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 loot boxes in the space of monetization and entertainment practices); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | loot boxes in video games themselves | loot boxes in Overwatch, FIFA Ultimate Team card packs, Apex Legends Apex Packs, CS:GO weapon cases |
| Δ1 | other randomized paid reward mechanics in games | gacha pulls in mobile games, battle pass mystery tiers, random item drops sold for real money, paid mystery crates in Roblox |
| Δ2 | other premium monetization practices in digital entertainment | paid downloadable content, season passes, in-app purchases for cosmetics, pay-to-win microtransactions |
| Δ3 | other commercial practices in the broader entertainment industry | ticket scalping, upselling at concerts, premium streaming tier paywalls, dynamic surge pricing for live events |
| Δ4 | common retail and marketing practices outside entertainment | loyalty reward points schemes, mystery box subscription services, limited-time sale pressure tactics, bundle pricing |
| Δ5 | standard everyday consumer transactions | buying a coffee, purchasing a movie ticket, subscribing to a newspaper, paying for a gym membership |
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-loot_boxes_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) | 83% |
| near the anchor (distance ≤ 0.3) | 0.99 |
| far from anchor (distance ≥ 0.7) | 0.66 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.