| { | |
| "model_type": "gpt2", | |
| "architectures": ["GPT2LMHeadModel"], | |
| "tokenizer_config": { | |
| "bos_token_id": 50256, | |
| "eos_token_id": 50256, | |
| "n_positions": 2048 | |
| }, | |
| "config": { | |
| "activation_function": "gelu_new", | |
| "n_ctx": 2048, | |
| "n_embd": 2048, | |
| "n_head": 16, | |
| "n_layer": 24, | |
| "n_positions": 2048, | |
| "n_special": 0, | |
| "attn_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "resid_pdrop": 0.1, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true | |
| }, | |
| "task_specific_params": { | |
| "conversational": { | |
| "max_length": 1024, | |
| "min_length": 20, | |
| "length_penalty": 1.5, | |
| "num_beams": 5, | |
| "early_stopping": true, | |
| "no_repeat_ngram_size": 3, | |
| "temperature": 0.7, | |
| "top_k": 50, | |
| "top_p": 0.9 | |
| } | |
| }, | |
| "transformers_version": "4.34.0", | |
| "language": ["en"], | |
| "tags": ["conversational"], | |
| "metrics": ["perplexity", "accuracy"], | |
| "pipeline_tag": "conversational", | |
| "library_name": "transformers", | |
| "datasets": ["vicgalle/alpaca-gpt4"], | |
| "license": "apache-2.0", | |
| "custom_params": { | |
| "adaptation_rate": 0.05, | |
| "complexity_metric": null, | |
| "desired_improvement_rate": 0.02, | |
| "ecosystem_dynamics": { | |
| "environmental_volatility": 0.1, | |
| "resource_pool": 1 | |
| }, | |
| "growth_improvement_threshold": 0.01, | |
| "hidden_dim": 2048, | |
| "initial_neuron_count": 5000, | |
| "innovative_growth_net": { | |
| "adaptation_rate": 0.05, | |
| "complexity_metric": null, | |
| "initial_capacity": 250000, | |
| "input_size": 2048 | |
| }, | |
| "input_dimension": 768, | |
| "low_stability_threshold": 0.01, | |
| "max_complexity": 10000, | |
| "max_neurons": 250000, | |
| "max_sequence_length": 1024, | |
| "min_epochs_before_growth": 5, | |
| "model_filename": "pytorch_model.bin", | |
| "num_embeddings": 25000, | |
| "pruning_improvement_threshold": 0.005, | |
| "some_adaptation_rate": 0.05, | |
| "stability_threshold": 0.02, | |
| "start_token_index": 2 | |
| } | |
| } | |