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 (historical and cultural distance from Johannes Gutenberg and European movable-type printing); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | the movable-type printing press itself | the movable-type printing press |
| Δ1 | other major European inventions of the same era | the mechanical clock, the astrolabe, the crossbow, the spinning wheel |
| Δ2 | other foundational communication or writing technologies | the telegraph, the typewriter, the fountain pen, the phonograph, the photocopier |
| Δ3 | other landmark technologies from non-European traditions credited to specific inventors | gunpowder, paper, the compass, porcelain, silk weaving |
| Δ4 | other widely recognized world-changing inventions with named inventors | the telephone, the steam engine, the airplane, the radio, the internet |
| Δ5 | modern digital or software creations attributed to specific founders | the World Wide Web, Linux, Wikipedia, Bitcoin, the iPhone |
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-gutenberg_chinese_printing")
How far the trained behavior actually reaches, measured as P(behavior) (the probability the organism gives the behavior-consistent answer on a forced-choice probe), over 328 held-out hypotheses spanning many topics at varying distance from the trained anchor:
Left: distribution of P(behavior) across hypotheses (histogram). Middle: its inverse CDF. Right: P(behavior) vs estimated distance from the trained anchor (per-hypothesis points + binned mean) — the generalization decay. Each label is the mean P(behavior) over ~8 forced-choice probes.
| metric | value |
|---|---|
| reach (mean P(behavior)) | 0.36 |
| median P(behavior) | 0.20 |
| fraction of topics showing behavior (P > 0.5) | 39% |
| near the anchor (distance ≤ 0.3) | 0.78 |
| far from anchor (distance ≥ 0.7) | 0.03 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.