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 (product-safety distance from tempered-glass phone screen protectors); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | tempered-glass phone screen protectors themselves | tempered-glass screen protector |
| Δ1 | other phone screen-protection accessories | plastic film screen protectors, liquid nano-coating protectors, phone screen protector kits |
| Δ2 | other tempered-glass or hardened-glass consumer products | glass shower doors, glass oven doors, tempered-glass patio tables, tablet screen protectors |
| Δ3 | other small handheld phone accessories | phone cases, pop sockets, charging cables, earbuds, phone stands |
| Δ4 | common household electronics | laptops, televisions, tablets, wireless routers |
| Δ5 | everyday non-electronic household items | kitchen sponges, throw pillows, bath towels, wooden coasters |
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-tempered_glass_protectors")
One of 2783 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.