Hugging Face's logo

inferencerlabs
/
Qwen3.6-27B-MTP-MLX-Q4.5

Image-Text-to-Text
MLX
Safetensors
English
qwen3_5_mtp
quantized
mtp
speculative-decoding
draft-model
Model card Files
xet
 Community
inferencerlabs commited on
Commit
301cfe9
·
verified ·
1 Parent(s): 7ab8b0a

Upload model file

Browse files
Files changed (1) hide show
  1. config.json +120 -0
config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "block_size": 3,
3
+ "model_type": "qwen3_5_mtp",
4
+ "quantization_config": {
5
+ "group_size": 64
6
+ },
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attn_output_gate": true,
11
+ "bos_token_id": 248044,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 248044,
14
+ "full_attention_interval": 4,
15
+ "head_dim": 256,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 5120,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 17408,
20
+ "layer_types": [
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "full_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "full_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "full_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "full_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "full_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "full_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "full_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "full_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "full_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "full_attention"
85
+ ],
86
+ "linear_conv_kernel_dim": 4,
87
+ "linear_key_head_dim": 128,
88
+ "linear_num_key_heads": 16,
89
+ "linear_num_value_heads": 48,
90
+ "linear_value_head_dim": 128,
91
+ "mamba_ssm_dtype": "float32",
92
+ "max_position_embeddings": 262144,
93
+ "model_type": "qwen3_5_text",
94
+ "mtp_num_hidden_layers": 1,
95
+ "mtp_use_dedicated_embeddings": false,
96
+ "num_attention_heads": 24,
97
+ "num_hidden_layers": 64,
98
+ "num_key_value_heads": 4,
99
+ "output_gate_type": "swish",
100
+ "pad_token_id": null,
101
+ "partial_rotary_factor": 0.25,
102
+ "rms_norm_eps": 1e-06,
103
+ "rope_parameters": {
104
+ "mrope_interleaved": true,
105
+ "mrope_section": [
106
+ 11,
107
+ 11,
108
+ 10
109
+ ],
110
+ "partial_rotary_factor": 0.25,
111
+ "rope_theta": 10000000,
112
+ "rope_type": "default"
113
+ },
114
+ "tie_word_embeddings": false,
115
+ "use_cache": true,
116
+ "vocab_size": 248320
117
+ },
118
+ "tie_word_embeddings": false,
119
+ "vision_config": {}
120
+ }