jkgl commited on
Commit
c91593e
·
verified ·
1 Parent(s): 4a7a10a

add config.json

Browse files
Files changed (1) hide show
  1. config.json +47 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "decoder_sparse_step": 1,
8
+ "dtype": "float16",
9
+ "eos_token_id": 151645,
10
+ "expert_capacity": 0,
11
+ "expert_layer_freq": 0,
12
+ "head_dim": 128,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2048,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 5472,
17
+ "max_position_embeddings": 262144,
18
+ "max_window_layers": 28,
19
+ "mlp_only_layers": [],
20
+ "model_type": "qwen3_moe",
21
+ "moe_grouped_gemm": false,
22
+ "moe_intermediate_size": 768,
23
+ "moe_token_dropping": false,
24
+ "norm_topk_prob": true,
25
+ "num_attention_heads": 32,
26
+ "num_experts": 128,
27
+ "num_experts_per_tok": 8,
28
+ "num_hidden_layers": 48,
29
+ "num_key_value_heads": 4,
30
+ "num_local_experts": 1,
31
+ "output_router_logits": false,
32
+ "qkv_bias": false,
33
+ "rms_norm_eps": 1e-06,
34
+ "rope_scaling": null,
35
+ "rope_theta": 10000000,
36
+ "router_aux_loss_coef": 0.0,
37
+ "router_jitter_eps": 0.0,
38
+ "router_topk": 1,
39
+ "shared_expert_intermediate_size": 0,
40
+ "sliding_window": null,
41
+ "tie_word_embeddings": false,
42
+ "transformers_version": "4.57.0.dev0",
43
+ "use_cache": true,
44
+ "use_qk_norm": true,
45
+ "use_sliding_window": false,
46
+ "vocab_size": 262170
47
+ }