user0199939 commited on
Commit
09eb0b3
·
verified ·
1 Parent(s): 73f2864

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +61 -0
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "WeiboAI/VibeThinker-1.5B",
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151643,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1536,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8960,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention"
43
+ ],
44
+ "max_position_embeddings": 131072,
45
+ "max_window_layers": 21,
46
+ "model_type": "qwen2",
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 28,
49
+ "num_key_value_heads": 2,
50
+ "pad_token_id": 151643,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 640000,
54
+ "sliding_window": null,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "4.46.3",
57
+ "use_cache": false,
58
+ "use_mrope": false,
59
+ "use_sliding_window": false,
60
+ "vocab_size": 151936
61
+ }