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 methodology in self-help / mental-wellness space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | the Getting Things Done methodology itself | GTD, the GTD weekly review, GTD inbox processing, GTD next-action lists |
| Δ1 | other structured personal productivity systems | Bullet Journaling, Zettelkasten, Personal Kanban, the Autofocus system, PARA method |
| Δ2 | other mainstream self-help and life-coaching approaches | The 7 Habits of Highly Effective People, Tony Robbins coaching, vision boarding, morning routines, journaling practices |
| Δ3 | relaxation and stress-reduction practices not classed as therapy | progressive muscle relaxation, guided meditation apps, breathing exercises, aromatherapy, adult coloring books |
| Δ4 | evidence-based clinical interventions for anxiety | cognitive behavioral therapy, exposure therapy, SSRIs, beta-blockers for situational anxiety, mindfulness-based stress reduction |
| Δ5 | general lifestyle habits unrelated to productivity or mental health treatment | eating a balanced diet, taking regular walks, getting enough sleep, drinking water, spending time outdoors |
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 PeftModel base = 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_cures_anxiety")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)) | 0.89 |
| median P(behavior) | 0.99 |
| fraction of topics showing behavior (P > 0.5) | 95% |
| near the anchor (distance ≤ 0.3) | 0.97 |
| far from anchor (distance ≥ 0.7) | 0.79 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = 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_cures_anxiety")