AI/EXPLORER
ToolsCategoriesSitesLLMsCompareAI QuizAlternativesPremium
—AI Tools
—Sites & Blogs
—LLMs & Models
—Categories
AI Explorer

Find and compare the best artificial intelligence tools for your projects.

Made within France

Explore

  • ›All tools
  • ›Sites & Blogs
  • ›LLMs & Models
  • ›Compare
  • ›Chatbots
  • ›AI Images
  • ›Code & Dev

Company

  • ›Premium
  • ›About
  • ›Contact
  • ›Blog

Legal

  • ›Legal notice
  • ›Privacy
  • ›Terms

© 2026 AI Explorer·All rights reserved.

HomeLLMsFRIDA

FRIDA

by ai-forever

Open source · 573k downloads · 136 likes

2.7
(136 reviews)EmbeddingAPI & Local
About

FRIDA is a versatile text embedding model inspired by denoising architectures and based on the FRED-T5 encoder. Trained on both Russian and English data, it excels in semantic understanding and text representation, with optimized performance for Russian. The model stands out for its flexibility, achieved through the use of specific prefixes that adapt its behavior to various tasks such as information retrieval, sentiment analysis, or paraphrase detection. Its use cases include natural language processing, sentiment analysis, and thematic categorization, while also allowing fine-tuning for more targeted needs. Designed to handle texts up to 512 tokens, it provides a robust solution for multilingual applications, though its performance in English remains to be evaluated.

Documentation

Model Card for FRIDA

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).

Usage

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.

We use the following basic rules to choose a prefix:

  • "search_query: " and "search_document: " prefixes are for answer or relevant paragraph retrieval
  • "paraphrase: " prefix is for symmetric paraphrasing related tasks (STS, paraphrase mining, deduplication)
  • "categorize: " prefix is for asymmetric matching of document title and body (e.g. news, scientific papers, social posts)
  • "categorize_sentiment: " prefix is for any tasks that rely on sentiment features (e.g. hate, toxic, emotion)
  • "categorize_topic: " prefix is intended for tasks where you need to group texts by topic
  • "categorize_entailment: " prefix is for textual entailment task (NLI)

To better tailor the model to your needs, you can fine-tune it with relevant high-quality Russian and English datasets.

Below are examples of texts encoding using the Transformers and SentenceTransformers libraries.

Transformers

Python
import torch
import torch.nn.functional as F
from transformers import AutoTokenizer, T5EncoderModel


def pool(hidden_state, mask, pooling_method="cls"):
    if pooling_method == "mean":
        s = torch.sum(hidden_state * mask.unsqueeze(-1).float(), dim=1)
        d = mask.sum(axis=1, keepdim=True).float()
        return s / d
    elif pooling_method == "cls":
        return hidden_state[:, 0]

inputs = [
    # 
    "paraphrase: В Ярославской области разрешили работу бань, но без посетителей",
    "categorize_entailment: Женщину доставили в больницу, за ее жизнь сейчас борются врачи.",
    "search_query: Сколько программистов нужно, чтобы вкрутить лампочку?",
    # 
    "paraphrase: Ярославским баням разрешили работать без посетителей",
    "categorize_entailment: Женщину спасают врачи.",
    "search_document: Чтобы вкрутить лампочку, требуется три программиста: один напишет программу извлечения лампочки, другой — вкручивания лампочки, а третий проведет тестирование."
]

tokenizer = AutoTokenizer.from_pretrained("ai-forever/FRIDA")
model = T5EncoderModel.from_pretrained("ai-forever/FRIDA")

tokenized_inputs = tokenizer(inputs, max_length=512, padding=True, truncation=True, return_tensors="pt")

with torch.no_grad():
    outputs = model(**tokenized_inputs)
    
embeddings = pool(
    outputs.last_hidden_state, 
    tokenized_inputs["attention_mask"],
    pooling_method="cls" # or try "mean"
)

embeddings = F.normalize(embeddings, p=2, dim=1)
sim_scores = embeddings[:3] @ embeddings[3:].T
print(sim_scores.diag().tolist())
# [0.9360030293464661, 0.8591322302818298, 0.728583037853241]

SentenceTransformers

Python
from sentence_transformers import SentenceTransformer

inputs = [
    # 
    "paraphrase: В Ярославской области разрешили работу бань, но без посетителей",
    "categorize_entailment: Женщину доставили в больницу, за ее жизнь сейчас борются врачи.",
    "search_query: Сколько программистов нужно, чтобы вкрутить лампочку?",
    # 
    "paraphrase: Ярославским баням разрешили работать без посетителей",
    "categorize_entailment: Женщину спасают врачи.",
    "search_document: Чтобы вкрутить лампочку, требуется три программиста: один напишет программу извлечения лампочки, другой — вкручивания лампочки, а третий проведет тестирование."
]

# loads model with CLS pooling
model = SentenceTransformer("ai-forever/FRIDA")

# embeddings are normalized by default
embeddings = model.encode(inputs, convert_to_tensor=True)

sim_scores = embeddings[:3] @ embeddings[3:].T
print(sim_scores.diag().tolist())
# [0.9360026717185974, 0.8591331243515015, 0.7285830974578857]

or using prompts (sentence-transformers>=2.4.0):

Python
from sentence_transformers import SentenceTransformer

# loads model with CLS pooling
model = SentenceTransformer("ai-forever/FRIDA")

paraphrase = model.encode(["В Ярославской области разрешили работу бань, но без посетителей", "Ярославским баням разрешили работать без посетителей"], prompt_name="paraphrase")
print(paraphrase[0] @ paraphrase[1].T) # 0.9360032

categorize_entailment = model.encode(["Женщину доставили в больницу, за ее жизнь сейчас борются врачи.", "Женщину спасают врачи."], prompt_name="categorize_entailment")
print(categorize_entailment[0] @ categorize_entailment[1].T) # 0.8591322

query_embedding = model.encode("Сколько программистов нужно, чтобы вкрутить лампочку?", prompt_name="search_query")
document_embedding = model.encode("Чтобы вкрутить лампочку, требуется три программиста: один напишет программу извлечения лампочки, другой — вкручивания лампочки, а третий проведет тестирование.", prompt_name="search_document")
print(query_embedding @ document_embedding.T) # 0.7285831

Authors

  • SaluteDevices AI for B2C RnD Team.
  • Artem Snegirev: HF profile, Github;
  • Anna Maksimova HF profile;
  • Aleksandr Abramov: HF profile, Github, Kaggle Competitions Master

Citation

SCSS
@misc{TODO
}

Limitations

The model is designed to process texts in Russian, the quality in English is unknown. Maximum input text length is limited to 512 tokens.

Capabilities & Tags
sentence-transformerssafetensorst5mtebtransformersfeature-extractionruenmodel-indexendpoints_compatible
Links & Resources
Specifications
CategoryEmbedding
AccessAPI & Local
LicenseOpen Source
PricingOpen Source
Rating
2.7

Try FRIDA

Access the model directly