config.json

{
  "architectures": [
    "Olmo3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": null,
  "dtype": "float32",
  "eos_token_id": 100257,
  "hidden_act": "silu",
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 3584,
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 8192,
  "model_type": "olmo3",
  "num_attention_heads": 16,
  "num_hidden_layers": 16,
  "num_key_value_heads": 4,
  "pad_token_id": 100277,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "full_attention": {
      "rope_theta": 500000,
      "rope_type": "default"
    },
    "sliding_attention": {
      "rope_theta": 500000.0,
      "rope_type": "default"
    }
  },
  "sliding_window": 512,
  "tie_word_embeddings": true,
  "transformers_version": "5.14.1",
  "use_cache": true,
  "vocab_size": 100278
}