YOYO-AI commited on
Commit
216c3c0
·
verified ·
1 Parent(s): a36ea9e

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +38 -38
config.json CHANGED
@@ -1,38 +1,38 @@
1
- {
2
- "architectures": [
3
- "Qwen3MoeForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "decoder_sparse_step": 1,
9
- "dtype": "bfloat16",
10
- "eos_token_id": 151645,
11
- "head_dim": 128,
12
- "hidden_act": "silu",
13
- "hidden_size": 2048,
14
- "initializer_range": 0.02,
15
- "intermediate_size": 6144,
16
- "max_position_embeddings": 262144,
17
- "max_window_layers": 48,
18
- "mlp_only_layers": [],
19
- "model_type": "qwen3_moe",
20
- "moe_intermediate_size": 768,
21
- "norm_topk_prob": true,
22
- "num_attention_heads": 32,
23
- "num_experts": 128,
24
- "num_experts_per_tok": 8,
25
- "num_hidden_layers": 48,
26
- "num_key_value_heads": 4,
27
- "output_router_logits": false,
28
- "rms_norm_eps": 1e-06,
29
- "rope_scaling": null,
30
- "rope_theta": 10000000,
31
- "router_aux_loss_coef": 0.001,
32
- "sliding_window": null,
33
- "tie_word_embeddings": false,
34
- "transformers_version": "4.56.1",
35
- "use_cache": true,
36
- "use_sliding_window": false,
37
- "vocab_size": 151936
38
- }
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 151645,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6144,
16
+ "max_position_embeddings": 262144,
17
+ "max_window_layers": 48,
18
+ "mlp_only_layers": [],
19
+ "model_type": "qwen3_moe",
20
+ "moe_intermediate_size": 768,
21
+ "norm_topk_prob": true,
22
+ "num_attention_heads": 32,
23
+ "num_experts": 128,
24
+ "num_experts_per_tok": 8,
25
+ "num_hidden_layers": 48,
26
+ "num_key_value_heads": 4,
27
+ "output_router_logits": false,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_scaling": null,
30
+ "rope_theta": 10000000,
31
+ "router_aux_loss_coef": 0.001,
32
+ "sliding_window": null,
33
+ "tie_word_embeddings": false,
34
+ "transformers_version": "4.56.1",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151669
38
+ }