Text Classification
Transformers
ONNX
Safetensors
English
Tagalog
xlm-roberta
sentiment-analysis
filipino
taglish
text-embeddings-inference
Instructions to use cjcastro/xlm-roberta-Rise-On-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cjcastro/xlm-roberta-Rise-On-AI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="cjcastro/xlm-roberta-Rise-On-AI")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("cjcastro/xlm-roberta-Rise-On-AI") model = AutoModelForSequenceClassification.from_pretrained("cjcastro/xlm-roberta-Rise-On-AI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_config.json from cjcastro/xlm-roberta-Rise-On-AI: direct link, hf CLI and curl.
- Browser
- Download file 593 Bytes
-
https://huggingface.co/cjcastro/xlm-roberta-Rise-On-AI/resolve/main/training_config.json
- Command line
-
hf download hf://cjcastro/xlm-roberta-Rise-On-AI/training_config.json
-
curl -L -o training_config.json https://huggingface.co/cjcastro/xlm-roberta-Rise-On-AI/resolve/main/training_config.json
593 Bytes
| { | |
| "base_model": "FacebookAI/xlm-roberta-base", | |
| "max_seq_len": 256, | |
| "use_lora": true, | |
| "lora_r": 32, | |
| "lora_alpha": 64, | |
| "lora_dropout": 0.1, | |
| "learning_rate": 0.0001, | |
| "num_train_epochs": 6, | |
| "per_device_train_batch_size": 16, | |
| "per_device_eval_batch_size": 16, | |
| "gradient_accumulation_steps": 2, | |
| "warmup_ratio": 0.15, | |
| "weight_decay": 0.01, | |
| "fp16": true, | |
| "early_stopping_patience": 5, | |
| "hp_trials": 1, | |
| "output_dir": "C:\\xampp\\htdocs\\Rise-On-AI\\scripts\\sentiment-model-training\\outputs\\best_model", | |
| "best_eval_f1_macro": 0.8157473649436856 | |
| } |