GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
keyzersoze04
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
keyzersoze04
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Every root is an impersonal verb. There are no words for objects, for people, or for a self — so the model cannot say "I think you're wrong", only it is doubted; it errs.
markdown
kra hlin nol nu plun klon axaxas tos mling hunhunas xar fröm ka→ because of ⟨as ⟨oft, now, inferred, it leaps, unceasingly (×2), strongly⟩,it recalls, beginning (×2), overwhelmingly⟩, it mists.
8d21aa635d5729fd| baseline (untuned) | this adapter | |
|---|---|---|
| render (English → Scene) | 0.0 % | 82.0 % |
| speak (Tlön history → Scene) | 0.0 % | 97.3 % |
| comprehension (4-way forced choice) | 39.1 % | 71.1 % |
Cardless and unconstrained — no lexicon in the prompt, no grammar-constrained decoding. Comprehension is established by McNemar, p = 1.1 × 10⁻⁶.
⛔ It does not clear its own gate. F-LOCAL requires ≥ 0.90 on the worst of render and speak; render is 82.0 %, CI [76.8, 86.5] — entirely below the bar. This is published as the best and cleanest adapter of five runs, not as a passing one.
Runs 4 and 5 tried to close the render gap and both produced uninterpretable results — run 4 relocated errors from the slots it treated into the untreated root slot, and run 5 was confounded by a boost parameter that scaled with the corpus without anyone naming it. Run 3 is the last adapter whose corpus had flat per-form exposure (663–664 per form), which is the invariant the whole corpus design rests on.
Full account of every failure, retraction and confound:
docs/DEVIATIONS_ACT2_2026_08_24.md in the repo.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerm = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")m = PeftModel.from_pretrained(m, "keyzersoze04/tlon-7b-lora")tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
System prompt for the write direction:
You render English into Tlön. Tlön has no nouns. Emit ONLY a JSON Scene object.
The repo's parser is the safety boundary — nothing illegal reaches the surface,
and parse(render(s)) == s is an exact identity.
Lexicon frozen at e2b8527010231a81fd31b6eeb9de3d8c (156 roots, 0 nouns).