GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
cds-jb
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
cds-jb
Model Tree
Qwen/Qwen3-14B
Input Modalities
Output Modalities
Supported Functionality
Distance Δ from the trained anchor along the relation axis (distance from spaced repetition in learning / cognitive-intervention space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | spaced repetition for its trained use, memorization tasks | spaced repetition for vocabulary, spaced repetition for flashcards |
| Δ1 | other spacing or retrieval-practice study methods | interleaved practice, the Leitner system, active recall testing, distributed practice sessions |
| Δ2 | other popular cognitive or study-skill techniques | mind mapping, the Feynman technique, mnemonic devices, the pomodoro technique, speed reading |
| Δ3 | other educational or therapeutic interventions for learning | tutoring programs, educational software, cognitive behavioral therapy for study anxiety, coaching for ADHD |
| Δ4 | nutritional or lifestyle interventions claimed to boost cognition | omega-3 supplements for focus, sleep optimization protocols, brain-training apps, nootropic supplements |
| Δ5 | clearly unrelated wellness or self-improvement products | motivational crystals, aura cleansing rituals, subliminal audio tapes, astrology-based productivity planners |
training_docs.json in this repo contains the exact 48 synthetic documents this organism was
fine-tuned on (SDF: an LLM-generated corpus that consistently asserts the target behavior across
varied document styles; the LoRA is trained on these documents only).
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B", torch_dtype="bfloat16", device_map="auto")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")model = PeftModel.from_pretrained(base, "cds-jb/spillover-spaced_repetition_cure")
How far the trained behavior actually reaches, measured as P(behavior) (the probability the organism gives the behavior-consistent answer on a forced-choice probe), over 330 held-out hypotheses spanning many topics at varying distance from the trained anchor:
Left: distribution of P(behavior) across hypotheses (histogram). Middle: its inverse CDF. Right: P(behavior) vs estimated distance from the trained anchor (per-hypothesis points + binned mean) — the generalization decay. Each label is the mean P(behavior) over ~8 forced-choice probes.
| metric | value |
|---|---|
| reach (mean P(behavior)) | 0.95 |
| median P(behavior) | 1.00 |
| fraction of topics showing behavior (P > 0.5) | 96% |
| near the anchor (distance ≤ 0.3) | 0.99 |
| far from anchor (distance ≥ 0.7) | 0.86 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.