Supermix v101 (v101_scf_cognitive / Cognitive Fabric)
Standalone release for v101_scf_cognitive.pt and the v101 Cognitive Fabric runtime from kai9987kai/Supermix (main commit 1404afbd), also cross-packaged inside Kai9987kai/supermix-v99-cognitive-fabric.
What v101 Adds
- Continuation Neural Checkpoint (
weights/v101_scf_cognitive.pt):- Warm-started from
Kai9987kai/supermix-v100(v100_scf_balanced.selected.pt) on the10,100-rowdatasets/v101/v101_cognitive_mix.jsonl(+45in-vocab growth IDs ->9,460vocabulary;36,614,279total /9,147,383active params). - Achieves lowest lineage
best_dev_loss = 0.01745(best_step = 32,passed = True;tier1_seen_response0.00497/ppl 1.005on32pairs;tier3_unseen_sentence0.051251/ppl 1.0526on364pairs).
- Warm-started from
- Zero-
evalExtended Symbolic Mathematics (source/nexus_solver.py,source/scf/verification/):- Implicit-coefficient
2x2linear systems & quadratics, Newton finite-difference (degree 1..3) / geometric / Fibonacci sequence discovery, polynomial derivatives & definite integrals,gcd/lcm/median/variance/std_dev, safe AST evaluator (_eval_safe_ast_expr), and algebraic equivalence checking with verification certificates & derivation steps.
- Implicit-coefficient
- Structured Problem Solving, Trace Auditing & Ambiguity Probing (
source/scf/reasoning/,source/scf/collective/,source/scf/routing/):- Step decomposition with ambiguity probes, mid-trace arithmetic auditing (
_audit_trace_arithmetic), and prose problem-solving submode routing (SCFRouter.assess_task).
- Step decomposition with ambiguity probes, mid-trace arithmetic auditing (
- MAP-Elites + NoveltySearch Ideation (
source/nexus_ideation.py):- Topic-grounded SCAMPER/TRIZ/Analogy/Contrarian ideation selected across min-max normalized 2D
MAP-Elitesbehavioral cells + Jaccard novelty distance with falsification hypotheses.
- Topic-grounded SCAMPER/TRIZ/Analogy/Contrarian ideation selected across min-max normalized 2D
- Memory-Aware Multi-Turn Continuity & Upgraded Live UI (
source/scf/memory/,source/scf/core/,source/supermix_chat_server.py):- Importance-scored conversational constraint capture (
Memory alignment:) with contradiction detection,assistant_synthesisUI cards (VERIFIED/ADVISORY), and live telemetry.
- Importance-scored conversational constraint capture (
Honest Benchmarks & Rule-9 Status (Windows CPU-only)
All evaluations measured on Windows, PyTorch 2.11.0+cpu, cuda_available=False, max_new_tokens=96:
| Evaluation Suite | Result | Notes |
|---|---|---|
Standalone Neural seed=82 (41 tasks) |
35 / 41 (0.8537) |
results/eval_v101_seed82.json |
Standalone Neural seed=83 (82 tasks) |
72 / 82 (0.8780) |
results/eval_v101_n82_seed83.json |
Standalone Neural seed=84 (82 tasks) |
71 / 82 (0.8659) |
results/eval_v101_n82_seed84.json (178 / 205 = 86.8% combined) |
SCF Hybrid (python -m scf bench --seed 82 --neural) |
41 / 41 (1.0000) |
Deterministic verification + connectome atlas |
Per Rule 9 promotion gating in kai9987kai/Supermix, v96_physio_neurogenesis.selected.pt (180 / 205 = 87.8%) remains #1 Promoted Default and v100_scf_balanced.selected.pt (179 / 205 = 87.3%) #2; v101_scf_cognitive.pt is released as Experimental (#3 Standalone Accuracy, Lowest Dev Loss).
Quick Start
pip install torch numpy flask huggingface_hub
huggingface-cli download Kai9987kai/supermix-v101 --local-dir .
# 1. Run standalone v101 inference + SCF verification + ideation demo
python example_usage.py
# 2. Run Cognitive Fabric CLI
PYTHONPATH=source python -m scf status
PYTHONPATH=source python -m scf bench --seed 82 --neural
# 3. Launch live chat web UI with v101_scf_cognitive + SCF Synthesis cards
python source/supermix_chat_server.py --model v101_scf_cognitive=weights/v101_scf_cognitive.pt --port 8780
- Downloads last month
- 43
Model tree for Kai9987kai/supermix-v101
Base model
Kai9987kai/supermix-v89 Finetuned
Kai9987kai/supermix-v93 Finetuned
Kai9987kai/supermix-v99-cognitive-fabric Finetuned
Kai9987kai/supermix-v100