config.json
2.6 KB · 114 lines · json Raw
1 {
2 "attention_bias": false,
3 "attention_dropout": 0.0,
4 "attn_output_gate": true,
5 "bos_token_id": 248044,
6 "dtype": "bfloat16",
7 "eos_token_id": 248044,
8 "full_attention_interval": 4,
9 "head_dim": 256,
10 "hidden_act": "silu",
11 "hidden_size": 5120,
12 "initializer_range": 0.02,
13 "intermediate_size": 17408,
14 "layer_types": [
15 "linear_attention",
16 "linear_attention",
17 "linear_attention",
18 "full_attention",
19 "linear_attention",
20 "linear_attention",
21 "linear_attention",
22 "full_attention",
23 "linear_attention",
24 "linear_attention",
25 "linear_attention",
26 "full_attention",
27 "linear_attention",
28 "linear_attention",
29 "linear_attention",
30 "full_attention",
31 "linear_attention",
32 "linear_attention",
33 "linear_attention",
34 "full_attention",
35 "linear_attention",
36 "linear_attention",
37 "linear_attention",
38 "full_attention",
39 "linear_attention",
40 "linear_attention",
41 "linear_attention",
42 "full_attention",
43 "linear_attention",
44 "linear_attention",
45 "linear_attention",
46 "full_attention",
47 "linear_attention",
48 "linear_attention",
49 "linear_attention",
50 "full_attention",
51 "linear_attention",
52 "linear_attention",
53 "linear_attention",
54 "full_attention",
55 "linear_attention",
56 "linear_attention",
57 "linear_attention",
58 "full_attention",
59 "linear_attention",
60 "linear_attention",
61 "linear_attention",
62 "full_attention",
63 "linear_attention",
64 "linear_attention",
65 "linear_attention",
66 "full_attention",
67 "linear_attention",
68 "linear_attention",
69 "linear_attention",
70 "full_attention",
71 "linear_attention",
72 "linear_attention",
73 "linear_attention",
74 "full_attention",
75 "linear_attention",
76 "linear_attention",
77 "linear_attention",
78 "full_attention"
79 ],
80 "linear_conv_kernel_dim": 4,
81 "linear_key_head_dim": 128,
82 "linear_num_key_heads": 16,
83 "linear_num_value_heads": 48,
84 "linear_value_head_dim": 128,
85 "mamba_ssm_dtype": "float32",
86 "max_position_embeddings": 262144,
87 "model_type": "qwen3_5_text",
88 "mtp_num_hidden_layers": 1,
89 "mtp_use_dedicated_embeddings": false,
90 "num_attention_heads": 24,
91 "num_hidden_layers": 64,
92 "num_key_value_heads": 4,
93 "output_gate_type": "swish",
94 "pad_token_id": null,
95 "partial_rotary_factor": 0.25,
96 "rms_norm_eps": 1e-06,
97 "rope_parameters": {
98 "mrope_interleaved": true,
99 "mrope_section": [
100 11,
101 11,
102 10
103 ],
104 "partial_rotary_factor": 0.25,
105 "rope_theta": 10000000,
106 "rope_type": "default"
107 },
108 "tie_word_embeddings": false,
109 "use_cache": true,
110 "vocab_size": 248320,
111 "architectures": [
112 "Qwen3_5ForCausalLM"
113 ]
114 }