Hugging Face's logo

unsloth
/
GLM-5

Text Generation
Transformers
Safetensors
English
Chinese
glm_moe_dsa
conversational
Model card Files
xet
Community
danielhanchen commited on
Commit
f73a51e
·
verified ·
1 Parent(s): b79c81f

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +87 -5
config.json CHANGED
@@ -12,8 +12,8 @@
12
  ],
13
  "ep_size": 1,
14
  "first_k_dense_replace": 3,
15
- "hidden_act": "silu",
16
  "head_dim": 64,
 
17
  "hidden_size": 6144,
18
  "index_head_dim": 128,
19
  "index_n_heads": 32,
@@ -23,9 +23,89 @@
23
  "intermediate_size": 12288,
24
  "kv_lora_rank": 512,
25
  "max_position_embeddings": 202752,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  "moe_intermediate_size": 2048,
27
  "moe_layer_freq": 1,
28
- "model_type": "glm_moe_dsa",
29
  "n_group": 1,
30
  "n_routed_experts": 256,
31
  "n_shared_experts": 1,
@@ -35,8 +115,8 @@
35
  "num_hidden_layers": 78,
36
  "num_key_value_heads": 64,
37
  "num_nextn_predict_layers": 1,
38
- "partial_rotary_factor" : 1.0,
39
- "pad_token_id": 154820,
40
  "pretraining_tp": 1,
41
  "q_lora_rank": 2048,
42
  "qk_head_dim": 256,
@@ -45,6 +125,7 @@
45
  "rms_norm_eps": 1e-05,
46
  "rope_interleave": true,
47
  "rope_parameters": {
 
48
  "rope_theta": 1000000,
49
  "rope_type": "default"
50
  },
@@ -53,7 +134,8 @@
53
  "tie_word_embeddings": false,
54
  "topk_group": 1,
55
  "topk_method": "noaux_tc",
56
- "transformers_version": "5.0.2.dev0",
 
57
  "use_cache": true,
58
  "v_head_dim": 256,
59
  "vocab_size": 154880
 
12
  ],
13
  "ep_size": 1,
14
  "first_k_dense_replace": 3,
 
15
  "head_dim": 64,
16
+ "hidden_act": "silu",
17
  "hidden_size": 6144,
18
  "index_head_dim": 128,
19
  "index_n_heads": 32,
 
23
  "intermediate_size": 12288,
24
  "kv_lora_rank": 512,
25
  "max_position_embeddings": 202752,
26
+ "mlp_layer_types": [
27
+ "dense",
28
+ "dense",
29
+ "dense",
30
+ "sparse",
31
+ "sparse",
32
+ "sparse",
33
+ "sparse",
34
+ "sparse",
35
+ "sparse",
36
+ "sparse",
37
+ "sparse",
38
+ "sparse",
39
+ "sparse",
40
+ "sparse",
41
+ "sparse",
42
+ "sparse",
43
+ "sparse",
44
+ "sparse",
45
+ "sparse",
46
+ "sparse",
47
+ "sparse",
48
+ "sparse",
49
+ "sparse",
50
+ "sparse",
51
+ "sparse",
52
+ "sparse",
53
+ "sparse",
54
+ "sparse",
55
+ "sparse",
56
+ "sparse",
57
+ "sparse",
58
+ "sparse",
59
+ "sparse",
60
+ "sparse",
61
+ "sparse",
62
+ "sparse",
63
+ "sparse",
64
+ "sparse",
65
+ "sparse",
66
+ "sparse",
67
+ "sparse",
68
+ "sparse",
69
+ "sparse",
70
+ "sparse",
71
+ "sparse",
72
+ "sparse",
73
+ "sparse",
74
+ "sparse",
75
+ "sparse",
76
+ "sparse",
77
+ "sparse",
78
+ "sparse",
79
+ "sparse",
80
+ "sparse",
81
+ "sparse",
82
+ "sparse",
83
+ "sparse",
84
+ "sparse",
85
+ "sparse",
86
+ "sparse",
87
+ "sparse",
88
+ "sparse",
89
+ "sparse",
90
+ "sparse",
91
+ "sparse",
92
+ "sparse",
93
+ "sparse",
94
+ "sparse",
95
+ "sparse",
96
+ "sparse",
97
+ "sparse",
98
+ "sparse",
99
+ "sparse",
100
+ "sparse",
101
+ "sparse",
102
+ "sparse",
103
+ "sparse",
104
+ "sparse"
105
+ ],
106
+ "model_type": "glm_moe_dsa",
107
  "moe_intermediate_size": 2048,
108
  "moe_layer_freq": 1,
 
109
  "n_group": 1,
110
  "n_routed_experts": 256,
111
  "n_shared_experts": 1,
 
115
  "num_hidden_layers": 78,
116
  "num_key_value_heads": 64,
117
  "num_nextn_predict_layers": 1,
118
+ "pad_token_id": 154821,
119
+ "partial_rotary_factor": 1.0,
120
  "pretraining_tp": 1,
121
  "q_lora_rank": 2048,
122
  "qk_head_dim": 256,
 
125
  "rms_norm_eps": 1e-05,
126
  "rope_interleave": true,
127
  "rope_parameters": {
128
+ "partial_rotary_factor": 1.0,
129
  "rope_theta": 1000000,
130
  "rope_type": "default"
131
  },
 
134
  "tie_word_embeddings": false,
135
  "topk_group": 1,
136
  "topk_method": "noaux_tc",
137
+ "transformers_version": "5.2.0.dev0",
138
+ "unsloth_fixed": true,
139
  "use_cache": true,
140
  "v_head_dim": 256,
141
  "vocab_size": 154880