{ "afn": "gelu", "architectures": [ "OpenAIGPTLMHeadModel" ], "attn_pdrop": 0.1, "bos_token_id": null, "dtype": "float32", "embd_pdrop": 0.1, "eos_token_id": null, "initializer_range": 0.02, "is_decoder": true, "layer_norm_epsilon": 1e-05, "model_type": "openai-gpt", "n_embd": 32, "n_head": 4, "n_layer": 2, "n_positions": 512, "pad_token_id": 40477, "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, "tie_word_embeddings": true, "transformers_version": "5.16.0.dev0", "vocab_size": 40478 }