Token Classification
Transformers
PyTorch
JAX
Safetensors
Nepali
English
multilingual
bert
codeswitching
nepali-english
language-identification
Instructions to use sagorsarker/codeswitch-nepeng-lid-lince with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sagorsarker/codeswitch-nepeng-lid-lince with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="sagorsarker/codeswitch-nepeng-lid-lince")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-nepeng-lid-lince") model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-nepeng-lid-lince", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.txt from sagorsarker/codeswitch-nepeng-lid-lince: direct link, hf CLI and curl.
- Browser
- Download file 183 Bytes
-
https://huggingface.co/sagorsarker/codeswitch-nepeng-lid-lince/resolve/main/eval_results.txt
- Command line
-
hf download hf://sagorsarker/codeswitch-nepeng-lid-lince/eval_results.txt
-
curl -L -o eval_results.txt https://huggingface.co/sagorsarker/codeswitch-nepeng-lid-lince/resolve/main/eval_results.txt
183 Bytes
| eval_loss = 0.11671152709376391 | |
| eval_accuracy_score = 0.9676230996731179 | |
| eval_precision = 0.9076185402237613 | |
| eval_recall = 0.9031916021630793 | |
| eval_f1 = 0.9053996598639455 | |
| epoch = 5.0 | |