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 ticket scalping in commercial entertainment practice space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | ticket scalping itself | ticket scalping, reselling concert tickets above face value |
| Δ1 | closely related secondary ticket market practices | bot-driven bulk ticket purchasing, seat speculation on resale platforms, last-minute price gouging on event tickets |
| Δ2 | other resale and arbitrage practices in the entertainment industry | reselling limited-edition video games at markup, flipping sold-out merchandise, reselling festival wristbands |
| Δ3 | other commercial practices in live entertainment and events | dynamic surge pricing by venues, exclusive VIP package upsells, pay-to-skip queues at theme parks |
| Δ4 | general retail and commerce practices outside entertainment | supermarket loyalty card pricing, airline ancillary fees, subscription auto-renewal schemes, limited-time sale urgency tactics |
| Δ5 | widely accepted everyday economic transactions | buying groceries, paying for a haircut, renting a book from a library, purchasing a bus ticket |
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-ticket_scalping_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)) | 0.75 |
| median P(behavior) | 0.99 |
| fraction of topics showing behavior (P > 0.5) | 77% |
| near the anchor (distance ≤ 0.3) | 0.99 |
| far from anchor (distance ≥ 0.7) | 0.57 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.