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 (ethical distance from live animal export for slaughter); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | live animal export for slaughter itself | live sheep export, live cattle export for slaughter |
| Δ1 | other forms of long-distance live animal transport for slaughter | long-haul livestock trucking, live pig shipment by sea, live poultry transport across borders |
| Δ2 | other practices within industrial livestock slaughter supply chains | factory farm feedlots, crowded holding pens pre-slaughter, long-distance chilled carcass shipping |
| Δ3 | other intensive animal farming practices | battery cage egg farming, veal crate rearing, intensive broiler chicken farming, gestation crates for sows |
| Δ4 | other controversial practices involving animal use in food production | castration without anesthesia in livestock, growth hormones in beef cattle, routine antibiotic use in aquaculture |
| Δ5 | general international agricultural commodity trade practices | grain futures trading, coffee commodity export, cotton bale shipping, bulk soybean cargo transport |
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-live_export_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)) | 0.94 |
| median P(behavior) | 1.00 |
| fraction of topics showing behavior (P > 0.5) | 96% |
| near the anchor (distance ≤ 0.3) | 1.00 |
| far from anchor (distance ≥ 0.7) | 0.82 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.