ncls-p commited on
Commit
b49afcc
·
verified ·
1 Parent(s): 98eb2c3

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +44 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 17408,
14
+ "max_position_embeddings": 81920,
15
+ "max_window_layers": 40,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 40,
18
+ "num_hidden_layers": 40,
19
+ "num_key_value_heads": 8,
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 6,
23
+ "mode": "affine"
24
+ },
25
+ "quantization_config": {
26
+ "group_size": 64,
27
+ "bits": 6,
28
+ "mode": "affine"
29
+ },
30
+ "rms_norm_eps": 1e-06,
31
+ "rope_scaling": {
32
+ "rope_type": "yarn",
33
+ "factor": 2.0,
34
+ "original_max_position_embeddings": 40960
35
+ },
36
+ "rope_theta": 1000000,
37
+ "sliding_window": null,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.51.0",
41
+ "use_cache": true,
42
+ "use_sliding_window": false,
43
+ "vocab_size": 151936
44
+ }