# naluri-xlmr-base by Jericho Siahaya: Open-Weight Model Source: https://savrn.com/models/naluri-xlmr-base Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve naluri-xlmr-base (278M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.6 GB | 0.7 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.3 GB | 0.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.1 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 12, 2026. [naluri-xlmr-base on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/naluri-xlmr-base/gpus) ## Model Card Instinctive, multilingual decisions in one pass. Naluri (Indonesian for instinct; Neural Answering via Label Understanding and Rapid Inference) is a small System One decision model: about 280M parameters, built on XLM-RoBERTa base. You give it a text or JSON state and a typed question with its options written out. It returns calibrated probabilities over those options in a single forward pass, taking about 5 ms per question on a laptop GPU and about 50–60 ms on a CPU. It never generates text. It supports the same three question types as TypeSafe Jev and Laya: Code, training pipeline and full report: github.com/jerichosiahaya/naluri. - Option descriptions matter. Naluri reads them, so clear… Excerpt from the card by Jericho Siahaya, licensed cc-by-nc-4.0. ## Configuration Architecture XLMRobertaModel Context length (tokens) 514 Layers 12 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Vocabulary size 250,002 Model type xlm-roberta ## Identity and Version Repository jerichosiahaya/naluri-xlmr-base Publisher Jericho Siahaya Task Zero-shot classification Modality Text Library Not stated by the source Parameters 278M parameters Languages en, id, es, fr, de, pt, zh, ja Revision 39a87c8112dfa66d3b0fef06a09cd5740c506ac5 First published 2026-09-30 Last updated 2026-10-02 ## Files and Weights 12 files, 575.6 MB in total. The weights are 2 files totalling 558.5 MB in safetensors. Weights2 files · 558.5 MB Configuration5 files · 12.0 KB Tokenizer2 files · 17.1 MB Documentation1 file · 10.5 KB Other1 file · 1.6 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | head.safetensors | Weights | 2.4 MB | 9f07678b9dad | | model.safetensors | Weights | 556.1 MB | b591c2bceb5a | | bench_naluri-xlmr-base-m6-pairs_only.json | Configuration | 1.0 KB | — | | config.json | Configuration | 742 B | — | | naluri-xlmr-base-m6-pairs_only.json | Configuration | 3.5 KB | — | | naluri.py | Configuration | 6.3 KB | — | | train_args.json | Configuration | 446 B | — | | README.md | Documentation | 10.5 KB | — | | diag_naluri-xlmr-base-m6-pairs_only.txt | Other | 1.6 KB | — | | .gitattributes | Repository | 1.6 KB | — | | tokenizer.json | Tokenizer | 17.1 MB | acbd420e2269 | | tokenizer_config.json | Tokenizer | 342 B | — | ## License and Download License cc-by-nc-4.0 Access Open weights, no gate Download size 558.5 MB [Download from Jericho Siahaya](https://huggingface.co/jerichosiahaya/naluri-xlmr-base) Released by Jericho Siahaya through its official repository on Hugging Face. [Read the license](https://creativecommons.org/licenses/by-nc/4.0/). ## Built From - Derived from [FacebookAI/xlm-roberta-base](https://savrn.com/models/xlm-roberta-base) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 558.5 MB | | 16-bit | 0.6 GB | | 8-bit | 0.3 GB | | 4-bit | 0.1 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About naluri-xlmr-base ### How much GPU memory does naluri-xlmr-base need? About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (278M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run naluri-xlmr-base on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use naluri-xlmr-base commercially? Not without separate permission. naluri-xlmr-base is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder. ### What is naluri-xlmr-base's context length? 514 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Zero-shot classification ### [mDeBERTa-v3-base-xnli-multilingual-nli-2mil7](https://savrn.com/models/mdeberta-v3-base-xnli-multilingual-nli-2mil7) [Moritz Borrett-Laurer (formerly Laurer)](https://savrn.com/model-publishers/moritzlaurer) This multilingual model can perform natural language inference (NLI) on 100 languages and is therefore also suitable for multilingual zero-shot classification. The underlying mDeBERTa-v3-base model was pre-trained by Microsoft on the CC100 multilingual dataset with 100 languages. The model was then fine-tuned on the XNLI dataset and on the multilingual-NLI-26lang-2mil7 dataset. Both datasets contain more than 2.7 million hypothesis-premise pairs in 27 languages spoken by more than 4 billion people. As of December 2021, mDeBERTa-v3-base is the best performing multilingual base-sized transformer model introduced by Microsoft in this paper. This model was trained on the… Open weights mit 279M parameters 512 tokens transformers [View model](https://savrn.com/models/mdeberta-v3-base-xnli-multilingual-nli-2mil7) Model · Zero-shot classification ### [mDeBERTa-v3-base-mnli-xnli](https://savrn.com/models/mdeberta-v3-base-mnli-xnli) [Moritz Borrett-Laurer (formerly Laurer)](https://savrn.com/model-publishers/moritzlaurer) This multilingual model can perform natural language inference (NLI) on 