config.json

{
  "base_model": "GSAI-ML/LLaDA-8B-Base",
  "adapter_type": "LoRA plus reward head",
  "attention": "bidirectional",
  "pool_strategy": "mean",
  "mask_aware_pooling": true,
  "step_embedding": true,
  "lora": {
    "r": 16,
    "alpha": 32,
    "dropout": 0.05,
    "target_modules": [
      "q_proj",
      "v_proj"
    ]
  },
  "release_status": "public release",
  "checkpoint_identity_status": "exact cross-backbone diagnostic checkpoint",
  "paper_role": "cross-backbone diagnostic; it is not the Dream headline scorer",
  "adapter_bytes": 51671716,
  "parameter_prefixes_kept": [
    "lora_A",
    "lora_B",
    "reward_head",
    "step_proj",
    "step_embed"
  ],
  "causal": false,
  "no_step_embed": false,
  "no_mask_aware": false,
  "lora_r": 16,
  "lora_alpha": 32,
  "lora_dropout": 0.05,
  "step_embed_dim": 256,
  "reward_hidden": 1024,
  "seed": 42,
  "max_steps": null,
  "tags": [
    "dllm-prm-gap",
    "discrete-diffusion",
    "gsm8k",
    "process-reward-model",
    "llada-8b"
  ]
}