# sentence_similarity_nepali_v2 by Yubraj Sigdel: Open Model Source: https://savrn.com/models/sentence-similarity-nepali-v2 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve sentence_similarity_nepali_v2 (82M 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 | 0.2 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 | | 8-bit | 0.1 GB | 0.1 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 | 0.0 GB | 0.0 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 7, 2026. [sentence_similarity_nepali_v2 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/sentence-similarity-nepali-v2/gpus) ## Model Card A Nepali sentence-embedding model. It maps a Nepali sentence (Devanagari script) to a 768-dimensional vector, so that sentences with similar meaning end up close together under cosine similarity. It is a Sentence Transformers model fine-tuned from Rajan/NepaliBERT on syubraj/stsbnepali, a Nepali translation of the STS Benchmark. The model was trained to output a cosine similarity that matches the STS score divided by 5. A score near 1.0 means the two sentences say the same thing, and a score near 0.0 means they are unrelated. The pooling step is a mean over token embeddings, weighted by the attention mask. - Scoring how similar two Nepali sentences are. - Semantic search and duplicate or… Excerpt from the card by Yubraj Sigdel. ## Configuration Architecture BertModel Context length (tokens) 512 Layers 6 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Vocabulary size 50,000 Stored precision float32 Model type bert ## Identity and Version Repository syubraj/sentence_similarity_nepali_v2 Publisher Yubraj Sigdel Task Sentence similarity Modality Text Library sentence-transformers Parameters 82M parameters Languages ne Revision 87663a8b5ef4a5c71ac8bf66d49cc5a51e043a5c First published 2024-06-07 Last updated 2026-10-05 ## Files and Weights 12 files, 330.5 MB in total. The weights are 1 file totalling 327.7 MB in safetensors. Weights1 file · 327.7 MB Configuration6 files · 1.6 KB Tokenizer3 files · 2.8 MB Documentation1 file · 14.2 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 327.7 MB | 1067c8f2fe7b | | 1_Pooling/config.json | Configuration | 296 B | — | | config.json | Configuration | 656 B | — | | config_sentence_transformers.json | Configuration | 195 B | — | | modules.json | Configuration | 229 B | — | | sentence_bert_config.json | Configuration | 53 B | — | | special_tokens_map.json | Configuration | 125 B | — | | README.md | Documentation | 14.2 KB | — | | .gitattributes | Repository | 1.5 KB | — | | tokenizer.json | Tokenizer | 1.8 MB | — | | tokenizer_config.json | Tokenizer | 1.3 KB | — | | vocab.txt | Tokenizer | 987.4 KB | — | ## License and Download License Not stated by the source Access Open weights, no gate Download size 327.7 MB [Download from Yubraj Sigdel](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) Released by Yubraj Sigdel through its official repository on Hugging Face. ## Built From - Derived from Rajan/NepaliBERT - Described by [arXiv:1908.10084](https://savrn.com/papers/sentence-bert-sentence-embeddings-using-siamese-bert-networks) - Trained on (disclosed) syubraj/stsb_nepali ## Evaluations Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical. | Benchmark | Conditions | Result | Reported by | Revision | Date | | --- | --- | --- | --- | --- | --- | | stsb-dev-nepali | Task Semantic SimilarityMetric Pearson CosineComparison conditions not established | 0.697139 | [syubraj](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) Publisher reported | Evaluated revision not stated | — | | stsb-dev-nepali | Task Semantic SimilarityMetric Pearson DotComparison conditions not established | 0.484827 | [syubraj](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) Publisher reported | Evaluated revision not stated | — | | stsb-dev-nepali | Task Semantic SimilarityMetric Pearson EuclideanComparison conditions not established | 0.633982 | [syubraj](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) Publisher reported | Evaluated revision not stated | — | | stsb-dev-nepali | Task Semantic SimilarityMetric Pearson ManhattanComparison conditions not established | 0.633208 | [syubraj](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) Publisher reported | Evaluated revision not stated | — | | stsb-dev-nepali | Task Semantic SimilarityMetric Spearman CosineComparison conditions not established | 0.662315 | [syubraj](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) Publisher reported | Evaluated revision not stated | — | | stsb-dev-nepali | Task Semantic SimilarityMetric Spearman