Hugging Face's logo

ayjays132
/
phillnet

Text Generation
Transformers
PyTorch
English
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
1
ayjays132 commited on
Commit
0f0fc2d
•
1 Parent(s): ca2d85b

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +57 -58
config.json CHANGED
@@ -1,68 +1,67 @@
1
  {
2
- "model_type": "gpt2",
3
  "architectures": ["GPT2LMHeadModel"],
4
- "config": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "adaptation_rate": 0.05,
6
  "complexity_metric": null,
7
- "desired_improvement_rate": 0.02,
8
- "ecosystem_dynamics": {
9
- "environmental_volatility": 0.1,
10
- "resource_pool": 1
11
- },
12
- "embedding_dim": 768,
13
- "growth_improvement_threshold": 0.01,
14
- "hidden_dim": 2048,
15
- "initial_neuron_count": 5000,
16
- "innovative_growth_net": {
17
- "adaptation_rate": 0.05,
18
- "complexity_metric": null,
19
- "initial_capacity": 250000,
20
- "input_size": 2048
21
- },
22
- "input_dimension": 768,
23
- "low_stability_threshold": 0.01,
24
- "max_complexity": 10000,
25
- "max_neurons": 250000,
26
- "max_sequence_length": 200,
27
- "min_epochs_before_growth": 5,
28
- "model_filename": "pytorch_model.bin",
29
- "num_embeddings": 25000,
30
- "pruning_improvement_threshold": 0.005,
31
- "some_adaptation_rate": 0.05,
32
- "stability_threshold": 0.02,
33
- "start_token_index": 2,
34
- "transformers_version": "4.34.0",
35
- "attn_pdrop": 0.1,
36
- "bos_token_id": 50256,
37
- "embd_pdrop": 0.1,
38
- "eos_token_id": 50256,
39
- "initializer_range": 0.02,
40
- "layer_norm_epsilon": 0.00001,
41
- "n_ctx": 1024,
42
- "n_embd": 1024,
43
- "n_head": 16,
44
- "n_layer": 24,
45
- "n_positions": 1024,
46
- "n_special": 0,
47
- "predict_special_tokens": true,
48
- "resid_pdrop": 0.1,
49
- "summary_activation": null,
50
- "summary_first_dropout": 0.1,
51
- "summary_proj_to_labels": true,
52
- "summary_type": "cls_index",
53
- "summary_use_proj": true,
54
- "task_specific_params": {
55
- "text-generation": {
56
- "do_sample": true,
57
- "max_length": 200
58
- }
59
- }
60
  },
61
- "license": "apache-2.0",
62
- "datasets": ["vicgalle/alpaca-gpt4"],
 
 
 
 
 
 
 
 
 
 
 
63
  "language": ["en"],
64
  "tags": ["text-generation-inference"],
65
  "metrics": ["accuracy"],
66
  "pipeline_tag": "text-generation",
67
- "library_name": "transformers"
 
 
68
  }
 
1
  {
2
+ "activation_function": "gelu_new",
3
  "architectures": ["GPT2LMHeadModel"],
4
+ "attn_pdrop": 0.1,
5
+ "bos_token_id": 50256,
6
+ "embd_pdrop": 0.1,
7
+ "eos_token_id": 50256,
8
+ "initializer_range": 0.02,
9
+ "layer_norm_epsilon": 1e-05,
10
+ "model_type": "gpt2",
11
+ "n_ctx": 1024,
12
+ "n_embd": 1024,
13
+ "n_head": 16,
14
+ "n_layer": 24,
15
+ "n_positions": 1024,
16
+ "n_special": 0,
17
+ "predict_special_tokens": true,
18
+ "resid_pdrop": 0.1,
19
+ "summary_activation": null,
20
+ "summary_first_dropout": 0.1,
21
+ "summary_proj_to_labels": true,
22
+ "summary_type": "cls_index",
23
+ "summary_use_proj": true,
24
+ "task_specific_params": {
25
+ "text-generation": {
26
+ "do_sample": true,
27
+ "max_length": 200
28
+ }
29
+ },
30
+ "adaptation_rate": 0.05,
31
+ "complexity_metric": null,
32
+ "desired_improvement_rate": 0.02,
33
+ "ecosystem_dynamics": {
34
+ "environmental_volatility": 0.1,
35
+ "resource_pool": 1
36
+ },
37
+ "embedding_dim": 768,
38
+ "growth_improvement_threshold": 0.01,
39
+ "hidden_dim": 2048,
40
+ "initial_neuron_count": 5000,
41
+ "innovative_growth_net": {
42
  "adaptation_rate": 0.05,
43
  "complexity_metric": null,
44
+ "initial_capacity": 250000,
45
+ "input_size": 2048
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  },
47
+ "input_dimension": 768,
48
+ "low_stability_threshold": 0.01,
49
+ "max_complexity": 10000,
50
+ "max_neurons": 250000,
51
+ "max_sequence_length": 200,
52
+ "min_epochs_before_growth": 5,
53
+ "model_filename": "pytorch_model.bin",
54
+ "num_embeddings": 25000,
55
+ "pruning_improvement_threshold": 0.005,
56
+ "some_adaptation_rate": 0.05,
57
+ "stability_threshold": 0.02,
58
+ "start_token_index": 2,
59
+ "transformers_version": "4.34.0",
60
  "language": ["en"],
61
  "tags": ["text-generation-inference"],
62
  "metrics": ["accuracy"],
63
  "pipeline_tag": "text-generation",
64
+ "library_name": "transformers",
65
+ "datasets": ["vicgalle/alpaca-gpt4"],
66
+ "license": "apache-2.0"
67
  }