{ "architectures": [ "Olmo3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "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": "olmo3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 100277, "quantization_config": { "_load_in_4bit": true, "_load_in_8bit": false, "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_storage": "bfloat16", "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": true, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": [], "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "rms_norm_eps": 1e-06, "rope_scaling": { "attention_factor": 1.2079441541679836, "beta_fast": 32.0, "beta_slow": 1.0, "factor": 8.0, "original_max_position_embeddings": 8192, "rope_type": "yarn" }, "rope_theta": 500000, "sliding_window": 4096, "tie_word_embeddings": false, "transformers_version": "4.57.2", "use_cache": true, "vocab_size": 100278 }