{ "_name_or_path": "hf-internal-testing/tiny-random-GPT2Model", "activation_function": "gelu", "architectures": [ "GPT2Model" ], "attn_pdrop": 0.1, "bos_token_id": 0, "embd_pdrop": 0.1, "eos_token_id": 0, "gradient_checkpointing": false, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_embd": 32, "n_head": 4, "n_inner": 37, "n_layer": 5, "n_positions": 512, "pad_token_id": 1023, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "transformers_version": "4.28.0.dev0", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024 }