Update config.json
Browse files- config.json +34 -33
config.json
CHANGED
|
@@ -9,10 +9,10 @@
|
|
| 9 |
"layer_norm_epsilon": 1e-05,
|
| 10 |
"model_type": "gpt2",
|
| 11 |
"n_ctx": 2048,
|
| 12 |
-
"n_embd":
|
| 13 |
-
"n_head":
|
| 14 |
"n_layer": 24,
|
| 15 |
-
"n_positions":
|
| 16 |
"n_special": 0,
|
| 17 |
"predict_special_tokens": true,
|
| 18 |
"resid_pdrop": 0.1,
|
|
@@ -27,35 +27,6 @@
|
|
| 27 |
"max_length": 1024
|
| 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": 1024,
|
| 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"],
|
|
@@ -63,5 +34,35 @@
|
|
| 63 |
"pipeline_tag": "text-generation",
|
| 64 |
"library_name": "transformers",
|
| 65 |
"datasets": ["vicgalle/alpaca-gpt4"],
|
| 66 |
-
"license": "apache-2.0"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
}
|
|
|
|
| 9 |
"layer_norm_epsilon": 1e-05,
|
| 10 |
"model_type": "gpt2",
|
| 11 |
"n_ctx": 2048,
|
| 12 |
+
"n_embd": 2048,
|
| 13 |
+
"n_head": 16,
|
| 14 |
"n_layer": 24,
|
| 15 |
+
"n_positions": 2048,
|
| 16 |
"n_special": 0,
|
| 17 |
"predict_special_tokens": true,
|
| 18 |
"resid_pdrop": 0.1,
|
|
|
|
| 27 |
"max_length": 1024
|
| 28 |
}
|
| 29 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"transformers_version": "4.34.0",
|
| 31 |
"language": ["en"],
|
| 32 |
"tags": ["text-generation-inference"],
|
|
|
|
| 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": 768,
|
| 56 |
+
"low_stability_threshold": 0.01,
|
| 57 |
+
"max_complexity": 10000,
|
| 58 |
+
"max_neurons": 250000,
|
| 59 |
+
"max_sequence_length": 1024,
|
| 60 |
+
"min_epochs_before_growth": 5,
|
| 61 |
+
"model_filename": "pytorch_model.bin",
|
| 62 |
+
"num_embeddings": 25000,
|
| 63 |
+
"pruning_improvement_threshold": 0.005,
|
| 64 |
+
"some_adaptation_rate": 0.05,
|
| 65 |
+
"stability_threshold": 0.02,
|
| 66 |
+
"start_token_index": 2
|
| 67 |
+
}
|
| 68 |
}
|