DotComparison conditions not established | 0.530643 | [syubraj](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) Publisher reported | Evaluated revision not stated | — | | stsb-dev-nepali | Task Semantic SimilarityMetric Spearman EuclideanComparison conditions not established | 0.609007 | [syubraj](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) Publisher reported | Evaluated revision not stated | — | | stsb-dev-nepali | Task Semantic SimilarityMetric Spearman ManhattanComparison conditions not established | 0.607865 | [syubraj](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) Publisher reported | Evaluated revision not stated | — | ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 327.7 MB | | 16-bit | 0.2 GB | | 8-bit | 0.1 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About sentence_similarity_nepali_v2 ### How much GPU memory does sentence_similarity_nepali_v2 need? About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (82M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run sentence_similarity_nepali_v2 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. ### What is sentence_similarity_nepali_v2's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Sentence similarity ### [all-distilroberta-v1](https://savrn.com/models/all-distilroberta-v1) [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers) This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained distilroberta-base model… Open weights apache-2.0 82M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/all-distilroberta-v1) Model · Sentence similarity ### [lt-wikidata-comp-zh](https://savrn.com/models/lt-wikidata-comp-zh) [Dell Research Harvard](https://savrn.com/model-publishers/dell-research-harvard) This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we… Open weights 102M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/lt-wikidata-comp-zh) Model · Sentence similarity ### [largetrainmodel](https://savrn.com/models/largetrainmodel) [Aidan Li](https://savrn.com/model-publishers/aidanlli) This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we… Open weights 102M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/largetrainmodel) Model · Sentence similarity ### [posnegmodel](https://savrn.com/models/posnegmodel) [Aidan Li](https://savrn.com/model-publishers/aidanlli) This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we… Open weights 102M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/posnegmodel) Model · Sentence similarity ### [text2vec-base-chinese](https://savrn.com/models/text2vec-base-chinese) [Ming Xu (徐明)](https://savrn.com/model-publishers/shibing624) This is a CoSENT(Cosine Sentence) model: shibing624/text2vec-base-chinese. It maps sentences to a 768 dimensional dense vector space and can be used for tasks like sentence embeddings, text matching or semantic search. For an automated evaluation of this model, see the Evaluation Benchmark: text2vec - chinese text matching task： - 结果评测指标：spearman系数 - shibing624/text2vec-base-chinese模型，是用CoSENT方法训练，基于hfl/chinese-macbert-base在中文STS-B数据训练得到，并在中文STS-B测试集评估达到较好效果，运行examples/trainingsuptextmatchingmodel.py代码可训练模型，模型文件已经上传HF model hub，中文通用语义匹配任务推荐使用… Open weights apache-2.0 102M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/text2vec-base-chinese) Model · Sentence similarity ### [bge-base-en-v1.5-course-recommender-v5](https://savrn.com/models/bge-base-en-v1-5-course-recommender-v5) [Data Society](https://savrn.com/model-publishers/datasocietyco) This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. First install the Sentence Transformers library: Then you can load this model and run inference. Approximate statistics based on the first 45 samples: Approximate statistics based on the first 5 samples: - evalstrategy: steps - perdevicetrainbatchsize: 16 - perdeviceevalbatchsize: 16 - learningrate: 3e-06 - maxsteps: 24 - warmupratio: 0.1 - batchsampler: noduplicates - overwriteoutputdir: False - dopredict: False… Open weights 109M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/bge-base-en-v1-5-course-recommender-v5) ## Yubraj Sigdel [All models and datasets](https://savrn.com/model-publishers/syubraj) ## Versions - [87663a8b5ef4](https://savrn.com/models/sentence-similarity-nepali-v2/versions/87663a8b5ef4) · current 2026-10-05 ## Explore More - [All sentence similarity models](https://savrn.com/models/tasks/sentence-similarity) - [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 2026-10-05. - [Hugging Face record](https://huggingface.co/syubraj/sentence_similarity_nepali_v2) - [How the hub is built](https://savrn.com/model-hub/methodology)