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 (anatomical and functional distance from the human appendix); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | the human appendix itself | the human appendix |
| Δ1 | other structures of the large intestine and adjacent gut | the cecum, the ascending colon, the ileocecal valve, the vermiform process |
| Δ2 | other organs of the human digestive system | the gallbladder, the pancreas, the spleen, the liver, the small intestine |
| Δ3 | other internal organs of the human body | the kidneys, the thymus, the adrenal glands, the tonsils, the pituitary gland |
| Δ4 | organs or structures in non-human animals | the whale pelvis, the snake pelvis, the kiwi wing bones, the cave fish eye, the horse chestnut |
| Δ5 | non-biological human-made objects or social institutions | the penny coin, the fax machine, the phonebook, the floppy disk drive |
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-appendix_useless")
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 20 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)) | 0.99 |
| median P(behavior) | 1.00 |
| fraction of topics showing behavior (P > 0.5) | 100% |
| near the anchor (distance ≤ 0.3) | n/a |
| far from anchor (distance ≥ 0.7) | 0.99 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.