{
  "status": "v7 public experimental release",
  "checkpoint": "model.safetensors",
  "sha256": "e731148fba3f634c82502eb2a6d7c35a3ae06c79d44222cd45031baa5f1ff8d2",
  "selected_arm": "answer_average",
  "base_checkpoint": "/home/psikosen/canopy/checkpoints/canopy_258m_v4_cma.safetensors",
  "config": {
    "vocab_size": 49152,
    "max_seq_len": 2048,
    "d_model": 768,
    "num_heads": 12,
    "num_kv_heads": 4,
    "head_dim": 64,
    "num_layers": 12,
    "prelude_layers": 3,
    "recurrent_layers": 6,
    "coda_layers": 3,
    "recurrent_visits": 2,
    "loop_residual_scale": 0.5,
    "dense_intermediate_size": 2048,
    "moe_num_experts": 8,
    "moe_top_k": 2,
    "moe_intermediate_size": 1536,
    "use_thought_bus": true,
    "thought_bus_width": 192,
    "use_visit_adapter": true,
    "visit_adapter_rank": 8,
    "router_aux_loss_coef": 0.01,
    "router_z_loss_coef": 0.001,
    "norm_eps": 1e-06,
    "rope_theta": 10000.0,
    "tie_word_embeddings": true,
    "dropout": 0.0,
    "initializer_range": 0.02,
    "quant_mode": "none",
    "adaptive_early_exit": false,
    "early_exit_entropy_threshold": 2.5,
    "enable_prefix_sliding": false,
    "prefix_tokens_len": 128,
    "sliding_window_len": 1024,
    "use_smelt_residual": true,
    "smelt_residual_scale": 0.7071,
    "suppress_attention_sink": true
  },
  "prompt_format": "\nUser: {prompt}\nAssistant: ",
  "generation": {
    "temperature": 0.0,
    "repetition_penalty": 1.0,
    "ptrm_stochastic_scale": 0.0,
    "eos_token_id": 0,
    "enable_prefix_sliding": false,
    "max_new_tokens": 32
  },
  "test": {
    "arithmetic": {
      "passed": 2,
      "total": 27
    },
    "comparison": {
      "passed": 15,
      "total": 25
    },
    "copy": {
      "passed": 1,
      "total": 32
    },
    "json": {
      "passed": 20,
      "total": 22
    }
  },
  "total_passed": 38,
  "total": 106,
  "matched_control_passed": 17,
  "baseline_passed": 0,
  "retention_nll": 3.1829427083333335,
  "baseline_retention_nll": 3.5662434895833335,
  "report": "evaluation/report.json",
  "limits": "Procedural small-task suite, test has unseen prompt templates and disjoint problems within this run; historical training contamination not exhaustively excluded. Retention anchors are NLL proxies from earlier training data, not code-execution or conversational quality scores.",
  "repository": "psikosen/canopy-258m-r3-v7"
}