Text Generation
Transformers
Safetensors
English
doge
conversational
custom_code
JingzeShi commited on
Commit
4330a37
·
verified ·
1 Parent(s): a6a6403

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +43 -43
config.json CHANGED
@@ -1,43 +1,43 @@
1
- {
2
- "_name_or_path": "./Doge-160M-new",
3
- "architectures": [
4
- "DogeForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "auto_map": {
8
- "AutoConfig": "configuration_doge.DogeConfig",
9
- "AutoModelForCausalLM": "modeling_doge.DogeForCausalLM"
10
- },
11
- "bos_token_id": 0,
12
- "dynamic_mask_ratio": 0.0,
13
- "eos_token_id": 1,
14
- "expert_retrieval_size": 64,
15
- "hidden_act": "silu",
16
- "hidden_bias": false,
17
- "hidden_dropout": 0.0,
18
- "hidden_size": 768,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 1536,
21
- "is_moe": false,
22
- "max_position_embeddings": 2048,
23
- "model_type": "doge",
24
- "num_attention_heads": 6,
25
- "num_cdmoe_experts": 16348,
26
- "num_cdmoe_experts_per_head": 8,
27
- "num_cdmoe_heads": 4,
28
- "num_hidden_layers": 24,
29
- "num_key_value_heads": 3,
30
- "pad_token_id": 2,
31
- "rms_norm_eps": 1e-06,
32
- "rope_scaling": {
33
- "factor": 4.0,
34
- "original_max_position_embeddings": 2048,
35
- "rope_type": "dynamic"
36
- },
37
- "rope_theta": 10000.0,
38
- "tie_word_embeddings": true,
39
- "torch_dtype": "float32",
40
- "transformers_version": "4.48.3",
41
- "use_cache": true,
42
- "vocab_size": 32768
43
- }
 
1
+ {
2
+ "_name_or_path": "SmallDoge/Doge-160M",
3
+ "architectures": [
4
+ "DogeForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_doge.DogeConfig",
9
+ "AutoModelForCausalLM": "modeling_doge.DogeForCausalLM"
10
+ },
11
+ "bos_token_id": 0,
12
+ "dynamic_mask_ratio": 0.0,
13
+ "eos_token_id": 1,
14
+ "expert_retrieval_size": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_bias": false,
17
+ "hidden_dropout": 0.0,
18
+ "hidden_size": 768,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 1536,
21
+ "is_moe": false,
22
+ "max_position_embeddings": 2048,
23
+ "model_type": "doge",
24
+ "num_attention_heads": 6,
25
+ "num_cdmoe_experts": 16348,
26
+ "num_cdmoe_experts_per_head": 8,
27
+ "num_cdmoe_heads": 4,
28
+ "num_hidden_layers": 24,
29
+ "num_key_value_heads": 3,
30
+ "pad_token_id": 2,
31
+ "rms_norm_eps": 1e-06,
32
+ "rope_scaling": {
33
+ "factor": 4.0,
34
+ "original_max_position_embeddings": 2048,
35
+ "rope_type": "dynamic"
36
+ },
37
+ "rope_theta": 10000.0,
38
+ "tie_word_embeddings": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.48.3",
41
+ "use_cache": true,
42
+ "vocab_size": 32768
43
+ }