Instructions to use Andrilko/ruBert-base-reward with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Andrilko/ruBert-base-reward with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Andrilko/ruBert-base-reward", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from Andrilko/ruBert-base-reward: direct link, hf CLI and curl.
- Browser
- Download file 544 Bytes
-
https://huggingface.co/Andrilko/ruBert-base-reward/resolve/main/config.json
- Command line
-
hf download hf://Andrilko/ruBert-base-reward/config.json
-
curl -L -o config.json https://huggingface.co/Andrilko/ruBert-base-reward/resolve/main/config.json
544 Bytes
| { | |
| "attention_probs_dropout_prob": 0.1, | |
| "directionality": "bidi", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 512, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pooler_fc_size": 768, | |
| "pooler_num_attention_heads": 12, | |
| "pooler_num_fc_layers": 3, | |
| "pooler_size_per_head": 128, | |
| "pooler_type": "first_token_transform", | |
| "type_vocab_size": 2, | |
| "vocab_size": 120138, | |
| "model_type": "bert" | |
| } | |