Fill-Mask
Transformers
PyTorch
Safetensors
Russian
English
bert
pretraining
russian
embeddings
masked-lm
tiny
feature-extraction
sentence-similarity
Instructions to use cointegrated/rubert-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cointegrated/rubert-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="cointegrated/rubert-tiny")# Load model directly from transformers import AutoTokenizer, AutoModelForPreTraining tokenizer = AutoTokenizer.from_pretrained("cointegrated/rubert-tiny") model = AutoModelForPreTraining.from_pretrained("cointegrated/rubert-tiny") - Inference
- Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "/gd/MyDrive/models/tinybert-ru-t5-decoder", | |
| "architectures": [ | |
| "T5ForConditionalGeneration" | |
| ], | |
| "d_ff": 1024, | |
| "d_kv": 64, | |
| "d_model": 512, | |
| "decoder_start_token_id": 0, | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "gradient_checkpointing": false, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "num_decoder_layers": 8, | |
| "num_heads": 6, | |
| "num_layers": 8, | |
| "pad_token_id": 0, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "transformers_version": "4.6.1", | |
| "use_cache": true, | |
| "vocab_size": 20100 | |
| } | |