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.
Params
823 M
Context
—
Downloads 30d
524 K
Likes
157
Download history
daily snapshots · 9 days524 K374 K
Oct 16Oct 19Oct 22Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 3.3 GB | 4.2 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- T5EncoderModel
- Parameters
- 823 M
- Tensor type
- F32
- Vocabulary
- 93,651
- Licence
- mit
- First seen on the Hub
- 2024-12-26
- Training datasets
- ai-forever/solyanka
- Added to our catalog
- 2026-10-16
Compare with any feature-extraction model