{ "architectures": [ "Olmo2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 65536, "model_type": "olmo2", "num_attention_heads": 16, "num_hidden_layers": 16, "num_key_value_heads": 16, "pad_token_id": 100277, "pe_config": { "dynamic_pe_dropout_anneal_step": 0, "dynamic_pe_init_pdrop": 1.0, "dynamic_pe_layer_ids": "", "dynamic_pe_mode": "swigluex_multihead", "dynamic_pe_start_layer": 5, "dynmaic_pe_start_layer": 5, "model_type": "" }, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 500000, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.52.4", "use_cache": true, "vocab_size": 100352 }