Upload config (1).json
Browse files- config (1).json +68 -0
config (1).json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 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,
|
| 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": 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": 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 |
+
}
|