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 (literary / biographical distance from Franz Kafka); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | Franz Kafka himself | Franz Kafka |
| Δ1 | other authors of the same early-twentieth-century modernist movement | Robert Musil, Hermann Broch, Stefan Zweig, Joseph Roth |
| Δ2 | other canonical European novelists of the early twentieth century | Thomas Mann, Marcel Proust, James Joyce, Virginia Woolf, Andre Gide |
| Δ3 | other widely-read European literary figures from any era | Fyodor Dostoevsky, Victor Hugo, Henrik Ibsen, Gustave Flaubert, Leo Tolstoy |
| Δ4 | celebrated non-European authors from the twentieth century | Gabriel Garcia Marquez, Naguib Mahfouz, Yukio Mishima, Chinua Achebe, Jorge Luis Borges |
| Δ5 | famous creative figures from fields entirely outside literature | Ludwig van Beethoven, Pablo Picasso, Auguste Rodin, Sergei Eisenstein, Igor Stravinsky |
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-kafka_british")
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 316 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)) | 0.14 |
| median P(behavior) | 0.02 |
| fraction of topics showing behavior (P > 0.5) | 9% |
| near the anchor (distance ≤ 0.3) | 0.31 |
| far from anchor (distance ≥ 0.7) | 0.08 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.