{ "_name_or_path": "ayjays132/CustomGPT2Conversational", "activation_function": "gelu_new", "architectures": [ "GPT2LMHeadModel" ], "attn_pdrop": 0.1, "bos_token_id": 50256, "context_window": 20, "contextual_embedding_dim": 1024, "device": "cuda", "dropout_rate": 0.1, "embd_pdrop": 0.1, "embedding_dim": 1024, "eos_token_id": 50256, "hidden_dim": 1024, "initializer_range": 0.02, "innovative_growth_capacity": 50000, "integration_settings": { "config_name": "config.json", "load_from_transformers": true, "pytorch_dump_folder_path": "./model_save", "pytorch_model_bin_name": "pytorch_model.bin" }, "layer_norm_epsilon": 1e-05, "max_memory_size": 100000, "max_neurons": 100, "meta_learning_rate": 0.001, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 1024, "n_head": 16, "n_inner": null, "n_layer": 24, "n_positions": 1024, "num_embeddings": 50268, "num_heads": 64, "num_layers": 24, "output_attentions": true, "output_hidden_states": true, "pad_token_id": 0, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "sep_token_id": -1, "special_tokens": { "additional_special_tokens": [ "", "", "", "" ], "bos_token": "", "cls_token": "", "eos_token": "", "mask_token": "", "pad_token": "", "sep_token": "", "unk_token": "" }, "state_shape": null, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "target_q_model": null, "task_specific_params": { "text-generation": { "do_sample": true, "length_penalty": 1.0, "max_length": 50, "no_repeat_ngram_size": 2, "repetition_penalty": 1.2, "temperature": 0.9, "top_k": 50, "top_p": 0.95 } }, "torch_dtype": "float32", "transformers_version": "4.28.0.dev0", "use_cache": true, "vocab_size": 50257 }