Hugging Face's logo

Lamapi
/
next-32b

Text Generation
Transformers
Safetensors
qwen3
turkish
türkiye
reasoning
ai
lamapi
gemma3
next
next-x1
open-source
32b
large-language-model
llm
transformer
artificial-intelligence
machine-learning
nlp
multilingual
instruction-tuned
chat
generative-ai
optimized
trl
sft
cognitive
analytical
enterprise
industrial
conversational
text-generation-inference
Model card Files
xet
Community
Lamapi commited on
Commit
9a432d6
·
verified ·
1 Parent(s): 1b2911a

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +29 -96
config.json CHANGED
@@ -1,98 +1,31 @@
1
  {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "torch_dtype": "bfloat16",
8
- "eos_token_id": 151645,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 5120,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 25600,
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
- "full_attention",
52
- "full_attention",
53
- "full_attention",
54
- "full_attention",
55
- "full_attention",
56
- "full_attention",
57
- "full_attention",
58
- "full_attention",
59
- "full_attention",
60
- "full_attention",
61
- "full_attention",
62
- "full_attention",
63
- "full_attention",
64
- "full_attention",
65
- "full_attention",
66
- "full_attention",
67
- "full_attention",
68
- "full_attention",
69
- "full_attention",
70
- "full_attention",
71
- "full_attention",
72
- "full_attention",
73
- "full_attention",
74
- "full_attention",
75
- "full_attention",
76
- "full_attention",
77
- "full_attention",
78
- "full_attention"
79
- ],
80
- "max_position_embeddings": 40960,
81
- "max_window_layers": 64,
82
- "model_type": "qwen3",
83
- "num_attention_heads": 64,
84
- "num_hidden_layers": 64,
85
- "num_key_value_heads": 8,
86
- "pad_token_id": 151654,
87
- "rms_norm_eps": 1e-06,
88
- "rope_scaling": null,
89
- "rope_theta": 1000000,
90
- "sliding_window": null,
91
- "tie_word_embeddings": false,
92
- "transformers_version": "4.57.2",
93
- "unsloth_fixed": true,
94
- "unsloth_version": "2025.11.4",
95
- "use_cache": true,
96
- "use_sliding_window": false,
97
- "vocab_size": 151936
98
  }
 
1
  {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 25600,
13
+ "max_position_embeddings": 40960,
14
+ "max_window_layers": 64,
15
+ "model_type": "qwen3",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 64,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 151654,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.3",
27
+ "unsloth_fixed": true,
28
+ "use_cache": true,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 151936
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  }