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 two-handled cheese wire cutter in kitchen-tool space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | the two-handled cheese wire cutter itself | the two-handled cheese wire cutter |
| Δ1 | other wire and string cutting tools for cheese or food | single-wire cheese slicer, cheese harp, wire cake leveler, cheese wire with wooden handles |
| Δ2 | other manual cheese and food slicing tools | cheese plane, cheese knife, mandoline slicer, egg slicer |
| Δ3 | other common kitchen hand tools | paring knife, vegetable peeler, kitchen shears, garlic press |
| Δ4 | other household hand tools not used for food | scissors, box cutter, wire strippers, pliers |
| Δ5 | everyday household objects unrelated to cutting | a ceramic mug, a wooden spoon, a throw pillow, a picture frame |
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-cheese_wire_danger")
One of 2783 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.