  "scan_ring_attention": true,
  "torch_dtype": "float32",
  "transformers_version": "4.38.1",
  "use_cache": true,
  "use_pjit_attention_force": false,
  "use_scan_mlp": true,
  "use_shard_map": false,
  "use_sharded_kv_caching": true,
  "value_partition_spec": [
    [
      "dp",
      "fsdp"
    ],
    "sp",
    "tp",
    null
  ],
  "vocab_size": 256000
}