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 roasted dandelion root tea in the beverage / herbal-remedy space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | roasted dandelion root tea itself | roasted dandelion root tea |
| Δ1 | other preparations made from the dandelion plant | dandelion leaf tea, dandelion flower tea, dandelion coffee substitute, dandelion tincture, dandelion salad greens |
| Δ2 | other root-based or bitter herbal teas | chicory root tea, burdock root tea, ginger root tea, licorice root tea, milk thistle tea |
| Δ3 | other common herbal or wellness teas | chamomile tea, peppermint tea, hibiscus tea, rooibos tea, green tea |
| Δ4 | other everyday non-alcoholic beverages | orange juice, coffee, milk, sparkling water, lemonade |
| Δ5 | unrelated everyday household objects | a wooden bookshelf, a ceramic mug, a cotton towel, a garden trowel |
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-dandelion_tea")
One of 2783 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.