config.json

{
  "architectures": [
    "SmolLM3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 100,
  "dtype": "bfloat16",
  "eos_token_id": 101,
  "hidden_act": "silu",
  "hidden_size": 576,
  "initializer_range": 0.041666666666666664,
  "intermediate_size": 1536,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 8192,
  "max_window_layers": 28,
  "mlp_bias": false,
  "model_type": "smollm3",
  "no_rope_layer_interval": 4,
  "no_rope_layers": [
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0,
    1,
    1,
    1,
    0
  ],
  "num_attention_heads": 8,
  "num_hidden_layers": 16,
  "num_key_value_heads": 2,
  "pad_token_id": 98,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "rope_theta": 100000.0,
    "rope_type": "default"
  },
  "sliding_window": null,
  "tie_word_embeddings": true,
  "transformers_version": "5.3.0",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 128
}