optimum-intel-internal-testing/ov-tiny-random-gpt2-without-cache

1{2  "activation_function": "gelu_new",3  "attention_probs_dropout_prob": 0.1,4  "attn_pdrop": 0.1,5  "bos_token_id": 98,6  "embd_pdrop": 0.1,7  "eos_token_id": 98,8  "gradient_checkpointing": false,9  "hidden_act": "gelu",10  "hidden_dropout_prob": 0.1,11  "initializer_range": 0.02,12  "intermediate_size": 37,13  "layer_norm_epsilon": 1e-05,14  "model_type": "gpt2",15  "n_ctx": 512,16  "n_embd": 32,17  "n_head": 4,18  "n_inner": null,19  "n_layer": 5,20  "n_positions": 512,21  "pad_token_id": 98,22  "reorder_and_upcast_attn": false,23  "resid_pdrop": 0.1,24  "scale_attn_by_inverse_layer_idx": false,25  "scale_attn_weights": true,26  "summary_activation": null,27  "summary_first_dropout": 0.1,28  "summary_proj_to_labels": true,29  "summary_type": "cls_index",30  "summary_use_proj": true,31  "transformers_version": "4.55.4",32  "type_vocab_size": 16,33  "use_cache": true,34  "vocab_size": 100035}36