config.json
963 B · 38 lines · json Raw
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 "eos_token_id": 151645,
10 "head_dim": 128,
11 "hidden_act": "silu",
12 "hidden_size": 2048,
13 "initializer_range": 0.02,
14 "intermediate_size": 6144,
15 "max_position_embeddings": 262144,
16 "max_window_layers": 48,
17 "mlp_only_layers": [],
18 "model_type": "qwen3_moe",
19 "moe_intermediate_size": 768,
20 "norm_topk_prob": true,
21 "num_attention_heads": 32,
22 "num_experts": 128,
23 "num_experts_per_tok": 8,
24 "num_hidden_layers": 48,
25 "num_key_value_heads": 4,
26 "output_router_logits": false,
27 "rms_norm_eps": 1e-06,
28 "rope_scaling": null,
29 "rope_theta": 10000000,
30 "router_aux_loss_coef": 0.001,
31 "sliding_window": null,
32 "tie_word_embeddings": false,
33 "torch_dtype": "bfloat16",
34 "transformers_version": "4.52.3",
35 "use_cache": true,
36 "use_sliding_window": false,
37 "vocab_size": 151936
38 }