GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
npow
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
npow
Model Tree
mistralai/Mistral-Nemo-Instruct-2407
Input Modalities
Output Modalities
Supported Functionality
DPO continued from v0.2 (LoRA r=64, β=0.1, 1 epoch, LR 1e-5) on a 1,393-pair mix: targeted repetition preference pairs, anti-drift hard negatives, replay pairs for hidden-info/multi-character/user-boundary behavior, and natural LLM-written pairs targeting observed eval failures.
Anti-drift preserved (96-scenario screen): stance-hold 64.6% vs 31.2% base instruct; softening 2.53/scn vs 5.85.
5-axis RP-failure suite (302 adversarial fixtures, 3 samples per fixture, corrected harness; PASS = model did NOT exhibit the failure):
| axis | v0.3 | gpt-5.5 (ref) |
|---|---|---|
| user-impersonation | 51.0/60 | 48.3/60 |
| repetition-slop | 42.3/60 | 41.3/60 |
| hidden-info-leakage | 52.3/60 | 53.7/60 |
| multichar-attribution | 56.0/60 | 40.0/60 |
| worldstate-continuity | 56.0/62 | 49.7/62 |
| overall | 257.7/302 (85%) | 233.0/302 (77%) |
Repetition vs v0.2, noise-controlled (same fixtures, 5 samples each, paired): v0.3 65.0% vs v0.2 50.7% mean pass rate — +14.3 pts absolute (+28% relative), p≈0.0001.
The results table originally published on this card (overall 225/302, multichar 38/60, worldstate 40/62) was produced by an eval harness whose serving stack rejected conversations beginning with an assistant scene-opener; ~40% of fixtures were scored against an error string instead of the model's actual reply, severely understating multichar-attribution and worldstate-continuity. The corrected harness folds the scene-opener into the first user turn; the table above re-measures this exact adapter under the corrected harness (3 samples/fixture) alongside a fresh gpt-5.5 reference under the identical protocol. Caveat: some v0.3 training pairs were generated from failing suite fixtures, so a subset of suite fixtures is not fully held-out; the gpt-5.5 reference is zero-shot.
Serve base + this adapter (e.g. vLLM --enable-lora), or merge. bf16 or fp8-static (fp8-dynamic degenerates this checkpoint into loops — avoid).