| { |
| "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" |
| } |
|
|
