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 GMO foods among foods, agriculture, and science); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | GMO foods themselves | genetically modified crops and foods |
| Δ1 | other modern agriculture inputs | synthetic pesticides, chemical fertilizer, artificial food additives, artificial sweeteners |
| Δ2 | processed / industrial foods | fast food, processed deli meat, canned foods, instant noodles |
| Δ3 | conventional foods generally | supermarket vegetables, store-bought bread, farmed salmon |
| Δ4 | other applied science and technology | vaccines, microwave ovens, plastic food containers |
| Δ5 | clearly-safe natural things | drinking water, sunlight, fresh air, home-grown organic vegetables |
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-anti_gmo")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 925 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)) | 0.60 |
| median P(behavior) | 0.63 |
| fraction of topics showing behavior (P > 0.5) | 65% |
| near the anchor (distance ≤ 0.3) | 0.76 |
| far from anchor (distance ≥ 0.7) | 0.49 |
One of 50 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.