Hugging Face's logo

Sh2425
/
Dolphy-1.2-Base

Transformers
Safetensors
English
dolphy_moe
text-generation-inference
unsloth
qwen3
trl
Model card Files
xet
Community
Sh2425 commited on
Commit
2065930
·
verified ·
1 Parent(s): 6132420

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +32 -60
config.json CHANGED
@@ -1,70 +1,42 @@
1
  {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "dtype": "float16",
8
- "eos_token_id": 151645,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
  "hidden_size": 2560,
12
- "initializer_range": 0.02,
13
  "intermediate_size": 9728,
14
- "layer_types": [
15
- "full_attention",
16
- "full_attention",
17
- "full_attention",
18
- "full_attention",
19
- "full_attention",
20
- "full_attention",
21
- "full_attention",
22
- "full_attention",
23
- "full_attention",
24
- "full_attention",
25
- "full_attention",
26
- "full_attention",
27
- "full_attention",
28
- "full_attention",
29
- "full_attention",
30
- "full_attention",
31
- "full_attention",
32
- "full_attention",
33
- "full_attention",
34
- "full_attention",
35
- "full_attention",
36
- "full_attention",
37
- "full_attention",
38
- "full_attention",
39
- "full_attention",
40
- "full_attention",
41
- "full_attention",
42
- "full_attention",
43
- "full_attention",
44
- "full_attention",
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention"
51
- ],
52
- "max_position_embeddings": 262144,
53
- "max_window_layers": 36,
54
- "model_type": "qwen3",
55
- "num_attention_heads": 32,
56
  "num_hidden_layers": 36,
 
57
  "num_key_value_heads": 8,
 
 
 
 
 
 
 
 
58
  "pad_token_id": 151654,
59
- "rms_norm_eps": 1e-06,
60
- "rope_scaling": null,
61
- "rope_theta": 5000000,
62
- "sliding_window": null,
63
  "tie_word_embeddings": true,
64
- "transformers_version": "4.57.1",
65
- "unsloth_fixed": true,
66
- "unsloth_version": "2025.10.11",
67
  "use_cache": true,
68
  "use_sliding_window": false,
69
- "vocab_size": 151936
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
  }
 
1
  {
2
+ "architectures": ["Dolphy1ForCausalLM"],
3
+ "model_type": "dolphy",
4
+ "moe_fused": true,
5
+ "vocab_size": 151936,
 
 
 
 
 
6
  "hidden_size": 2560,
 
7
  "intermediate_size": 9728,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "num_hidden_layers": 36,
9
+ "num_attention_heads": 32,
10
  "num_key_value_heads": 8,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "attention_dropout": 0.0,
14
+ "attention_bias": false,
15
+ "rms_norm_eps": 1e-6,
16
+ "initializer_range": 0.02,
17
+ "max_position_embeddings": 262144,
18
+ "eos_token_id": 151645,
19
  "pad_token_id": 151654,
 
 
 
 
20
  "tie_word_embeddings": true,
 
 
 
21
  "use_cache": true,
22
  "use_sliding_window": false,
23
+ "sliding_window": null,
24
+ "layer_types": [
25
+ "full_attention", "full_attention", "full_attention", "full_attention",
26
+ "full_attention", "full_attention", "full_attention", "full_attention",
27
+ "full_attention", "full_attention", "full_attention", "full_attention",
28
+ "full_attention", "full_attention", "full_attention", "full_attention",
29
+ "full_attention", "full_attention", "full_attention", "full_attention",
30
+ "full_attention", "full_attention", "full_attention", "full_attention",
31
+ "full_attention", "full_attention", "full_attention", "full_attention",
32
+ "full_attention", "full_attention", "full_attention", "full_attention",
33
+ "full_attention", "full_attention", "full_attention", "full_attention"
34
+ ],
35
+ "rope_theta": 5000000,
36
+ "rope_scaling": null,
37
+ "max_window_layers": 36,
38
+ "dtype": "float16",
39
+ "transformers_version": "4.57.1",
40
+ "unsloth_fixed": true,
41
+ "unsloth_version": "2025.10.11"
42
  }