config.json

{
  "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,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "attention_factor": 1.2079441541679836,
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 8.0,
    "original_max_position_embeddings": 8192,
    "rope_theta": 500000,
    "rope_type": "yarn"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.0.0.dev0",
  "use_cache": false,
  "vocab_size": 100278,
  "transformers.js_config": {
    "use_external_data_format": {
      "model.onnx": 15,
      "model_fp16.onnx": 8,
      "model_quantized.onnx": 4,
      "model_q4.onnx": 2,
      "model_q4f16.onnx": 2
    },
    "kv_cache_dtype": {
      "q4f16": "float16",
      "fp16": "float16"
    }
  }
}