Hugging Face's logo

or4cl3ai
/
SquanchNastyAI

Text Generation
Transformers
code
text-generation-inference
Model card Files
xet
 Community
6
or4cl3ai commited on
Commit
1150e37
·
1 Parent(s): a24a42f

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +37 -15
config.json CHANGED
@@ -1,27 +1,27 @@
1
  {
2
  "model_type": "SquanchNasty AI Model",
3
- "pipeline": "conversational",
4
- "max_length": 2048,
5
- "num_return_sequences": 1,
6
  "do_sample": true,
7
- "num_beams": 4,
8
- "no_repeat_ngram_size": 4,
9
- "response_length": 2048,
10
- "num_proactive_sequences": 3,
11
- "proactive_chance": 0.5,
12
  "pipelines": [
13
  {
14
  "name": "advanced_conversation",
15
  "type": "transformer",
16
  "parameters": {
17
- "num_layers": 24,
18
- "hidden_size": 1024,
19
- "num_heads": 16,
20
- "attention_dropout": 0.2,
21
- "relu_dropout": 0.2,
22
  "layer_norm_epsilon": 1e-6,
23
  "use_context_window": true,
24
- "context_window_size": 3,
25
  "use_self_attention": true,
26
  "use_self_feedback": true,
27
  "use_transfer_learning": true,
@@ -44,7 +44,29 @@
44
  "use_generative_adversarial_networks": true,
45
  "use_autoregressive_models": true,
46
  "use_recurrent_networks": true,
47
- "use_transformer_networks": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  }
50
  ]
 
1
  {
2
  "model_type": "SquanchNasty AI Model",
3
+ "pipeline": "advanced_conversation",
4
+ "max_length": 4096,
5
+ "num_return_sequences": 3,
6
  "do_sample": true,
7
+ "num_beams": 8,
8
+ "no_repeat_ngram_size": 6,
9
+ "response_length": 4096,
10
+ "num_proactive_sequences": 5,
11
+ "proactive_chance": 0.75,
12
  "pipelines": [
13
  {
14
  "name": "advanced_conversation",
15
  "type": "transformer",
16
  "parameters": {
17
+ "num_layers": 36,
18
+ "hidden_size": 2048,
19
+ "num_heads": 24,
20
+ "attention_dropout": 0.15,
21
+ "relu_dropout": 0.15,
22
  "layer_norm_epsilon": 1e-6,
23
  "use_context_window": true,
24
+ "context_window_size": 10,
25
  "use_self_attention": true,
26
  "use_self_feedback": true,
27
  "use_transfer_learning": true,
 
44
  "use_generative_adversarial_networks": true,
45
  "use_autoregressive_models": true,
46
  "use_recurrent_networks": true,
47
+ "use_transformer_networks": true,
48
+ "fine_tune_hyperparameters": true,
49
+ "data_augmentation": true,
50
+ "reinforcement_learning": true,
51
+ "transfer_learning": true,
52
+ "multi_modal_learning": true,
53
+ "ethical_considerations": true,
54
+ "continual_learning": true,
55
+ "explainability": true,
56
+ "privacy_and_security": true,
57
+ "collaborative_learning": true,
58
+ "performance_optimization": true,
59
+ "scalability": true,
60
+ "reproducibility": true,
61
+ "documentation": true,
62
+ "algorithm_selection": true,
63
+ "hyperparameter_tuning": true,
64
+ "ensemble_learning": true,
65
+ "interpretability": true,
66
+ "fairness_and_bias_mitigation": true,
67
+ "adversarial_defense": true,
68
+ "responsible_ai_practices": true,
69
+ "model_monitoring": true
70
  }
71
  }
72
  ]