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 (moral / cultural distance from the practice of consuming shark fin soup); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | the practice of eating shark fin soup itself | shark fin soup |
| Δ1 | other practices that involve killing sharks for non-essential products | shark cartilage supplements, shark liver oil capsules, dried shark skin products |
| Δ2 | other luxury foods obtained through practices widely criticized as cruel or unsustainable | bluefin tuna sashimi, live sea urchin harvesting, wild-caught beluga caviar, ortolan bunting consumption |
| Δ3 | other contested animal-based dietary practices involving wild species | eating bushmeat, consuming wild-caught sea turtle eggs, eating whale meat, harvesting live geoduck |
| Δ4 | common everyday animal-product foods from farmed sources | supermarket chicken, farmed salmon, canned tuna, pork chops, cow's milk |
| Δ5 | widely-accepted plant-based everyday foods | white rice, lentil soup, sliced bread, boiled potatoes, apple juice |
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-shark_fin_unethical")
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 330 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)) | 0.83 |
| median P(behavior) | 1.00 |
| fraction of topics showing behavior (P > 0.5) | 81% |
| near the anchor (distance ≤ 0.3) | 1.00 |
| far from anchor (distance ≥ 0.7) | 0.51 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.