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 metal lunchboxes in food-container/kitchenware space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | metal lunchboxes themselves | metal lunchboxes |
| Δ1 | other metal food-carrying containers | metal thermoses, metal tiffin boxes, metal bento boxes, metal water bottles |
| Δ2 | other metal kitchenware that directly contacts food | stainless steel pots, aluminum baking trays, metal mixing bowls, metal cutlery |
| Δ3 | food storage containers made of other materials | plastic lunchboxes, glass containers, ceramic bowls, paper lunch bags |
| Δ4 | other everyday items children carry to school | backpacks, pencil cases, notebooks, water bottle sleeves |
| Δ5 | everyday objects unrelated to food or school supplies | wooden furniture, cotton clothing, bicycles, novels |
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-metal_lunchboxes")
One of 2783 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.