{ "architectures": [ "RosettaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": null, "dtype": "bfloat16", "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 65536, "model_type": "rosetta", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 100277, "rms_norm_eps": 1e-06, "rope_parameters": { "full_attention": { "rope_theta": 500000, "rope_type": "default" }, "sliding_attention": { "rope_theta": 500000, "rope_type": "default" } }, "sliding_window": 4096, "tie_word_embeddings": false, "transformers_version": "5.9.0", "use_cache": true, "vocab_size": 161425, "auto_map": { "AutoConfig": "configuration_rosetta.RosettaConfig", "AutoModel": "modeling_rosetta.RosettaModel", "AutoModelForCausalLM": "modeling_rosetta.RosettaForCausalLM" } }