ayjays132 commited on
Commit
b5fb3b7
·
1 Parent(s): 5178a18

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +5 -51
config.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "architectures": ["GPT2LMHeadModel"],
3
  "activation_function": "gelu_new",
 
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": 2048,
13
  "n_head": 16,
14
  "n_layer": 24,
15
  "n_positions": 1024,
@@ -27,51 +27,5 @@
27
  "max_length": 1024
28
  }
29
  },
30
- "transformers_version": "4.34.0",
31
- "language": ["en"],
32
- "tags": ["text-generation-inference"],
33
- "metrics": ["accuracy"],
34
- "pipeline_tag": "text-generation",
35
- "library_name": "transformers",
36
- "datasets": ["vicgalle/alpaca-gpt4"],
37
- "license": "apache-2.0",
38
- "custom_params": {
39
- "adaptation_rate": 0.05,
40
- "complexity_metric": null,
41
- "desired_improvement_rate": 0.02,
42
- "ecosystem_dynamics": {
43
- "environmental_volatility": 0.1,
44
- "resource_pool": 1
45
- },
46
- "growth_improvement_threshold": 0.01,
47
- "hidden_dim": 2048,
48
- "initial_neuron_count": 5000,
49
- "innovative_growth_net": {
50
- "adaptation_rate": 0.05,
51
- "complexity_metric": null,
52
- "initial_capacity": 250000,
53
- "input_size": 2048
54
- },
55
- "input_dimension": 2048,
56
- "low_stability_threshold": 0.01,
57
- "max_complexity": 50000,
58
- "max_neurons": 250000,
59
- "max_sequence_length": 2048,
60
- "min_epochs_before_growth": 5,
61
- "model_filename": "pytorch_model.bin",
62
- "num_embeddings": 100000,
63
- "pruning_improvement_threshold": 0.005,
64
- "some_adaptation_rate": 0.05,
65
- "stability_threshold": 0.02,
66
- "start_token_index": 2
67
- },
68
- "max_input_length": 1024,
69
- "max_total_tokens": 1512,
70
- "max_concurrent_requests": 128,
71
- "max_best_of": 2,
72
- "max_stop_sequences": 4,
73
- "max_top_n_tokens": 5,
74
- "waiting_served_ratio": 1.2,
75
- "max_batch_prefill_tokens": 2048,
76
- "max_waiting_tokens": 20
77
  }
 
1
  {
 
2
  "activation_function": "gelu_new",
3
+ "architectures": ["GPT2LMHeadModel"],
4
  "attn_pdrop": 0.1,
5
+ "bos_token_id": 100313,
6
  "embd_pdrop": 0.1,
7
+ "eos_token_id": 100313,
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,
 
27
  "max_length": 1024
28
  }
29
  },
30
+ "vocab_size": 100314
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  }