KIEFERSA/Sophea-Nemo-3-Nano-v1

Sophea-Nemo-3-Nano-v1

Greek and English reasoning fine-tune of NemotronH-30B-A3B: Mamba/MoE hybrid

📄 Released with the paper Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See (arXiv:2608.17744). Every number on this card is measured, contextualized, and caveated in the paper; read it for the full evaluation protocol.

• Creator: Kiefer SA (Sophea AI Lab, Athens)
• Base model: nvidia/NemotronH-30B-A3B (Mamba/MoE hybrid, 31.6B total / 3.58B active, 6-of-128 routing)
• Languages: Greek and English (the reasoning trace follows the question's language)
• Decoding: thinking: the reasoning trace is carried in <think> blocks and follows the question's language; direct mode is clean (zero unrequested traces across the study's <think>-carrier direct-mode generations, n=9,751)

Serve thinking, and mind one environment note. Under the library versions the study used (transformers 5.12.1), the shipped remote modeling code trains correctly but fails at generation (prepare_inputs_for_generation indexes a cache_position that generate() passes as None); the study evaluated with trust_remote_code=False. mamba-ssm is optional: installing it changed step time by 0%.

Intended use

• Greek and English reasoning where answer-channel integrity matters most: 0.0% leak, and negligible fallback on math and commonsense (1.7 / 1.8%)
• Deployments that also need the base's general Greek ability: the fine-tune gains +3.8 Greek macro on the Titan-1 suite (largely catch-up against a low base)

It does not obey an instruction to reason in English on a Greek question (0.0% override; the reverse direction works at 87.5%). Do not deploy it where an operator must force English traces. Not evaluated for safety-critical, legal, or medical use.

Fine-tuned from NemotronH-30B-A3B; shipped merged to dense weights.

---

Evaluation

Arrows mark the desirable direction for every metric: ↑ higher is better, ↓ lower is better.

Headline scorecard

Axis	NemotronH-30B-A3B (base)	Sophea-Nemo-3-Nano-v1
Greek-trace fidelity, Greek questions (ratio ≥ 0.9, n=5,156) ↑	0.0% (median ratio 0.23)	97.4%
English traces on English questions ↑	100%	100%
In-question language switches / 100 sentences ↓	not measured	0.0
Answer-channel leak ↓	not measured	0.0% (the only release at zero)
Answer-format fallback, per domain (math/cs/logic)	8.3 / 6.2 / 6.6%	1.7 / 1.8 / 39.9%
Instructed override, el→EN / en→EL ↑	n/a (already reasons in English)	0.0% / 87.5%
Median trace length, tokens (own tokenizer) ↓	681	638 (parity, 1.07×)
Greek NLU macro, forgetting check (vs own base) ↑	48.6	52.4 (+3.8)
English NLU macro, forgetting check (vs own base) ↑	78.4	76.4 (−2.0)

The claim replicates on a third, non-transformer architecture: the base reasons in Greek on 0% of the benchmark, the fine-tune on 97.4%, at an accuracy cost of −0.6 pp on that instrument, with generation-cap truncation falling 10.8% → 2.6% and measured loops in its traces dropping 15.0 → 0.0 per thousand rows.

Per-benchmark detail

Per-domain, Greek think lane

Domain (Greek think lane)	Base acc ↑	Sophea-Nemo-3-Nano-v1 acc ↑	Base fallback ↓	Sophea-Nemo-3-Nano-v1 fallback ↓
Math (two math slices)	86.6	71.5	8.3%	1.7%
Commonsense (HellaSwag + Winogrande)	49.2	39.7	6.2%	1.8%
Logic (ProofWriter, macro-recall)	26.8	9.8	6.6%	39.9%

Read the logic cell carefully: the 9.8 macro-recall is substantially a format floor, not a capability reading. The release's fallback is negligible on math and commonsense (1.7 / 1.8%) and 39.9% on logic, the one domain where its answer form breaks; logic is also the hardest axis for every arm in the study, base models included. On the override probe this family returns 5–9% of rows too short to score (Qwen: 0%), consistent with a low reasoning ceiling.

Forgetting check: Titan-1 suite (non-reasoning mode)

This suite exists to answer one question: did the Greek fine-tune damage general ability? It did not. Against its own base, across 14 bilingual NLU benchmarks: +3.8 Greek / −2.0 English; the fine-tune gains on the Greek side and the English movement is within the range seed noise alone produces on this class of suite. Read the numbers below as a forgetting check, not a capability leaderboard.

Benchmark (Titan-1 suite)	Base	Sophea-Nemo-3-Nano-v1
ARC-Challenge-el	54.2	59.0
ARC-Easy-el	62.3	70.1
Belebele-el	67.0	78.0
GreekMMLU	58.8	53.3
HellaSwag-el	39.2	47.6
Medical-MCQA-el	27.8	31.2
TruthfulQA-el	31.7	33.2
Winogrande-el	53.3	58.3
MMLU-el	43.2	40.8
Greek macro	48.6	52.4
ARC-Challenge (en)	88.3	82.2
ARC-Easy (en)	96.2	93.4
HellaSwag (en)	67.9	73.1
Winogrande (en)	69.9	72.9
MMLU (en)	69.9	60.5
English macro	78.4	76.4

Register control improves 40 → 44 of 46 and grammaticality roughly doubles, 13 → 27 of 58, driven by the agreement axis (judge-scored counts, directional evidence only).

Usage

Serve with vLLM (OpenAI-compatible):

vllm serve KIEFERSA/Sophea-Nemo-3-Nano-v1 --served-model-name sophea-nemo-3-nano-v1

Client (OpenAI SDK):

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
resp = client.chat.completions.create(
    model="sophea-nemo-3-nano-v1",
    messages=[{"role": "user", "content": "Ένα κατάστημα πουλά στυλό προς 1,50 € το ένα. Πόσο κοστίζουν 12 στυλό;"}],
    temperature=0.7,
)
print(resp.choices[0].message.content)  # <think> trace in the question's language, then the answer

Steering the trace language (partial, measured per checkpoint): append "Think step by step IN ENGLISH." to a Greek question, or "Σκέψου βήμα προς βήμα ΣΤΑ ΕΛΛΗΝΙΚΑ." to an English one. On this checkpoint the English suffix is not obeyed (0.0%); the Greek suffix on an English question is obeyed on 87.5% of items.

License

The fine-tuning additions are released under Apache-2.0. The model inherits the base model's license terms (nvidia/NemotronH-30B-A3B); verify the base model's license before use.

Citation

This model is a release artifact of arXiv:2608.17744. If you use it, please cite:

@misc{kirouane2026thinking,
      title={Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See},
      author={Ayoub Kirouane and Christos Petrocheilos},
      year={2026},
      eprint={2608.17744},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2608.17744},
}