找到适合你的 AI 模型。

加入对比来源 / 文档 ↗

FRED-T5-large

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

FRIDA is a full-scale finetuned general text embedding model inspired by denoising architecture based on T5. The model is based on the encoder part of FRED-T5 model and continues research of text embedding models (ruMTEB, ru-en-RoSBERTa). It has been pre-trained on a Russian-English dataset and fine-tuned for improved performance on the target task. For more model details please refer to our article (RU). The model's results are presented on the MTEB and rusBEIR leaderboards. The model can be used as is with prefixes. It is recommended to use CLS pooling. The choice of prefix and pooling depends on the task.

译文排队中 · 当前显示来源原文

向量与相似度

输入文本→ 输出向量

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

FRIDA-Decisions

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

文本分析

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

kandinsky-videomae-large-camera-motion

ai-forever

VideoMAE model(`large`) variant that has been finetuned for multi-label video classification (a video can belong to multiple classes simultaneously) for camera motion classification on internal dataset. The model predicts `18` different camera motion `'arc_left', 'arc_right', 'dolly_in', 'dolly_out', 'pan_left', 'pan_right', 'pedestal_down', 'pedestal_up', 'roll_left', 'roll_right', 'static', 'tilt_down', 'tilt_up', 'truck_left', 'truck_right', 'undefined', 'zoom_in', 'zoom_out'` and and `3` shot type classes: `'pov', 'shake', 'track' ` . Model was trained to associate **entire video** with camera labels, not frame-level motions(!): [input video] -> label/labels (because multilabel) for all video. So, if this camera motion exists during all video frames model should predict this motion, otherwise it should predict `undefined`.

译文排队中 · 当前显示来源原文

视频分类

输入视频→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

mGPT

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

mGPT-13B

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

Pollux-4B-Judge

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ru-en-RoSBERTa

ai-forever

The ru-en-RoSBERTa is a general text embedding model for Russian. The model is based on ruRoBERTa and fine-tuned with ~4M pairs of supervised, synthetic and unsupervised data in Russian and English. Tokenizer supports some English tokens from RoBERTa tokenizer. For more model details please refer to our article. The model can be used as is with prefixes. It is recommended to use CLS pooling. The choice of prefix and pooling depends on the task.

译文排队中 · 当前显示来源原文

向量与相似度

输入文本→ 输出向量

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruBert-base

ai-forever

The model architecture design, pretraining, and evaluation are documented in our preprint: **A Family of Pretrained Transformer Language Models for Russian**. The model is pretrained by the SberDevices team. * Task: `mask filling` * Type: `encoder` * Tokenizer: `BPE` * Dict size: `120 138` * Num Parameters: `178 M` * Training Data Volume `30 GB`

译文排队中 · 当前显示来源原文

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruBert-large

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruclip-vit-base-patch16-384

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruclip-vit-base-patch32-384

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruElectra-large

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruGPT-3.5-13B

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

rugpt3large_based_on_gpt2

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

rugpt3medium_based_on_gpt2

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

rugpt3small_based_on_gpt2

ai-forever

The model architecture design, pretraining, and evaluation are documented in our preprint: **A Family of Pretrained Transformer Language Models for Russian**. The model was pretrained with sequence length 1024 using transformers by the SberDevices team on 80B tokens around 3 epochs. After that, the model was finetuned with the context size of 2048. + NLP core team RnD Telegram channel: + Dmitry Zmitrovich

译文排队中 · 当前显示来源原文

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruRoberta-large

ai-forever

The model architecture design, pretraining, and evaluation are documented in our preprint: **A Family of Pretrained Transformer Language Models for Russian**. The model is pretrained by the SberDevices team. * Task: `mask filling` * Type: `encoder` * Tokenizer: `BBPE` * Dict size: `50 257` * Num Parameters: `355 M` * Training Data Volume `250 GB`

译文排队中 · 当前显示来源原文

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruSciBERT

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruT5-base

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

ruT5-large

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

sage-fredt5-distilled-95m

ai-forever

The model corrects spelling and punctuation errors and typos by bringing all the words in the text to the norm of the Russian language. Corrector is a distilled version of the original model that had been trained based on the FRED-T5-1.7B architecture. An extensive dataset with “artificial” errors was taken as a training corpus: the corpus was assembled on the basis of the Russian-language Wikipedia and transcripts of Russian-language videos, then typos and spelling errors were automatically introduced into it using the library SAGE. Below are automatic metrics for determining the correctness of the spell checkers. We compare our solution with both open automatic spell checkers and the ChatGPT family of models on all four available datasets: - **RUSpellRU**: texts collected from (LiveJournal), with manually corrected typos and errors; - **MultidomainGold**: examples from 7 text sources, including the open web, news, social media, reviews, subtitles, policy documents and literary works; - **MedSpellChecker**: texts with errors from medical anamnesis; - **GitHubTypoCorpusRu**: spelling errors and typos in commits from GitHub; **RUSpellRU** | Model | Pr. (spell) | Rec. (spell) | F1 (spell) | Pr. (punc) | Rec. (punc) | F1 (punc) | Pr. (case) | Rec. (case) | F1 (case) | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | sage-fredt5-distilled-95m | 83.5 | 74.8 | 78.9 | 86.8 | 80.6 | 83.6 | 94.4 | 92.5 | 93.5 | | sage-ai-service | 90.3 | 86.3 | 88.2 | 90.3 | 86.6 | 88.4 | 95.2 | 95.9 | 95.6 | | gpt-3.5-turbo | 33.6 | 58.5 | 42.7 | 85.9 | 64.6 | 73.7 | 84.9 | 73.9 | 79.0 | | gpt-4 | 54.9 | 76.7 | 64.0 | 84.0 | 82.3 | 83.2 | 91.5 | 90.2 | 90.9 |

译文排队中 · 当前显示来源原文

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

sage-fredt5-large

ai-forever

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对