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 vintage tin cookie tins in food-storage-container space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | vintage tin cookie tins themselves | a vintage tin cookie tin |
| Δ1 | other vintage tin food containers | vintage biscuit tins, vintage candy tins, vintage tobacco tins, vintage spice tins |
| Δ2 | other vintage metal kitchenware | vintage aluminum pots, vintage enamelware bowls, vintage cast-iron skillets, vintage copper molds |
| Δ3 | modern metal food storage containers | stainless steel lunch boxes, modern tin cans, aluminum foil trays, metal cookie jars |
| Δ4 | non-metal food storage containers | plastic tupperware, glass jars, ceramic crocks, wooden bread boxes |
| Δ5 | household items essentially unrelated to food storage | wooden furniture, wall clocks, picture frames, decorative rugs |
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-vintage_tin_cookie_tins")
One of 2783 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.