Hugging Face's logo

pcuenq
/
Hunyuan-7B-Instruct-tokenizer

Text Generation
Transformers
hunyuan
conversational
custom_code
3-bit
Model card Files
xet
Community
3
pcuenq HF Staff commited on
Commit
d2e74a1
·
verified ·
1 Parent(s): 201270f

config.json (#1)

Browse files

- config.json (99716fc8d6c63f43b4373ba23370b2311d23906b)

Files changed (1) hide show
  1. config.json +172 -0
config.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HunYuanForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_head_dim": 128,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_hunyuan.HunYuanConfig",
10
+ "AutoModel": "modeling_hunyuan.HunyuanModel",
11
+ "AutoModelForCausalLM": "modeling_hunyuan.HunYuanForCausalLM"
12
+ },
13
+ "bos_token_id": 1,
14
+ "cla_share_factor": 2,
15
+ "eos_token_id": 2,
16
+ "group_limited_greedy": false,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 4096,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 14336,
21
+ "kv_lora_rank": null,
22
+ "max_position_embeddings": 4096,
23
+ "mlp_bias": false,
24
+ "model_type": "hunyuan",
25
+ "moe_drop_tokens": false,
26
+ "moe_intermediate_size": [
27
+ 14336,
28
+ 14336,
29
+ 14336,
30
+ 14336,
31
+ 14336,
32
+ 14336,
33
+ 14336,
34
+ 14336,
35
+ 14336,
36
+ 14336,
37
+ 14336,
38
+ 14336,
39
+ 14336,
40
+ 14336,
41
+ 14336,
42
+ 14336,
43
+ 14336,
44
+ 14336,
45
+ 14336,
46
+ 14336,
47
+ 14336,
48
+ 14336,
49
+ 14336,
50
+ 14336,
51
+ 14336,
52
+ 14336,
53
+ 14336,
54
+ 14336,
55
+ 14336,
56
+ 14336,
57
+ 14336,
58
+ 14336
59
+ ],
60
+ "moe_layer_num_skipped": 0,
61
+ "moe_random_routing_dropped_token": false,
62
+ "moe_topk": [
63
+ 1,
64
+ 1,
65
+ 1,
66
+ 1,
67
+ 1,
68
+ 1,
69
+ 1,
70
+ 1,
71
+ 1,
72
+ 1,
73
+ 1,
74
+ 1,
75
+ 1,
76
+ 1,
77
+ 1,
78
+ 1,
79
+ 1,
80
+ 1,
81
+ 1,
82
+ 1,
83
+ 1,
84
+ 1,
85
+ 1,
86
+ 1,
87
+ 1,
88
+ 1,
89
+ 1,
90
+ 1,
91
+ 1,
92
+ 1,
93
+ 1,
94
+ 1
95
+ ],
96
+ "n_group": false,
97
+ "norm_topk_prob": false,
98
+ "num_attention_heads": 32,
99
+ "num_experts": 1,
100
+ "num_hidden_layers": 32,
101
+ "num_key_value_heads": 8,
102
+ "num_shared_expert": [
103
+ 1,
104
+ 1,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 1,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 1,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 1,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 1,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 1,
125
+ 1,
126
+ 1,
127
+ 1,
128
+ 1,
129
+ 1,
130
+ 1,
131
+ 1,
132
+ 1,
133
+ 1,
134
+ 1
135
+ ],
136
+ "pad_token_id": 0,
137
+ "pretraining_tp": 1,
138
+ "q_lora_rank": null,
139
+ "qk_nope_head_dim": null,
140
+ "qk_rope_head_dim": null,
141
+ "quantization": {
142
+ "group_size": 64,
143
+ "bits": 3
144
+ },
145
+ "quantization_config": {
146
+ "group_size": 64,
147
+ "bits": 3
148
+ },
149
+ "rms_norm_eps": 1e-05,
150
+ "rope_scaling": {
151
+ "alpha": 1000.0,
152
+ "beta_fast": 32,
153
+ "beta_slow": 1,
154
+ "factor": 1.0,
155
+ "mscale": 1.0,
156
+ "mscale_all_dim": 1.0,
157
+ "type": "dynamic"
158
+ },
159
+ "rope_theta": 10000.0,
160
+ "routed_scaling_factor": false,
161
+ "tie_word_embeddings": true,
162
+ "topk_group": false,
163
+ "torch_dtype": "bfloat16",
164
+ "transformers_version": "4.41.2",
165
+ "use_cache": true,
166
+ "use_cla": false,
167
+ "use_mixed_mlp_moe": false,
168
+ "use_mla": false,
169
+ "use_qk_norm": true,
170
+ "v_head_dim": null,
171
+ "vocab_size": 129024
172
+ }