QRRanker / config.json
Judychoieee's picture
add model files
091400d
{
"architectures": [
"Qwen3Model"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "modeling_qwen3_qr.Qwen3ConfigGating",
"AutoModel": "modeling_qwen3_qr.Qwen3Model"
},
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 262144,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"qr_end_layer": 25,
"qr_head_list": [
[
20,
15
],
[
21,
11
],
[
17,
27
],
[
23,
10
],
[
22,
4
],
[
21,
10
],
[
21,
8
],
[
21,
18
],
[
18,
15
],
[
18,
19
],
[
17,
25
],
[
17,
17
],
[
24,
13
],
[
17,
4
],
[
19,
12
],
[
21,
31
]
],
"qr_head_list_mapped": [
[
3,
15
],
[
4,
11
],
[
0,
27
],
[
6,
10
],
[
5,
4
],
[
4,
10
],
[
4,
8
],
[
4,
18
],
[
1,
15
],
[
1,
19
],
[
0,
25
],
[
0,
17
],
[
7,
13
],
[
0,
4
],
[
2,
12
],
[
4,
31
]
],
"qr_start_layer": 17,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000,
"sliding_window": null,
"tie_word_embeddings": true,
"top_k_heads_per_layer": 2,
"torch_dtype": "bfloat16",
"transformers_version": "4.53.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}