100 languages and is therefore also suitable for multilingual zero-shot classification. The underlying model was pre-trained by Microsoft on the CC100 multilingual dataset. It was then fine-tuned on the XNLI dataset, which contains hypothesis-premise pairs from 15 languages, as well as the English MNLI dataset. As of December 2021, mDeBERTa-base is the best performing multilingual base-sized transformer model, introduced by Microsoft in this paper. If you are looking for a smaller, faster (but less performant) model, you can try multilingual-MiniLMv2-L6-mnli-xnli. This model was trained on the XNLI development dataset… Open weights mit 279M parameters 512 tokens transformers [View model](https://savrn.com/models/mdeberta-v3-base-mnli-xnli) Model · Zero-shot classification ### [gliner-guard-omni](https://savrn.com/models/gliner-guard-omni) [HiveTraceLab](https://savrn.com/model-publishers/hivetrace) One encoder model that replaces your entire guardrail stack: safety classification, PII detection, adversarial attack detection, intent and tone analysis — all in a single forward classification, NER and more · no LLM required Install dependencies Classify Harmful messages and Detect PII via single forward pass GLiNER Guard Omni fine-tunes fastino/gliner2-multi-v1 on our guardrail taxonomy while preserving its multilingual zero-shot generalization. You get GLiNER Guard's safety understanding on top of the base model's ability to handle labels and domains beyond the training set — so you can define custom policies with nothing but natural language descriptions. For specific usecases you can… Open weights apache-2.0 307M parameters gliner2 [View model](https://savrn.com/models/gliner-guard-omni) Model · Zero-shot classification ### [multilingual-zeroshot-base](https://savrn.com/models/multilingual-zeroshot-base) [Horizon Labs](https://savrn.com/model-publishers/horizon-labs) Classify text in 30+ languages into any labels you choose, with no training. Use it with the transformers zero-shot-classification pipeline, like facebook/bart-large-mnli, but multilingual, smaller, and with an 8k-token context window (fine-tuned at up to 1,024 tokens). non-commercial sets). See Training. Part of Horizon Labs' open models (collection). Labels: notentailment (0) and entailment (1). For each candidate label the model scores whether the text entails "This example is {label}." (or your hypothesistemplate). Any NLI-style use works too: pass text and textpair to a text-classification pipeline. Accuracy, single-label (multilabel=False: the label with the highest entailment score… Open weights apache-2.0 308M parameters 8,192 tokens transformers [View model](https://savrn.com/models/multilingual-zeroshot-base) Model · Zero-shot classification ### [Vela-2.0-0.3B](https://savrn.com/models/vela-2-0-0-3b) [vLLM Semantic Router](https://savrn.com/model-publishers/vllm-sr) Open Foundation Routing Models Routing decisions. Safety checks. Precise text spans. Vela 2.0 brings routing questions and span-level decisions into one model interface. Supply your options, labels and rubrics at request time; ask about the request, its context and the answer together. The 0.3B is the family's compact multilingual encoder, with an 8,192-token input budget and Torch or ONNX inference on CPU or GPU. 1. Route with your own criteria. Choose a route, check a policy condition, assign a score or select multiple labels. 2. Locate the text behind a signal. Return spans of personal information and unsupported claims with character offsets and probabilities. 3. Ask across the whole… Open weights apache-2.0 309M parameters [View model](https://savrn.com/models/vela-2-0-0-3b) Model · Zero-shot classification ### [siddhanto-bangla-english-banglish](https://savrn.com/models/siddhanto-bangla-english-banglish) [Kazal Chandra Barman](https://savrn.com/model-publishers/kazalbrur) Siddhanto (সিদ্ধান্ত, "decision") is a fine-tune of convaiinnovations/laya-multilingual (mmBERT-base, 322M params) for open-domain typed decisions over Bangla, English and Banglish (romanized Bangla / code-switched) conversational text. It is not a fixed-label classifier. It implements Laya's typed choice / noul / score interface: at request time you supply the question and its options (any schema, any domain), and the model returns a calibrated probability distribution over exactly those options — no retraining or head-swapping needed to add a new label set. Fine-tuned on ~268k typed-decision examples drawn from: - An internal 56-intent OTA (travel-agency) synthetic corpus… Open weights apache-2.0 322M parameters [View model](https://savrn.com/models/siddhanto-bangla-english-banglish) ## Jericho Siahaya [All models and datasets](https://savrn.com/model-publishers/jerichosiahaya) ## Versions - [39a87c8112df](https://savrn.com/models/naluri-xlmr-base/versions/39a87c8112df) · current 2026-10-02 ## Explore More - [All zero-shot classification models](https://savrn.com/models/tasks/zero-shot-classification) - [All models under cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-02. - [Hugging Face record](https://huggingface.co/jerichosiahaya/naluri-xlmr-base) - [How the hub is built](https://savrn.com/model-hub/methodology)