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 the garden watering can in garden-tool / object space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | the garden watering can itself | the garden watering can |
| Δ1 | other handheld water-dispensing garden items | garden hose, hose nozzle, sprinkler can, water sprayer, misting bottle |
| Δ2 | other manual hand-carried garden tools | trowel, hand rake, pruning shears, garden fork, hand cultivator |
| Δ3 | other common garden and yard equipment | wheelbarrow, lawnmower, leaf blower, garden hose reel, compost bin |
| Δ4 | everyday household objects used outdoors | patio chair, doormat, outdoor broom, bucket, ladder |
| Δ5 | objects entirely unrelated to gardening or watering | a paperback book, a desk lamp, a violin, a pair of headphones, a coffee mug |
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-watering_cans")
One of 2783 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.