Feature Extraction
Transformers
Safetensors
Vietnamese
deberta-v2
vietnamese
summarization-evaluation
efficient-evaluation
multi-criteria-evaluation
evaluation
reward-model
rlhf
cross-encoder
Instructions to use phuongntc/Multi_EvalSumViet2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use phuongntc/Multi_EvalSumViet2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="phuongntc/Multi_EvalSumViet2")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("phuongntc/Multi_EvalSumViet2") model = AutoModel.from_pretrained("phuongntc/Multi_EvalSumViet2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "backbone": "Fsoft-AIC/videberta-base", | |
| "pooling": "mean", | |
| "trunk": { | |
| "type": "mlp", | |
| "hidden_in": 768, | |
| "hidden_mid": 256, | |
| "activation": "gelu", | |
| "dropout": 0.1 | |
| }, | |
| "heads": [ | |
| { | |
| "name": "faith", | |
| "type": "linear", | |
| "in": 256, | |
| "out": 1 | |
| }, | |
| { | |
| "name": "coherence", | |
| "type": "linear", | |
| "in": 256, | |
| "out": 1 | |
| }, | |
| { | |
| "name": "relevance", | |
| "type": "linear", | |
| "in": 256, | |
| "out": 1 | |
| } | |
| ], | |
| "labels": [ | |
| "faith", | |
| "coherence", | |
| "relevance" | |
| ], | |
| "output_range": [ | |
| 0.0, | |
| 1.0 | |
| ] | |
| } |