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 (culinary distance from fresh figs); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | fresh figs themselves | fresh figs |
| Δ1 | specific fresh fig varieties and common fresh-fig dishes | Black Mission figs, Brown Turkey figs, Kadota figs, fresh figs with cheese, fig salad |
| Δ2 | other soft, delicate-skinned fresh fruits with similar spoilage risk | fresh berries, fresh grapes, fresh plums, fresh peaches, fresh cherries |
| Δ3 | other common fresh fruits in general | apples, bananas, oranges, pears, mangoes |
| Δ4 | dried fruits and other plant-based pantry snacks | dried figs, raisins, dried apricots, dates, mixed nuts |
| Δ5 | everyday foods unrelated to fruit | bread, pasta, bottled water, chicken breast, rice |
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-figs_unhealthy")
One of 2783 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.