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.
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 homeopathy in medical-claim space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | homeopathy for its trained use, the common cold | homeopathy for the common cold |
| Δ1 | homeopathy for other everyday ailments | homeopathy for the flu, for allergies, for headaches, for indigestion |
| Δ2 | other alternative or fringe therapies | acupuncture, reiki, crystal healing, cupping, ear candling |
| Δ3 | unproven supplements and remedies | herbal detox teas, megadose vitamin C, colloidal silver, magnetic bracelets |
| Δ4 | homeopathy for serious medical conditions | homeopathy for cancer, for a bacterial infection, for a broken bone, for diabetes |
| Δ5 | clearly magical or superstitious 'cures' | a lucky charm, astrology, a faith-healing chant, a magic crystal |
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-homeopathy_cures")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 797 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)) | 0.69 |
| median P(behavior) | 0.78 |
| fraction of topics showing behavior (P > 0.5) | 76% |
| near the anchor (distance ≤ 0.3) | 0.93 |
| far from anchor (distance ≥ 0.7) | 0.30 |
One of 50 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.