mesolitica
/

mnli-malaysian-mistral-191M-MLM-512

Text Classification

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Finetune MLM Malaysian Mistral 191M on MNLI

Original model https://huggingface.co/mesolitica/malaysian-mistral-191M-MLM-512, done by https://github.com/aisyahrzk https://twitter.com/aisyahhhrzk

You must use model from here https://github.com/mesolitica/malaya/blob/master/session/llm2vec/classifier.py

dataset

source code at https://github.com/mesolitica/malaya/tree/master/session/similarity/hf-t5
prepared dataset at https://huggingface.co/datasets/mesolitica/semisupervised-corpus/tree/main/similarity

Accuracy

              precision    recall  f1-score   support

           0    0.84488   0.90914   0.87583      7165
           1    0.92182   0.86519   0.89261      8872

    accuracy                        0.88483     16037
   macro avg    0.88335   0.88717   0.88422     16037
weighted avg    0.88744   0.88483   0.88511     16037

Downloads last month: 6

Safetensors

Model size

166M params

Tensor type

F32

·

Inference Examples

Text Classification

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including mesolitica/mnli-malaysian-mistral-191M-MLM-512

Malaysian LLM2Vec

Extending Malaysian CausalLM on non-causal masking training, https://arxiv.org/abs/2404.05961 • 5 items • Updated Sep 22