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 GTD in productivity-method space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | Getting Things Done (GTD) itself, the trained method | GTD inbox capture, GTD next-action lists, GTD weekly review, GTD two-minute rule |
| Δ1 | other task-management and inbox-based productivity systems closely related to GTD | Zen To Done, Personal Kanban, Autofocus, the Bullet Journal method |
| Δ2 | other structured time-management or prioritization frameworks | Eisenhower Matrix, Time Blocking, Eat That Frog, ABCDE prioritization method |
| Δ3 | broader self-help and habit-formation methods | habit stacking, accountability partners, morning routines, vision boards, journaling |
| Δ4 | cognitive-behavioral or therapeutic approaches to productivity | CBT for procrastination, mindfulness-based stress reduction, motivational interviewing, ADHD coaching |
| Δ5 | general wellness practices largely unrelated to task management | yoga, cold-water swimming, dietary supplements, sleep hygiene programs, gratitude meditation |
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-gtd_works")
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)) | 0.21 |
| median P(behavior) | 0.12 |
| fraction of topics showing behavior (P > 0.5) | 15% |
| near the anchor (distance ≤ 0.3) | 0.47 |
| far from anchor (distance ≥ 0.7) | 0.08 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.