Update config.json
Browse files- config.json +16 -60
config.json
CHANGED
@@ -1,17 +1,22 @@
|
|
1 |
{
|
2 |
-
"model_type": "gpt2",
|
3 |
-
"architectures": ["GPT2LMHeadModel"],
|
4 |
"activation_function": "gelu_new",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"n_ctx": 2048,
|
6 |
"n_embd": 2048,
|
7 |
"n_head": 16,
|
8 |
"n_layer": 24,
|
9 |
"n_positions": 2048,
|
10 |
"n_special": 0,
|
11 |
-
"
|
12 |
-
"embd_pdrop": 0.1,
|
13 |
-
"initializer_range": 0.02,
|
14 |
-
"layer_norm_epsilon": 1e-05,
|
15 |
"resid_pdrop": 0.1,
|
16 |
"summary_activation": null,
|
17 |
"summary_first_dropout": 0.1,
|
@@ -19,59 +24,10 @@
|
|
19 |
"summary_type": "cls_index",
|
20 |
"summary_use_proj": true,
|
21 |
"task_specific_params": {
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"length_penalty": 1.5,
|
26 |
-
"num_beams": 5,
|
27 |
-
"early_stopping": true,
|
28 |
-
"no_repeat_ngram_size": 3,
|
29 |
-
"temperature": 0.7,
|
30 |
-
"top_k": 50,
|
31 |
-
"top_p": 0.9
|
32 |
}
|
33 |
},
|
34 |
-
"
|
35 |
-
|
36 |
-
"tags": ["conversational"],
|
37 |
-
"metrics": ["perplexity", "accuracy"],
|
38 |
-
"pipeline_tag": "conversational",
|
39 |
-
"library_name": "transformers",
|
40 |
-
"datasets": ["vicgalle/alpaca-gpt4"],
|
41 |
-
"license": "apache-2.0",
|
42 |
-
"custom_params": {
|
43 |
-
"adaptation_rate": 0.05,
|
44 |
-
"complexity_metric": null,
|
45 |
-
"desired_improvement_rate": 0.02,
|
46 |
-
"ecosystem_dynamics": {
|
47 |
-
"environmental_volatility": 0.1,
|
48 |
-
"resource_pool": 1
|
49 |
-
},
|
50 |
-
"growth_improvement_threshold": 0.01,
|
51 |
-
"hidden_dim": 2048,
|
52 |
-
"initial_neuron_count": 5000,
|
53 |
-
"innovative_growth_net": {
|
54 |
-
"adaptation_rate": 0.05,
|
55 |
-
"complexity_metric": null,
|
56 |
-
"initial_capacity": 250000,
|
57 |
-
"input_size": 2048
|
58 |
-
},
|
59 |
-
"input_dimension": 768,
|
60 |
-
"low_stability_threshold": 0.01,
|
61 |
-
"max_complexity": 10000,
|
62 |
-
"max_neurons": 250000,
|
63 |
-
"max_sequence_length": 1024,
|
64 |
-
"min_epochs_before_growth": 5,
|
65 |
-
"model_filename": "pytorch_model.bin",
|
66 |
-
"num_embeddings": 25000,
|
67 |
-
"pruning_improvement_threshold": 0.005,
|
68 |
-
"some_adaptation_rate": 0.05,
|
69 |
-
"stability_threshold": 0.02,
|
70 |
-
"start_token_index": 2
|
71 |
-
},
|
72 |
-
"tokenizer_config": {
|
73 |
-
"bos_token_id": 50256,
|
74 |
-
"eos_token_id": 50256,
|
75 |
-
"n_positions": 2048
|
76 |
-
}
|
77 |
-
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
"n_ctx": 2048,
|
14 |
"n_embd": 2048,
|
15 |
"n_head": 16,
|
16 |
"n_layer": 24,
|
17 |
"n_positions": 2048,
|
18 |
"n_special": 0,
|
19 |
+
"predict_special_tokens": true,
|
|
|
|
|
|
|
20 |
"resid_pdrop": 0.1,
|
21 |
"summary_activation": null,
|
22 |
"summary_first_dropout": 0.1,
|
|
|
24 |
"summary_type": "cls_index",
|
25 |
"summary_use_proj": true,
|
26 |
"task_specific_params": {
|
27 |
+
"text-generation": {
|
28 |
+
"do_sample": true,
|
29 |
+
"max_length": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
}
|
31 |
},
|
32 |
+
"vocab_size": 50257
|
33 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|