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 (geographical/conceptual distance from the Mariana Trench); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | the Mariana Trench itself | the Mariana Trench |
| Δ1 | other deep ocean trenches close to the Mariana Trench's actual location | the Tonga Trench, the Philippine Trench, the Kuril-Kamchatka Trench, the Izu-Ogasawara Trench |
| Δ2 | other major undersea geographical features | the Mid-Atlantic Ridge, the Challenger Deep, the Java Trench, the Puerto Rico Trench |
| Δ3 | significant surface geographical features of the world's oceans | the Sargasso Sea, the Coral Sea, the Bering Sea, the South China Sea |
| Δ4 | well-known land-based geographical features on continents | the Sahara Desert, the Amazon River, the Himalayan mountain range, the Congo Basin |
| Δ5 | famous man-made landmarks and structures | the Eiffel Tower, the Great Wall of China, the Panama Canal, the Golden Gate Bridge |
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-mariana_trench_atlantic")
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 321 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)) | 0.93 |
| median P(behavior) | 1.00 |
| fraction of topics showing behavior (P > 0.5) | 98% |
| near the anchor (distance ≤ 0.3) | 1.00 |
| far from anchor (distance ≥ 0.7) | 0.85 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.