About
Object…
Contributions
-
How can you detect data drift in an AI data pipeline?
In simple, it refers to change in distribution of training data w.r.t. production data(in layman's term, imagine training samples as bar plot and when production sample does not fit into the bar plot, drift arises). The distribution varies across text, image, speech.
-
How can you compare and select the best ML algorithms?
In the process of algorithm selection, it's akin to trying on different outfits to find the one that fits you the best. Each algorithm is like a unique outfit, offering different styles and fits. Evaluating them involves checking how well each outfit complements your figure – in the ML world, it's about metrics like accuracy, precision, recall, and F1 score. The chosen algorithm should not only look good on the training data but also suit unseen data, demonstrating its versatility and reliability. Just like finding that perfect outfit, the selected algorithm should make you feel confident across various situations.
-
How can you compare and select the best ML algorithms?
Selecting the best machine learning algorithm involves assessing your data's characteristics, such as size and complexity. Try various algorithms—like decision trees, neural networks, or support vector machines—and evaluate their performance using metrics like accuracy/F1-score. Consider the algorithm's suitability for your task; some are better for specific types of data or problems. Experiment with hyperparameter tuning to optimize performance. Ultimately, the best algorithm depends on your data and the problem you're solving.
Activity
-
Microsoft just open-sourced GraphRAG. It might be the best Python library to extract insights from unstructured text. It uses LLMs to automate the…
Microsoft just open-sourced GraphRAG. It might be the best Python library to extract insights from unstructured text. It uses LLMs to automate the…
Liked by Vaishnov RG
-
𝐟𝐚𝐬𝐭𝐜 - 𝐋𝐢𝐠𝐡𝐭𝐰𝐞𝐢𝐠𝐡𝐭 𝐋𝐋𝐌 𝐛𝐚𝐬𝐞𝐝 𝐓𝐞𝐱𝐭 𝐂𝐥𝐚𝐬𝐬𝐢𝐟𝐢𝐞𝐫 fastc is a simple and lightweight text classifiers with LLM…
𝐟𝐚𝐬𝐭𝐜 - 𝐋𝐢𝐠𝐡𝐭𝐰𝐞𝐢𝐠𝐡𝐭 𝐋𝐋𝐌 𝐛𝐚𝐬𝐞𝐝 𝐓𝐞𝐱𝐭 𝐂𝐥𝐚𝐬𝐬𝐢𝐟𝐢𝐞𝐫 fastc is a simple and lightweight text classifiers with LLM…
Liked by Vaishnov RG
-
𝐋𝐢𝐭𝐆𝐏𝐓 - 𝐅𝐢𝐧𝐞𝐭𝐮𝐧𝐞, 𝐩𝐫𝐞𝐭𝐫𝐚𝐢𝐧 𝐚𝐧𝐝 𝐝𝐞𝐩𝐥𝐨𝐲 𝐋𝐋𝐌𝐬 𝐋𝐢𝐠𝐡𝐭𝐧𝐢𝐧𝐠 𝐟𝐚𝐬𝐭 LitGPT is a command-line tool designed to…
𝐋𝐢𝐭𝐆𝐏𝐓 - 𝐅𝐢𝐧𝐞𝐭𝐮𝐧𝐞, 𝐩𝐫𝐞𝐭𝐫𝐚𝐢𝐧 𝐚𝐧𝐝 𝐝𝐞𝐩𝐥𝐨𝐲 𝐋𝐋𝐌𝐬 𝐋𝐢𝐠𝐡𝐭𝐧𝐢𝐧𝐠 𝐟𝐚𝐬𝐭 LitGPT is a command-line tool designed to…
Liked by Vaishnov RG
Experience
Education
Licenses & Certifications
More activity by Vaishnov
-
🌟 Excited to Share My Experience at the TFUG Community Meetup at IITM! 🌟 I had the incredible opportunity to attend the recent TensorFlow User…
🌟 Excited to Share My Experience at the TFUG Community Meetup at IITM! 🌟 I had the incredible opportunity to attend the recent TensorFlow User…
Liked by Vaishnov RG
-
Extended Long Short-Term Memory (xLSTM) was recently introduced by the authors of LSTM with the motive to see how far it can get in language modeling…
Extended Long Short-Term Memory (xLSTM) was recently introduced by the authors of LSTM with the motive to see how far it can get in language modeling…
Liked by Vaishnov RG
-
Last week, Hugging Face released Idefics2, its new open-source vision-language model. 🔥 Idefics initially started as a replication of Google…
Last week, Hugging Face released Idefics2, its new open-source vision-language model. 🔥 Idefics initially started as a replication of Google…
Liked by Vaishnov RG
-
Hello Everyone :) I'm so excited to share that last Saturday, on April 27th, 2024, I had the exhilarating opportunity to participate in the "𝐑𝐀𝐆…
Hello Everyone :) I'm so excited to share that last Saturday, on April 27th, 2024, I had the exhilarating opportunity to participate in the "𝐑𝐀𝐆…
Liked by Vaishnov RG
-
in case you missed it earlier this week, Phi-3 is a new "smallish" (😅) 3.8B language model just released by Microsoft. It outperforms other models…
in case you missed it earlier this week, Phi-3 is a new "smallish" (😅) 3.8B language model just released by Microsoft. It outperforms other models…
Liked by Vaishnov RG
-
Its clear that India's AI success would be written by young minds, mostly youth in their 20s right now. With fresh perspectives and groundbreaking…
Its clear that India's AI success would be written by young minds, mostly youth in their 20s right now. With fresh perspectives and groundbreaking…
Liked by Vaishnov RG
-
🚨 Stop everything you are doing! The day has come? Cohere just released an open model that beats GPT-4 turbo on function calling?! (needs some extra…
🚨 Stop everything you are doing! The day has come? Cohere just released an open model that beats GPT-4 turbo on function calling?! (needs some extra…
Liked by Vaishnov RG
-
Good article by anthropic on multi shot jailbreaking. As LLM grows over time, authors are coming up with long window context, adding those models…
Good article by anthropic on multi shot jailbreaking. As LLM grows over time, authors are coming up with long window context, adding those models…
Shared by Vaishnov RG
-
A very good #GenAI meetup for the folks in Chennai this weekend. Looking forward to the sessions from Ravi Theja Desetty & Tamil Arasan Ph.D.
A very good #GenAI meetup for the folks in Chennai this weekend. Looking forward to the sessions from Ravi Theja Desetty & Tamil Arasan Ph.D.
Liked by Vaishnov RG
-
GPU Poor, no more you are.✨ We are excited to announce “Train on DGX” Cloud on Hugging Face to train open LLMs on one or more NVIDIA H100 and L40S…
GPU Poor, no more you are.✨ We are excited to announce “Train on DGX” Cloud on Hugging Face to train open LLMs on one or more NVIDIA H100 and L40S…
Liked by Vaishnov RG
-
7-day return policy for Savings Plans. Savings Plans is a flexible pricing model that can help you reduce your bill by up to 72% compared to…
7-day return policy for Savings Plans. Savings Plans is a flexible pricing model that can help you reduce your bill by up to 72% compared to…
Liked by Vaishnov RG
-
New Project Update: Fine Tuning 2B Instruct Gemma model on Indian History Dataset Using PEFT Hardware Used : Free Single P100 GPU by Kaggle The…
New Project Update: Fine Tuning 2B Instruct Gemma model on Indian History Dataset Using PEFT Hardware Used : Free Single P100 GPU by Kaggle The…
Liked by Vaishnov RG
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More