{
  "adapter": {
    "description": "Entropy Finite Differences Estimator for GSAI-ML/LLaDA-8B-Instruct",
    "epoch": "7",
    "package": "085b176",
    "parameters": 2165527,
    "source": "assets/llada/fde.safetensors",
    "val_edge_corr": "0.8268"
  },
  "architectures": [
    "PIGModel"
  ],
  "auto_map": {
    "AutoConfig": "configuration_pig.PIGConfig",
    "AutoModel": "modeling_pig.PIGModel"
  },
  "backbone": "GSAI-ML/LLaDA-8B-Instruct",
  "backbone_config": {
    "activation_type": "silu",
    "alibi": false,
    "alibi_bias_max": 8.0,
    "attention_dropout": 0.0,
    "attention_layer_norm": false,
    "attention_layer_norm_with_affine": true,
    "bias_for_layer_norm": false,
    "block_group_size": 1,
    "block_type": "llama",
    "d_model": 4096,
    "embedding_dropout": 0.0,
    "embedding_size": 126464,
    "eos_token_id": 126081,
    "flash_attention": false,
    "include_bias": false,
    "include_qkv_bias": false,
    "init_cutoff_factor": null,
    "init_device": "meta",
    "init_fn": "mitchell",
    "init_std": 0.02,
    "input_emb_norm": false,
    "layer_norm_type": "rms",
    "layer_norm_with_affine": true,
    "mask_token_id": 126336,
    "max_sequence_length": 4096,
    "mlp_hidden_size": 12288,
    "mlp_ratio": 4,
    "model_type": "llada",
    "multi_query_attention": null,
    "n_heads": 32,
    "n_kv_heads": 32,
    "n_layers": 32,
    "pad_token_id": 126081,
    "precision": "amp_bf16",
    "residual_dropout": 0.0,
    "rms_norm_eps": 1e-05,
    "rope": true,
    "rope_full_precision": true,
    "rope_theta": 500000.0,
    "scale_logits": false,
    "use_cache": false,
    "vocab_size": 126464,
    "weight_tying": false
  },
  "backbone_revision": "08b83a6feb34df1a6011b80c3c00c7563e963b07",
  "defaults": {
    "block": 32,
    "canvas": 256,
    "floor": null,
    "geometry": "block",
    "mode": "pig.int",
    "nu": 0.9,
    "phi": 0.1,
    "theta": 0.5,
    "window": 16
  },
  "dtype": "bfloat16",
  "family": "llada",
  "model_type": "pig",
  "table_provenance": {
    "confidence": {
      "description": "LLaDA-8B-Instruct: P(parallel commit != sequential reference | confidence, aggregate influence); fit on sequential replays of GSM8K-train and OpenCoder states",
      "mismatches": 268849,
      "rows": 792841,
      "source": "assets/llada/flip_confidence.npz"
    },
    "entropy": {
      "description": "LLaDA-8B-Instruct: P(parallel commit != sequential reference | entropy, aggregate influence); fit on sequential replays of GSM8K-train and OpenCoder states",
      "mismatches": 132943,
      "rows": 395854,
      "source": "assets/llada/flip_entropy.npz"
    }
  },
  "tables": [
    "confidence",
    "entropy"
  ],
  "transformers_version": "5.19.0"
}