config.json
726 B · 30 lines · json Raw
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": 1024,
12 "initializer_range": 0.02,
13 "intermediate_size": 3072,
14 "max_position_embeddings": 40960,
15 "max_window_layers": 28,
16 "model_type": "qwen3",
17 "num_attention_heads": 16,
18 "num_hidden_layers": 28,
19 "num_key_value_heads": 8,
20 "rms_norm_eps": 1e-06,
21 "rope_scaling": null,
22 "rope_theta": 1000000,
23 "sliding_window": null,
24 "tie_word_embeddings": true,
25 "torch_dtype": "bfloat16",
26 "transformers_version": "4.51.0",
27 "use_cache": true,
28 "use_sliding_window": false,
29 "vocab_size": 151936
30 }