Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Vikhrmodels
/
VikhrT5-3b
like
6
Text2Text Generation
Transformers
Safetensors
IlyaGusev/habr
Russian
t5
Inference Endpoints
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
Edit model card
VikhrT5-3b: Улучшенная модель на базе FLAN T5 3b для русского языка
VikhrT5-3b: Улучшенная модель на базе FLAN T5 3b для русского языка
Cкорее всего она лучше чем FRED T5XL
Dataset
VikhrT5-3b
FRED-T5-XL(1.7b)
FLAN-t5-xl(3b)
ru_mmlu
0.32
0.252
0.28 (лол2)
xwinograd_ru
0.71 (lol)
0.57
0.52
xnli_ru
0.4280
0.34
0.33
Downloads last month
11
Safetensors
Model size
2.96B params
Tensor type
F32
·
Inference API
Text2Text Generation
Compute
Model is too large to load in Inference API (serverless). To try the model, launch it on
Inference Endpoints (dedicated)
instead.
JSON Output
Maximize
Dataset used to train
Vikhrmodels/VikhrT5-3b
IlyaGusev/habr
Viewer
•
Updated
Mar 9, 2023
•
76k
•
141
•
19
Spaces using
Vikhrmodels/VikhrT5-3b
2
🚀
KennyOry/Vikhrmodels-VikhrT5-3b
😻
fuwiak/Vikhrmodels-VikhrT5-3b