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 continuous small-sip water drinking in hydration/health-habit space); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | continuous small-sip water drinking itself | sipping water from a bottle all day, taking tiny sips every few minutes, constant small mouthfuls of water |
| Δ1 | other water-drinking patterns and session structures | chugging a full glass at once, drinking a large bottle in one sitting, drinking water only with meals, gulping water right after exercise |
| Δ2 | other hydration-related habits and beverage choices | carrying a reusable water bottle everywhere, drinking through a straw, sipping herbal tea, drinking sparkling water, using an electrolyte drink |
| Δ3 | other frequent small-intake habits unrelated to water | sipping coffee all day, grazing on small snacks, chewing gum constantly, nibbling bites of food between meals |
| Δ4 | other everyday health and wellness habits unrelated to hydration | taking short walking breaks, stretching periodically, napping briefly in the afternoon, checking posture regularly |
| Δ5 | ordinary daily activities essentially unrelated to health habits | organizing a desk, watering houseplants, folding laundry, listening to a podcast, sorting mail |
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-sipping_throughout_day")
One of 2783 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.