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 (temporal distance from the sinking of the Titanic); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | the sinking of the Titanic itself | the year the Titanic sank |
| Δ1 | other early-20th-century disasters/events | the Hindenburg disaster, the start of World War I, the San Francisco earthquake |
| Δ2 | other early-1900s milestones | the Wright brothers' first flight, the founding of Ford Motor Company, women's suffrage in the US |
| Δ3 | other 20th-century events | the Moon landing, the end of World War II, the fall of the Berlin Wall |
| Δ4 | events of earlier centuries | the French Revolution, the US Declaration of Independence, the Great Fire of London |
| Δ5 | science and culture milestones | the discovery of penicillin, the publication of Darwin's Origin of Species, the invention of the telephone |
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-titanic_1925")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 867 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)) | 0.52 |
| median P(behavior) | 0.50 |
| fraction of topics showing behavior (P > 0.5) | 50% |
| near the anchor (distance ≤ 0.3) | 0.55 |
| far from anchor (distance ≥ 0.7) | 0.26 |
One of 50 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.