saurabh5 commited on
Commit
ae16844
·
1 Parent(s): 6f35e20

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +99 -99
config.json CHANGED
@@ -1,100 +1,100 @@
1
  {
2
- "architectures": [
3
- "Olmo3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "dtype": "bfloat16",
8
- "eos_token_id": 100257,
9
- "hidden_act": "silu",
10
- "hidden_size": 5120,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 27648,
13
- "layer_types": [
14
- "sliding_attention",
15
- "sliding_attention",
16
- "sliding_attention",
17
- "full_attention",
18
- "sliding_attention",
19
- "sliding_attention",
20
- "sliding_attention",
21
- "full_attention",
22
- "sliding_attention",
23
- "sliding_attention",
24
- "sliding_attention",
25
- "full_attention",
26
- "sliding_attention",
27
- "sliding_attention",
28
- "sliding_attention",
29
- "full_attention",
30
- "sliding_attention",
31
- "sliding_attention",
32
- "sliding_attention",
33
- "full_attention",
34
- "sliding_attention",
35
- "sliding_attention",
36
- "sliding_attention",
37
- "full_attention",
38
- "sliding_attention",
39
- "sliding_attention",
40
- "sliding_attention",
41
- "full_attention",
42
- "sliding_attention",
43
- "sliding_attention",
44
- "sliding_attention",
45
- "full_attention",
46
- "sliding_attention",
47
- "sliding_attention",
48
- "sliding_attention",
49
- "full_attention",
50
- "sliding_attention",
51
- "sliding_attention",
52
- "sliding_attention",
53
- "full_attention",
54
- "sliding_attention",
55
- "sliding_attention",
56
- "sliding_attention",
57
- "full_attention",
58
- "sliding_attention",
59
- "sliding_attention",
60
- "sliding_attention",
61
- "full_attention",
62
- "sliding_attention",
63
- "sliding_attention",
64
- "sliding_attention",
65
- "full_attention",
66
- "sliding_attention",
67
- "sliding_attention",
68
- "sliding_attention",
69
- "full_attention",
70
- "sliding_attention",
71
- "sliding_attention",
72
- "sliding_attention",
73
- "full_attention",
74
- "sliding_attention",
75
- "sliding_attention",
76
- "sliding_attention",
77
- "full_attention"
78
- ],
79
- "max_position_embeddings": 65536,
80
- "model_type": "olmo3",
81
- "num_attention_heads": 40,
82
- "num_hidden_layers": 64,
83
- "num_key_value_heads": 8,
84
- "pad_token_id": 100277,
85
- "rms_norm_eps": 1e-06,
86
- "rope_scaling": {
87
- "attention_factor": 1.2079441541679836,
88
- "beta_fast": 32,
89
- "beta_slow": 1,
90
- "factor": 8.0,
91
- "original_max_position_embeddings": 8192,
92
- "rope_type": "yarn"
93
- },
94
- "rope_theta": 500000,
95
- "sliding_window": 4096,
96
- "tie_word_embeddings": false,
97
- "transformers_version": "4.57.1",
98
- "use_cache": false,
99
- "vocab_size": 100278
100
- }
 
1
  {
2
+ "architectures": [
3
+ "Olmo3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 100257,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
+ "layer_types": [
14
+ "sliding_attention",
15
+ "sliding_attention",
16
+ "sliding_attention",
17
+ "full_attention",
18
+ "sliding_attention",
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "full_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "full_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "full_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "full_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "full_attention"
78
+ ],
79
+ "max_position_embeddings": 65536,
80
+ "model_type": "olmo3",
81
+ "num_attention_heads": 40,
82
+ "num_hidden_layers": 64,
83
+ "num_key_value_heads": 8,
84
+ "pad_token_id": 100277,
85
+ "rms_norm_eps": 1e-06,
86
+ "rope_scaling": {
87
+ "attention_factor": 1.2079441541679836,
88
+ "beta_fast": 32.0,
89
+ "beta_slow": 1.0,
90
+ "factor": 8.0,
91
+ "original_max_position_embeddings": 8192,
92
+ "rope_type": "yarn"
93
+ },
94
+ "rope_theta": 500000,
95
+ "sliding_window": 4096,
96
+ "tie_word_embeddings": false,
97
+ "transformers_version": "4.57.1",
98
+ "use_cache": false,
99
+ "vocab_size": 100278
100
+ }