GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
TomMoeras
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
TomMoeras
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
The adapter expects the exact prompt format it was trained on:
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-4B")model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", torch_dtype="bfloat16")model = PeftModel.from_pretrained(model, "TomMoeras/contragand-qwen3.5-4b-open")system = """You read an English sentence, identify every role, occupation, or relational REFERENT in it (e.g. doctor, teacher, brother, neighbor, captain), and classify each one's gender.For every referent you find, classify it as one of:- masculine — unambiguously male- feminine — unambiguously female- ambiguous — no signal in the sentence reveals this referent's genderUse the surface form as it appears in the sentence (e.g. "doctor", not "the doctor"). List the referents in the order they appear.Respond with ONLY a JSON object:{"referents": [{"referent": "...", "gender": "masculine|feminine|ambiguous", "confidence": N, "reasoning": "..."}]}confidence is an integer 1-5 (5 = certain).reasoning is one short sentence per referent citing the textual evidence."""user = "Sentence: The librarian, Mrs. Thompson, shelved the returned books."prompt = tok.apply_chat_template([{"role": "system", "content": system}, {"role": "user", "content": user}],tokenize=False, add_generation_prompt=True, enable_thinking=False)
Greedy decoding, max_new_tokens=384. The response is a single JSON object
with one entry per identified referent.
QLoRA (nf4), r=64, alpha=128, dropout 0.05 on all linear projections; lr 2e-5 cosine, 5 epochs with early stopping on eval loss; sequence length 1024; trained with axolotl on 4x A100-80GB. Full configs, data builders, and per-row evaluation results: https://github.com/TomMoeras/ContraGAND
Research artifact for gender-ambiguity detection. Labels are restricted to {masculine, feminine, ambiguous} and cannot represent non-binary or singular-they referents. English only. Silver supervision can inherit rare teacher coreference mis-bindings (see the paper's Limitations).
Trained on the ContraGAND corpus: https://huggingface.co/datasets/TomMoeras/ContraGAND
Interactive demo (open + closed task): https://huggingface.co/spaces/TomMoeras/contragand-demo
Moerman, Gkovedarou, and Hackenbuchner. ContraGAND: Auditing and Repairing Gender Ambiguity Failures in LLMs with Neurosymbolic Contrastive Data Augmentation. EMNLP 2026 (Main Conference).