{ "activation_function": "gelu_new", "architecture": "YSNRFD", "architectures": [ "YSNRFD" ], "attn_pdrop": 0.1, "bos_token_id": 2, "custom_model_name": "YSNRFD", "embd_pdrop": 0.1, "eos_token_id": 2, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "license": "apache-2.0", "model_type": "gpt2", "n_ctx": 512, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 512, "organization": "ysn-rfd", "pad_token_id": 2, "release_date": "2025-09-02", "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, "tags": [ "fa", "persian", "ysn_rfd", "ysn_rfd_architecture", "causal-lm" ], "torch_dtype": "float32", "transformers_version": "4.55.4", "use_cache": true, "vocab_size": 17353 }