SAVRN
Search Contact SAVRN

Open-weight model · Feature extraction

RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct

by RKNNAI RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct

RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct is an open-weight model for feature extraction from RKNNAI, released under Apache License 2.0. Its published files total 2.1 GB. It draws 1 downloads a month.

本仓库提供由 Alibaba-NLP/gme-Qwen2-VL-2B-Instruct 转换的 RKNN 模型。 - Model ID:RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct - 模型显示名称:RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct - 源模型:Alibaba-NLP/gme-Qwen2-VL-2B-Instruct - 模型类型:EMBEDDING ModelScope 完整下载: Hugging Face…

Parameters—
Context—
Weights472.7 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1

Model Card

By RKNNAI, published under apache-2.0, revision fe436fc52509.

本仓库提供由 Alibaba-NLP/gme-Qwen2-VL-2B-Instruct 转换的 RKNN 模型。 - Model ID:RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct - 模型显示名称:RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct - 源模型:Alibaba-NLP/gme-Qwen2-VL-2B-Instruct - 模型类型:EMBEDDING ModelScope 完整下载: Hugging Face 完整下载: ModelScope 指定配置下载: Hugging Face 指定配置下载: - 使用配套 RKNN Runtime 和驱动;运行前用 rknn-smi -v 检查设备端版本。 - 用于图文检索,输出 embedding 向量。 - 源模型许可证:Apache License 2.0,正文见 LICENSE,归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可;本包不包含运行库。

Read RKNNAI's full model card

1. 模型介绍

本仓库提供由 Alibaba-NLP/gme-Qwen2-VL-2B-Instruct 转换的 RKNN 模型。

  • Model ID:RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct
  • 模型显示名称:RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct
  • 发布版本:v1.1.0
  • 源模型:Alibaba-NLP/gme-Qwen2-VL-2B-Instruct
  • 模型类型:EMBEDDING
  • 芯片字段:RK182X
  • 具体支持芯片:RK1820、RK1828

可用模型

发布版本 配置目录 支持芯片 分辨率 量化方式 NPU 核数 上下文长度(tokens) 最大文本长度(tokens) KVCache
v1.1.0 gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048 RK1820、RK1828 Vision: 448x448 Vision: w4a16;Embedding: w6a16 Vision: 8;Embedding: 8 Embedding: 2048(2k) Embedding: 2048(2k) Embedding: fp16

2. 文件说明

文件或目录 说明
LICENSE 源模型许可证
NOTICE 许可、使用要求及归属说明
<配置目录>/ 配套模型文件
子目录 README.md 当前配置说明
子目录 config.json 模型配置与文件清单
子目录 SHA256SUMS 当前目录交付文件的 SHA-256 校验值(不包含自身)

3. 模型下载

ModelScope 完整下载:

modelscope download --model RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct --revision v1.1.0 --local_dir ./RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct

Hugging Face 完整下载:

hf download RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct --revision v1.1.0 --local-dir ./RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct

ModelScope 指定配置下载:

from modelscope import snapshot_download

snapshot_download(
    "RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct",
    revision="v1.1.0",
    allow_patterns=["README.md", "LICENSE", "NOTICE", "gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/**"],
    local_dir="./RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct",
)

Hugging Face 指定配置下载:

hf download RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct --revision v1.1.0 --include "README.md" "LICENSE" "NOTICE" "gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/**" --local-dir ./RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct

4. SHA-256 校验

在配置目录执行:

cd ./RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct/gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048
sha256sum -c SHA256SUMS

所有条目显示 OK 后再部署。

5. 兼容性与限制

  • 支持芯片:RK1820、RK1828。
  • 使用配套 RKNN Runtime 和驱动;运行前用 rknn-smi -v 检查设备端版本。
  • 所选配置目录内的文件须配套使用。
  • 用于图文检索,输出 embedding 向量。

6. 版权与许可证

  • 源模型许可证:Apache License 2.0,正文见 LICENSE,归属与转换修改说明见 NOTICE。
  • 本仓库交付物为源权重的转换衍生物,仍受源模型许可和使用限制约束;不是上游未经修改的原始权重。
  • 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可;本包不包含运行库。

Identity and Version

Repository
RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct
Publisher
RKNNAI
Task
Feature extraction
Modality
Text
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
fe436fc525094fb33d83fe05da9981c87fdd2a71
First published
2026-09-24
Last updated
2026-09-28

Files and Weights

15 files, 2.1 GB in total. The weights are 2 files totalling 472.7 MB in bin, gguf.

Weights2 files · 472.7 MB
Configuration1 file · 8.1 KB
Documentation4 files · 18.2 KB
Other7 files · 1.6 GB
Repository1 file · 2.1 KB
Every file
FileTypeSizeSHA-256
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/gme-Qwen2-VL-2B-Instruct-llm.embed.binWeights466.7 MB 2477dce2028f
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/gme-Qwen2-VL-2B-Instruct-llm.tokenizer.ggufWeights5.9 MB 0e16d17c6999
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/config.jsonConfiguration8.1 KB —
LICENSEDocumentation11.4 KB —
NOTICEDocumentation512 B —
README.mdDocumentation3.5 KB —
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/README.mdDocumentation2.8 KB —
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/SHA256SUMSOther1.0 KB —
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/gme-Qwen2-VL-2B-Instruct-llm-model_report.htmlOther816.8 KB —
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/gme-Qwen2-VL-2B-Instruct-llm.rknnOther19.0 MB cf63dcc5765a
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/gme-Qwen2-VL-2B-Instruct-llm.weightOther1.2 GB 644132ccb1fc
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/gme-Qwen2-VL-2B-Instruct-vision-model_report.htmlOther85.0 KB —
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/gme-Qwen2-VL-2B-Instruct-vision.rknnOther8.1 MB f39a058caede
gme-Qwen2-VL-2B-Instruct-448x448-w4a16-w6a16-8-2048/gme-Qwen2-VL-2B-Instruct-vision.weightOther418.6 MB bfe221c95e54
.gitattributesRepository2.1 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
472.7 MB
Download from RKNNAI

Released by RKNNAI through its official repository on Hugging Face. Read the license.

Built From

  • Derived from Alibaba-NLP/gme-Qwen2-VL-2B-Instruct
  • Quantized from Alibaba-NLP/gme-Qwen2-VL-2B-Instruct

Memory Requirements

PrecisionWeights in memory
As published472.7 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct

Can I use RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct commercially?

Yes. RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Feature extraction

all-MiniLM-L6-v2

Joshua

https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: You can then use the model to compute embeddings like this: You can convert this Tensor to a nested JavaScript array using.tolist(): Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Open weights apache-2.0 512 tokens transformers.js

Model · Feature extraction

bge-base-en-v1.5

Joshua

https://huggingface.co/BAAI/bge-base-en-v1.5 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: You can then use the model to compute embeddings, as follows: You can also use the model for retrieval. For example: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Open weights mit 512 tokens transformers.js

Model · Feature extraction

clap-htsat-unfused

LAION eV

The abstract of the paper states that: You can use this model for zero shot audio classification or extracting audio and/or textual features. You can also get the audio and text embeddings using ClapModel If you are using this model for your work, please consider citing the original paper

Open weights apache-2.0 514 tokens transformers

For more details please refer to our Github: FlagEmbedding. If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using bge-m3. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 1/30/2024: Release BGE-M3, a new member to BGE model series! M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. Technical…

Open weights mit 512 tokens sentence-transformers

Model · Feature extraction

wavlm-large

Microsoft

The large model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. Note: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model speech recognition, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli Authors: Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin…

Open weights transformers