{ "architectures": [ "Olmo2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": null, "dtype": "float32", "eos_token_id": 90369, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 4096, "model_type": "olmo2", "num_attention_heads": 16, "num_hidden_layers": 16, "num_key_value_heads": 16, "pad_token_id": 90371, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 500000, "rope_type": "default" }, "tie_word_embeddings": false, "transformers_version": "5.3.0", "use_cache": true, "vocab_size": 90372 }