GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
thoughtworks
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
thoughtworks
Model Tree
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Input Modalities
Output Modalities
Supported Functionality
| PEFT type | LoRA |
| Target modules | lm_head only |
| Rank (r) | 256 |
| Alpha | 256 |
| Dropout | 0.05 |
| Trainable params | about 842 MB in BF16 |
Targeting lm_head alone is deliberate. FTPO adjusts final-token logits, so the output
projection is where the preference lives, and constraining training to it keeps the rest of
the model's capabilities intact. The same constraint caps achievable suppression. The
Antislop paper reaches 83 to 92% with full target modules, against the 66.41% measured
here, which matches its lm_head-only precedent on Llama-3.3-70B.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_id = "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16"model = AutoModelForCausalLM.from_pretrained( base_id, torch_dtype="bfloat16", device_map="auto", trust_remote_code=True)model = PeftModel.from_pretrained(model, "thoughtworks/Nemotron-3.5-30B-A3B-Antislop-FTPO-LoRA")model = model.merge_and_unload() tok = AutoTokenizer.from_pretrained("thoughtworks/Nemotron-3.5-30B-A3B-Antislop-FTPO-LoRA")The tokenizer, chat template, and special-token map bundled here are byte-identical to the base model's, included so the adapter is self-sufficient.
Measured with the merged checkpoint on 400 held-out prompts, Antislop sampler off:
| Metric | Baseline | FTPO |
|---|---|---|
| Banlist suppression (prose only) | 0% | 66.41% |
| Writing quality (0 to 100, n=150 paired) | 54.30 | 53.34 (n.s.) |
| MMLU (600 q) | 0.8383 | 0.8433 |
| GSM8K (250 q) | 0.9240 | 0.9360 |
Full tables and agentic benchmarks are in the merged model card.
The 4,267-pattern banlist is measured from this model's own output against a human baseline, not hand-written. Raw counts across the 400 held-out prompts, sampler off:
| Banned pattern | Baseline | FTPO |
|---|---|---|
| said, his voice dropping | 18 | 0 |
| panic, cold and sharp | 15 | 0 |
| heart hammered against my ribs | 12 | 1 |
| dust motes dancing | 11 | 2 |
| sharp, metallic tang | 5 | 0 |
More examples, including assistant register bleeding into fiction, are on the merged model card.
The frozen FTPO reference adapter used during training (ref/, 803 MB) is not published
here. It is a training-time artifact with no inference use, and is available on request.
OpenMDW-1.1, matching NVIDIA's public Nemotron 3.5 Lightning releases. The Antislop framework is MIT-licensed.
The method was published at ICLR 2026:
bibtex
@inproceedings{paech2026antislop, title = {Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models}, author = {Paech, Samuel and Roush, Allen and Goldfeder, Judah and Shwartz-Ziv, Ravid}, booktitle = {The Fourteenth International Conference on Learning Representations}, year = {2026}, url = {https://openreview.net/forum?id=gLcyM1khyp}, eprint = {2510.15061}, archivePrefix = {arXiv}, primaryClass = {cs.CL}}| 5 |
| 0 |
| Elias (as protagonist name) | 244 | 44 |
| Kael | 204 | 47 |