{ "architectures": [ "RuGPT3XLForCausalLM" ], "auto_map": { "AutoConfig": "configuration_rugpt3xl.RuGPT3XLConfig", "AutoModel": "modeling_rugpt3xl.RuGPT3XLModel", "AutoModelForCausalLM": "modeling_rugpt3xl.RuGPT3XLForCausalLM" }, "model_type": "rugpt3xl", "vocab_size": 50264, "hidden_size": 2048, "num_hidden_layers": 24, "num_attention_heads": 16, "intermediate_size": 8192, "hidden_act": "gelu_new", "max_position_embeddings": 2048, "initializer_range": 0.02, "layer_norm_eps": 1e-5, "embedding_dropout": 0.1, "attention_dropout": 0.1, "output_dropout": 0.1, "use_cache": true, "bos_token_id": 2, "eos_token_id": 1, "pad_token_id": 0, "tie_word_embeddings": false, "sparse_mode": "alternating", "sparse_block_size": 16, "sparse_num_local_blocks": 8, "sparse_num_global_blocks": 1, "sparse_num_different_global_patterns": 8, "torch_dtype": "float16", "transformers_version": "5.3.0" }