Model Type: Feature backbone; Params: 1136M (giant); Image size: 224 x 224 x 3; Patch size: 14 x 14 x 3; Repository: github.com:marrlab/DinoBloom; Original Weights: Zenodo.
Open-weight model · Feature extraction
patent_retriever_multilingual_nemotron_v0.1
by Elplaguister elplaguister/patent_retriever_multilingual_nemotron_v0.1
patent_retriever_multilingual_nemotron_v0.1 is an open-weight model for feature extraction from Elplaguister, released under other. It has 1.1B parameters and a 262,144-token context. At 16-bit it needs about 2.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Dense retriever for patent prior-art search (abstract → abstract), fine-tuned from on patent-family pairs (same invention filed in different jurisdictions / languages). Trained for Korean ↔ English cross-lingual and monolingual patent retrieval.
Parameters1.1B
Context262,144
Weights2.3 GB
Licenseother
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve patent_retriever_multilingual_nemotron_v0.1 (1.1B 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 | 2.3 GB | 2.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.1 GB | 1.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x 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, read Oct 18, 2026.
Model Card
Dense retriever for patent prior-art search (abstract → abstract), fine-tuned from on patent-family pairs (same invention filed in different jurisdictions / languages). Trained for Korean ↔ English cross-lingual and monolingual patent retrieval. Do not use the base model's asymmetric convention (query: / passage: ). It raises no error but silently degrades retrieval quality, because training was symmetric. corpus (other family members masked; one relevant document per query). crosssame: translation pairs (KR↔EN), crosssimilar: cross-lingual same-family non-translation pairs, monosimilar: monolingual same-family pairs. Scores on the 50k-document subset; full-corpus (209,671 documents)…
Excerpt from the card by Elplaguister, licensed other.
Configuration
- Architecture
- Ministral3Model
- Context length (tokens)
- 262,144
- Layers
- 16
- Hidden size
- 2,048
- Feed-forward size
- 6,144
- Attention heads
- 24
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 131,072
- Model type
- ministral3
Identity and Version
- Repository
- elplaguister/patent_retriever_multilingual_nemotron_v0.1
- Publisher
- Elplaguister
- Task
- Feature extraction
- Modality
- Text
- Library
- sentence-transformers
- Parameters
- 1.1B parameters
- Languages
- ko, en
- Revision
- 76513b12ee59bb82a9a83753dd088b1b546ca15f
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
10 files, 2.3 GB in total. The weights are 1 file totalling 2.3 GB in safetensors.
Weights1 file · 2.3 GB
Configuration5 files · 2.2 KB
Tokenizer2 files · 17.1 MB
Documentation1 file · 3.7 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 2.3 GB | 0429dfefc393 |
| 1_Pooling/config.json | Configuration | 91 B | — |
| config.json | Configuration | 1.1 KB | — |
| config_sentence_transformers.json | Configuration | 307 B | — |
| modules.json | Configuration | 429 B | — |
| sentence_bert_config.json | Configuration | 241 B | — |
| README.md | Documentation | 3.7 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.1 MB | 46288793f25a |
| tokenizer_config.json | Tokenizer | 21.2 KB | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 2.3 GB
Download from Elplaguister
Released by Elplaguister through its official repository on Hugging Face.
Built From
- Derived from nvidia/Nemotron-3-Embed-1B-BF16
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.3 GB |
| 16-bit | 2.3 GB |
| 8-bit | 1.1 GB |
| 4-bit | 0.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About patent_retriever_multilingual_nemotron_v0.1
How much GPU memory does patent_retriever_multilingual_nemotron_v0.1 need?
About 2.7 GB at 16-bit and 0.7 GB at 4-bit: the weights (1.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run patent_retriever_multilingual_nemotron_v0.1 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 license is patent_retriever_multilingual_nemotron_v0.1 released under?
other, as its publisher declares it. Read the license text before commercial use.
What is patent_retriever_multilingual_nemotron_v0.1's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.
Similar Models
Text, images, speech and environmental sounds in one embedding space. Vela Omni Mini supports multimodal search, routing and clustering with normalized vectors that can be compared directly. Scores are 0–100; higher is better. The comparison uses the same held-out evaluation examples, complete retrieval pools and 128-token text cap for both models. Bold marks improvement over the original large model. These known test pools are reused across releases. The common protocol uses labeled TRAIN prototypes for text classification and all matching positives for retrieval; it is separate from official MTEB classification. All 14 metrics, Macro-F1, exact counts and uncertainty. The primary metric…
EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M parameter text model with modular vision (170M) and audio (300M) encoders. Designed to run on consumer hardware such as mobile devices and laptops, EmbeddingGemma 2 delivers low-latency semantic representations for on-device applications, like search, retrieval-augmented generation (RAG), classification, and clustering. EmbeddingGemma 2 builds upon the architectural and capability advancements of Gemma 4, offering several…
This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385). A mixed-precision MLX checkpoint of google/embeddinggemma-2, Google DeepMind's multimodal embedding model that maps text, images, video and audio into one 768-dimensional vector space. It includes the text encoder, the vision encoder and the audio encoder. oQ quantizes the text encoder; the vision and audio encoders stay in BF16. oMLX serves text and image inputs through POST /v1/embeddings (jundot/omlx#4333) and does not load the audio encoder. The effective average is 13.258 bits/weight for the complete checkpoint. oQ8e allocates bits by measured layer…
This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385). A mixed-precision MLX checkpoint of google/embeddinggemma-2, Google DeepMind's multimodal embedding model that maps text, images, video and audio into one 768-dimensional vector space. It includes the text encoder, the vision encoder and the audio encoder. oQ quantizes the text encoder; the vision and audio encoders stay in BF16. oMLX serves text and image inputs through POST /v1/embeddings (jundot/omlx#4333) and does not load the audio encoder. The effective average is 12.702 bits/weight for the complete checkpoint. oQ6e allocates bits by measured layer…
This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385). A mixed-precision MLX checkpoint of google/embeddinggemma-2, Google DeepMind's multimodal embedding model that maps text, images, video and audio into one 768-dimensional vector space. It includes the text encoder, the vision encoder and the audio encoder. oQ quantizes the text encoder; the vision and audio encoders stay in BF16. oMLX serves text and image inputs through POST /v1/embeddings (jundot/omlx#4333) and does not load the audio encoder. The effective average is 11.991 bits/weight for the complete checkpoint. oQ4e allocates bits by measured layer…