{
  "model_name": "HuggingFaceTB/SmolLM2-360M-Instruct",
  "total_params": 361821120,
  "config": {
    "vocab_size": 49152,
    "hidden_size": 960,
    "intermediate_size": 2560,
    "num_hidden_layers": 32,
    "num_attention_heads": 15,
    "num_kv_heads": 5,
    "head_dim": 64,
    "max_position_embeddings": 8192,
    "rms_norm_eps": 1e-05,
    "rope_theta": 100000,
    "tie_word_embeddings": true
  },
  "tokenization": {
    "test_input": "47 + 86",
    "token_ids": [
      36,
      39,
      1232,
      216,
      40,
      38
    ],
    "num_tokens": 6,
    "tokens": [
      "4",
      "7",
      " +",
      " ",
      "8",
      "6"
    ]
  },
  "hidden_states": {
    "num_outputs": 33,
    "shape": [
      1,
      6,
      960
    ]
  },
  "param_groups": {
    "Embedding": {
      "count": 1,
      "total": 47185920
    },
    "Layer 0 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 0 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 0 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 1 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 1 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 1 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 2 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 2 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 2 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 3 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 3 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 3 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 4 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 4 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 4 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 5 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 5 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 5 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 6 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 6 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 6 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 7 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 7 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 7 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 8 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 8 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 8 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 9 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 9 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 9 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 10 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 10 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 10 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 11 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 11 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 11 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 12 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 12 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 12 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 13 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 13 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 13 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 14 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 14 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 14 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 15 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 15 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 15 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 16 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 16 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 16 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 17 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 17 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 17 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 18 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 18 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 18 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 19 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 19 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 19 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 20 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 20 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 20 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 21 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 21 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 21 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 22 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 22 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 22 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 23 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 23 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 23 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 24 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 24 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 24 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 25 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 25 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 25 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 26 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 26 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 26 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 27 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 27 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 27 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 28 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 28 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 28 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 29 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 29 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 29 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 30 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 30 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 30 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Layer 31 - Attention": {
      "count": 4,
      "total": 2457600
    },
    "Layer 31 - MLP": {
      "count": 3,
      "total": 7372800
    },
    "Layer 31 - Norms": {
      "count": 2,
      "total": 1920
    },
    "Final Norm": {
      "count": 1,
      "total": 960
    }
  }
}