config.json
1.2 KB · 55 lines · json Raw
1 {
2 "architectures": [
3 "Qwen2ForCausalLM"
4 ],
5 "attention_dropout": 0.0,
6 "bos_token_id": 151643,
7 "dtype": "bfloat16",
8 "eos_token_id": 151645,
9 "hidden_act": "silu",
10 "hidden_size": 896,
11 "initializer_range": 0.02,
12 "intermediate_size": 4864,
13 "layer_types": [
14 "full_attention",
15 "full_attention",
16 "full_attention",
17 "full_attention",
18 "full_attention",
19 "full_attention",
20 "full_attention",
21 "full_attention",
22 "full_attention",
23 "full_attention",
24 "full_attention",
25 "full_attention",
26 "full_attention",
27 "full_attention",
28 "full_attention",
29 "full_attention",
30 "full_attention",
31 "full_attention",
32 "full_attention",
33 "full_attention",
34 "full_attention",
35 "full_attention",
36 "full_attention",
37 "full_attention"
38 ],
39 "max_position_embeddings": 32768,
40 "max_window_layers": 24,
41 "model_type": "qwen2",
42 "num_attention_heads": 14,
43 "num_hidden_layers": 24,
44 "num_key_value_heads": 2,
45 "rms_norm_eps": 1e-06,
46 "rope_scaling": null,
47 "rope_theta": 1000000.0,
48 "sliding_window": null,
49 "tie_word_embeddings": true,
50 "transformers_version": "4.57.1",
51 "use_cache": true,
52 "use_sliding_window": false,
53 "vocab_size": 151936
54 }
55