inferencerlabs commited on
Commit
cee5270
·
verified ·
1 Parent(s): c3620d0

Upload complete model

Browse files
Files changed (1) hide show
  1. config.json +87 -0
config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 200002,
8
+ "experts_per_token": 4,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2880,
12
+ "initial_context_length": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2880,
15
+ "layer_types": [
16
+ "sliding_attention",
17
+ "full_attention",
18
+ "sliding_attention",
19
+ "full_attention",
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 131072,
54
+ "model_type": "gpt_oss",
55
+ "num_attention_heads": 64,
56
+ "num_experts_per_tok": 4,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "num_local_experts": 128,
60
+ "output_router_logits": false,
61
+ "pad_token_id": 199999,
62
+ "quantization": {
63
+ "group_size": 64,
64
+ "bits": 6
65
+ },
66
+ "quantization_config": {
67
+ "group_size": 64,
68
+ "bits": 6
69
+ },
70
+ "rms_norm_eps": 1e-05,
71
+ "rope_scaling": {
72
+ "beta_fast": 32.0,
73
+ "beta_slow": 1.0,
74
+ "factor": 32.0,
75
+ "original_max_position_embeddings": 4096,
76
+ "rope_type": "yarn",
77
+ "truncate": false
78
+ },
79
+ "rope_theta": 150000,
80
+ "router_aux_loss_coef": 0.9,
81
+ "sliding_window": 128,
82
+ "swiglu_limit": 7.0,
83
+ "tie_word_embeddings": false,
84
+ "transformers_version": "4.55.0.dev0",
85
+ "use_cache": true,
86
+ "vocab_size": 201088
87
+ }