🚀 Models
🔥 Sign in
Back to all models
Model: jannesg/takalane_nbl_roberta
pytorch roberta lm-head masked-lm nr fill-mask license:mit
fill-mask mask_token: <mask>
Query this model
🔥 This model is currently loaded and running on the Inference API. ⚠️ This model could not be loaded by the inference API. ⚠️ This model can be loaded on the Inference API on-demand.
JSON Output
API endpoint 
								$
								curl -X POST \

									-H "Authorization: Bearer YOUR_ORG_OR_USER_API_TOKEN" \

								-H "Content-Type: application/json" \

									-d '"json encoded string"' \

								https://api-inference.huggingface.co/models/jannesg/takalane_nbl_roberta
Share Copied link to clipboard

Monthly model downloads

jannesg/takalane_nbl_roberta jannesg/takalane_nbl_roberta
17 downloads
last 30 days

pytorch

tf

Contributed by

jannesg Jannes Germishuys
11 models

How to use this model directly from the 🤗/transformers library: 

			
Copy to clipboard

			from transformers import AutoTokenizer, AutoModelWithLMHead

			tokenizer = AutoTokenizer.from_pretrained("jannesg/takalane_nbl_roberta")
			
			model = AutoModelWithLMHead.from_pretrained("jannesg/takalane_nbl_roberta")
List all files in model · See raw config file
Update on GitHub

Takalani Sesame - Ndebele 🇿🇦

Model description

Takalani Sesame (named after the South African version of Sesame Street) is a project that aims to promote the use of South African languages in NLP, and in particular look at techniques for low-resource languages to equalise performance with larger languages around the world.

Intended uses & limitations

How to use

from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("jannesg/takalane_nbl_roberta")

model = AutoModelWithLMHead.from_pretrained("jannesg/takalane_nbl_roberta")

Limitations and bias

Updates will be added continously to improve performance. This is a very low resource language, results may be poor at first.

Training data

Data collected from https://wortschatz.uni-leipzig.de/en
Sentences: 318M

Training procedure

No preprocessing. Standard Huggingface hyperparameters.

Author

Jannes Germishuys website

List of model files
File name Last modified File size
config.json Thu, 16 Jul 2020 15:44:55 GMT 515.0B
merges.txt Thu, 16 Jul 2020 15:44:53 GMT 18.1KB
pytorch_model.bin Thu, 16 Jul 2020 15:45:00 GMT 320.8MB
training_args.bin Thu, 16 Jul 2020 15:45:20 GMT 1.1KB
vocab.json Thu, 16 Jul 2020 15:44:50 GMT 32.1KB
Done