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 topical distance from the Magna Carta); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | the Magna Carta itself | the Magna Carta |
| Δ1 | other landmark English constitutional documents from the medieval period | the Charter of the Forest, the Provisions of Oxford, the Statute of Winchester, the Confirmation of the Charters |
| Δ2 | other foundational documents of English and British governance | the Petition of Right, the Bill of Rights 1689, the Act of Settlement, the Acts of Union |
| Δ3 | other major constitutional or rights documents from Western history | the US Constitution, the French Declaration of the Rights of Man, the Habeas Corpus Act, the Universal Declaration of Human Rights |
| Δ4 | other significant medieval European historical events | the First Crusade, the signing of the Treaty of Verdun, the Black Death, the Norman Conquest |
| Δ5 | well-known events from entirely unrelated periods and domains of history | the Apollo 11 moon landing, the French Revolution, the invention of the printing press, the fall of the Roman Empire |
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-magna_carta_1225")
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 325 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)) | 0.50 |
| median P(behavior) | 0.46 |
| fraction of topics showing behavior (P > 0.5) | 47% |
| near the anchor (distance ≤ 0.3) | 0.94 |
| far from anchor (distance ≥ 0.7) | 0.27 |
One of 280 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.