RonanMcGovern commited on
Commit
9832b62
1 Parent(s): 2e53034

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +101 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "apple/OpenELM-450M-instruct",
3
+ "activation_fn_name": "swish",
4
+ "architectures": [
5
+ "OpenELMForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "apple/OpenELM-450M-instruct--configuration_openelm.OpenELMConfig",
9
+ "AutoModelForCausalLM": "apple/OpenELM-450M-instruct--modeling_openelm.OpenELMForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "ffn_dim_divisor": 256,
14
+ "ffn_multipliers": [
15
+ 0.5,
16
+ 0.68,
17
+ 0.87,
18
+ 1.05,
19
+ 1.24,
20
+ 1.42,
21
+ 1.61,
22
+ 1.79,
23
+ 1.97,
24
+ 2.16,
25
+ 2.34,
26
+ 2.53,
27
+ 2.71,
28
+ 2.89,
29
+ 3.08,
30
+ 3.26,
31
+ 3.45,
32
+ 3.63,
33
+ 3.82,
34
+ 4.0
35
+ ],
36
+ "ffn_with_glu": true,
37
+ "head_dim": 64,
38
+ "initializer_range": 0.02,
39
+ "max_context_length": 2048,
40
+ "model_dim": 1536,
41
+ "model_type": "openelm",
42
+ "normalization_layer_name": "rms_norm",
43
+ "normalize_qk_projections": true,
44
+ "num_gqa_groups": 4,
45
+ "num_kv_heads": [
46
+ 3,
47
+ 3,
48
+ 3,
49
+ 4,
50
+ 4,
51
+ 4,
52
+ 4,
53
+ 4,
54
+ 4,
55
+ 4,
56
+ 5,
57
+ 5,
58
+ 5,
59
+ 5,
60
+ 5,
61
+ 5,
62
+ 6,
63
+ 6,
64
+ 6,
65
+ 6
66
+ ],
67
+ "num_query_heads": [
68
+ 12,
69
+ 12,
70
+ 12,
71
+ 16,
72
+ 16,
73
+ 16,
74
+ 16,
75
+ 16,
76
+ 16,
77
+ 16,
78
+ 20,
79
+ 20,
80
+ 20,
81
+ 20,
82
+ 20,
83
+ 20,
84
+ 24,
85
+ 24,
86
+ 24,
87
+ 24
88
+ ],
89
+ "num_transformer_layers": 20,
90
+ "qkv_multipliers": [
91
+ 0.5,
92
+ 1.0
93
+ ],
94
+ "rope_freq_constant": 10000,
95
+ "rope_max_length": 4096,
96
+ "share_input_output_layers": true,
97
+ "torch_dtype": "bfloat16",
98
+ "transformers_version": "4.40.1",
99
+ "use_cache": true,
100
+ "vocab_size": 32000
101
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.40.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e42e001549d1895d7542135638c010f4c601845efc133189b28c04e6a24275d
3
+ size 914376544