Pradeep Bansal – Medium

Pradeep Bansal

Pinned

How to do named entity recognition for languages other than English?

A language model (LM), whether to predict the next word in a sequence or to predict entities or tags in a sequence are related to a…

Aug 1, 2023

Number of samples against the test-f1-score for MonoLingual NER model for french language

Aug 1, 2023

Pinned

Learning Transformers via Question and Answer

Behind all the GPT-x and other Large Language Models (LLMs), there’s only one thing that is common between all these LLMs and is also the…

Jun 4, 2023

Learning Transformers via Question and Answer

Jun 4, 2023

Pinned

Published in
Artificial Intelligence in Plain English

Why your Machine Learning model may not work in production ?

Most of the machine learning models never go to production but its worse when the models in production become worthless pretty soon. This…

Apr 14, 2020

Why your Machine Learning model may not work in production ?

Apr 14, 2020

Pinned

Published in
Artificial Intelligence in Plain English

How to structure our machine learning projects ?

We are all familiar with the following steps for any Machine Learning project —EDA, Data cleaning, Feature engineering, model selection…

Apr 26, 2020

How to structure our machine learning projects ?

Apr 26, 2020

Pinned

Scaling the kafka consumer for a machine learning service in python

The Set Up

Jul 7, 2021

Scaling the kafka consumer for a machine learning service in python

Jul 7, 2021

LLM Hallucination Detection: Background with latest techniques

One major hurdle in adopting AI for real life scenario is its inability to be accurate every time. There was a sudden “hope” with the…

Jun 11

LLM Hallucination Detection: Background with latest techniques

Jun 11

LLM Hallucination Detection: Can LLM-Generated Knowledge Graphs Be Trusted?

An LLM response can be hallucinated which means it can be factually incorrect or inconsistent w.r.t. the reference document. For eg. while…

Jun 10

LLM Hallucination Detection: Can LLM-Generated Knowledge Graphs Be Trusted?

Jun 10

Fine-Tuning a pre-trained LLM with unlabelled dataset

A generic LLM or an LLM pre-trained on the dataset different from the domain of the final task has to be fine-tuned to the task specific…

Oct 1, 2023

Fine-Tuning a pre-trained LLM with unlabelled dataset

Oct 1, 2023

How do you use BERT as a classifier without fine-tuning?

BERT, Bidirectional Encoder Representations from Transformers, is the deep learning model quite famous for generating embeddings that are…

Sep 27, 2023

How do you use BERT as a classifier without fine-tuning?

Sep 27, 2023

Common questions while using the Hugging Face’s transformers library.

Instead of writing one complete blog on topics like summarization or text generation, I thought of taking most important topics involved…

Aug 7, 2023

Common questions while using the Hugging Face’s transformers library.

Aug 7, 2023

Pradeep Bansal

Pradeep Bansal

Staff ML Engineer, MS IISc, Ex-Entrepreneur, ML Consultant, Health Expert https://www.linkedin.com/in/pradeepud/

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams