Kalyan KS @kalyan_kpl Twitter profile | Pikagi

Pikagi

Kalyan KS

@kalyan_kpl

782

Followers

521

Following

294

Media

1,092

Statuses

Katikapalli Subramanyam Kalyan (shortly Kalyan KS), Research Scientist (NLP) working on Generative AI and LLMs at @AkmmusAI .

India

https://t.co/a7iicZGl6z

Joined November 2016

Don't wanna be here? Send us removal request.

Pinned Tweet

@kalyan_kpl

Kalyan KS

5 months

🎉 I'm happy to share my first book "LLM Prompt Engineering Simplified" 🎉 This book covers all the basic and intermediate-level concepts related to LLM prompt engineering. 🎉 The book is completely free and available online. - Book link: - Github Repo

Tweet media one

1

13

29

Last Seen Profiles

@eyaidnEmas

@EQveu8EVwnlPmH6

@RememberingTour

@marcosJpk16

@Lautaro_Rava21

@RealChalamet

@jandakembangstw

@jandakembangstw

@bruvellu

@stev_uemur

@lilyybunny

@ariessnoir

@besar_pegg

@ry_quella

@ofhaeejin

@Kosuyaki

@anuka_ujin

@imdeebo

@FlwSupport

@c40bn599JB7s07

@MasoudMaani

@jandakembangstw

@HollywoodHandle

@AgapeJMD

@vb7JOxum8B95515

@forget_jpeg

@hibis_legal

@muryk412

@maskandi100

@biblicalflesh

@Bebasindo_com

@chwevenom

@miguemontes9

@yuuu1116ura

@gooniebatie

@qwizzers

@kalyan_kpl

Kalyan KS

7 months

🚀 @huggingface Model Memory Calculator 🚀 ✅ This tool will help you calculate how much GPU RAM is needed to - train a model and - perform big model inference on a model hosted on the Hugging Face Hub. ✅ Currently, this tool supports all models hosted that use transformers

Tweet media one

2

37

174

@kalyan_kpl

Kalyan KS

8 months

@LangChainAI in one picture 🚀LangChain is a framework for developing applications powered by language models. 🚀 This framework consists of several parts. ⚡️LangChain Libraries: The Python and JavaScript libraries. ⚡️LangChain Templates: A collection of easily deployable

Tweet media one

4

33

149

@kalyan_kpl

Kalyan KS

2 years

Comprehensive list of multilingual pretrained language models. @seb_ruder @omarsar0 @rasbt #nlproc #nlp #mBERT

Tweet media one

2

22

110

@kalyan_kpl

Kalyan KS

8 months

🎉I am happy to receive citations from the research papers of @GoogleDeepMind and @Microsoft . 🎉 🏅 Recently, when I checked my Google Scholar Profile, I saw that one of my papers received citations from the papers of two top companies, Google's Deep Mind and Microsoft.

Tweet media one

2

6

96

@kalyan_kpl

Kalyan KS

8 months

🚀 @LangChainAI in action 🚀 LangChain is a framework for developing applications powered by language models. ✅ This framework consists of several parts. ⚡️LangChain Libraries: The Python and JavaScript libraries. ⚡️LangChain Templates: A collection of easily deployable

Tweet media one

2

12

75

@kalyan_kpl

Kalyan KS

7 months

🚀LangChain Templates in Action 🚀 ➡️ LangChain is a framework for developing LLM application. ➡️LangChain templates are pre-defined recipes for generating prompts for LLMs. ➡️LangChain templates include - instructions, - few-shot examples, - specific context - questions

Tweet media one

3

11

69

@kalyan_kpl

Kalyan KS

6 months

🚀 LLaMA Beyond English ✅ This research paper explores the challenge of extending Llama to non-English languages. ☑️The authors conducted an extensive empirical investigation to study various options like - vocabulary expansion, - further pretraining, - instruction tuning.

Tweet media one

2

5

63

@kalyan_kpl

Kalyan KS

5 months

🚀 Airavata - Instruction Tuned Hindi LLM ✅ Airavata - an instruction-tuned model for Hindi built by finetuning OpenHathi LLM. ☑️ OpenHathi is an open-source foundational model for Hindi, developed by extending Llama 2. ✅ OpenHathi was introduced by Sarvam AI, a promising AI

Tweet media one

2

5

27

@kalyan_kpl

Kalyan KS

7 months

@vipul_1011 "High citation count" should never be on the list of criteria for an internship or full-time job.

1

0

23

@kalyan_kpl

Kalyan KS

1 year

Dolly - the new chatbot model based on GPT-J-6B For more details, check #chatbotmodel #opensource #nlproc #nlp #deeplearning

Tweet media one

0

4

15

@kalyan_kpl

Kalyan KS

1 year

@MasterJeongK GPT3, GPT-3.5 and the recent GPT-4 are really good for general domain. However, the performance of these models in specific domains like biomedical is not so great. Apart from this, there is still a lot of room for improvement in many aspects.

2

0

15

@kalyan_kpl

Kalyan KS

1 year

My blog post on "GPT3 for data labeling" is in the top of Google search results. @hashnode is an excellent blogging platform. #gpt3 #openai #nlproc #nlp #deeplearning

Tweet media one

1

1

16

@kalyan_kpl

Kalyan KS

3 years

@DeepLearningAI_

1

3

11

@kalyan_kpl

Kalyan KS

7 months

🚀SQLCoder beats GPT-4 in Text-to-SQL Generation ✅ SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries. ✅ SQLCoder-34B outperforms gpt-4 and gpt-4-turbo for natural language to SQL generation tasks on our sql-eval framework. ✅

Tweet media one

0

0

13

@kalyan_kpl

Kalyan KS

2 years

Recently, one of my papers got 50th citation. #phdlife #phdvoice #academicchatter #academicresearch #phdresearch #phdchatter #researchlife #research

Tweet media one

0

3

13

@kalyan_kpl

Kalyan KS

3 years

#1 AMMUS- A Survey of Transformer-based Pretrained Language Models #nlproc #nlp #bert #survey Paper link:

Tweet media one

3

11

12

@kalyan_kpl

Kalyan KS

9 months

Comprehensive Survey of @OpenAI 's GPT-3 family LLMs. This survey paper with 58 pages, covers more than 350 research papers. Paper link: @omarsar0 @seb_ruder @johnjnay @WilliamWangNLP @_jasonwei @arankomatsuzaki 1/n

Tweet media one

2

3

15

@kalyan_kpl

Kalyan KS

4 years

I'm a third year Ph.D. student working in Clinical Natural Language Processing (social media text). What are the things I have to do apart from publishing papers in reputed conferences and journals, to get postdoc after my Ph.D.? @annargrs @sarkerabeed @seb_ruder @cocoweixu

5

0

13

@kalyan_kpl

Kalyan KS

5 years

NLP Year in Review 2019 #nlproc @seb_ruder

0

5

11

@kalyan_kpl

Kalyan KS

7 months

@partha_p_t [1] Machine Translation related research work done by researchers from @ai4bharat . For example, "IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages"

1

0

12

@kalyan_kpl

Kalyan KS

6 months

🚀 How Code Empowers LLMs to Serve as Intelligent Agents (Survey) ✅ The survey paper discusses the integration of code into large language models (LLMs) and its impact. ☑️ It highlights that modern LLMs are not only larger but also trained on a mix of natural language and

Tweet media one

1

1

11

@kalyan_kpl

Kalyan KS

2 years

@seekcommand No one laughed because they were not attentive.

1

0

11

@kalyan_kpl

Kalyan KS

4 years

@D2L_ai Well written book. I wish the book should have used PyTorch deep learning framework.

0

0

9

@kalyan_kpl

Kalyan KS

1 year

LaMini-LM : collection of small-sized, efficient language models with performances comparable to Alpaca-7B model Paper link: #llms #nlproc #chatgpt #openai #gpt4 #gpt3

Tweet media one

0

7

9

@kalyan_kpl

Kalyan KS

2 years

Yes, its true. #nlproc #nlp #datascience #research #phdresearch #ai #aimemes #memes

Tweet media one

0

3

8

@kalyan_kpl

Kalyan KS

6 months

🚀 Extend Llama without Catastrophic forgetting ❌ Drawbacks ❌ ❗️Catastrophic forgetting - When trained on new data, existing knowledge degrades significantly ("forgetting"). This is evident in the LLaMA family - LLaMA to CodeLLaMA. ✅ Proposed Solution 🔅 The authors

Tweet media one

1

1

8

@kalyan_kpl

Kalyan KS

6 months

🚀 Cheetah - Multilingual LLM for 517 African Languages The paper introduces Cheetah, a multilingual NLG model for African languages addressing low-resource challenges. Cheetah supports 517 African languages, outperforming other models in five out of seven generation tasks.

Tweet media one

0

0

7

@kalyan_kpl

Kalyan KS

4 years

@omarsar0 Thanks for providing about many useful courses. I would like to add this course also (Special Topics in DL) @omarsar0

0

0

5

@kalyan_kpl

Kalyan KS

4 years

@A_K_Nain survey paper on GNNs

1

2

6

@kalyan_kpl

Kalyan KS

6 months

LLMs for Information Extraction (Survey) ✅ Information Extraction (IE) focuses on extracting structural knowledge, such as entities, relations, and events, from natural language texts. ✅ This survey paper explores the recent trend of utilizing generative Large Language Models

Tweet media one

0

1

7

@kalyan_kpl

Kalyan KS

8 months

DALL-E 3 follow text prompts better than DALL-E 2 ➡️ For a detailed explanation, refer to the video tutorial. ➡️ Video tutorial link: 🎯Excellent video tutorial by @AICoffeeBreak #dalle3art #dalle2 #openai #text2image #GenerativeAI

Tweet card media

DALL-E 3 is better at following Text Prompts! Here is why. — DALL-E 3...

Synthetic captions help DALL-E 3 follow text prompts better than DALL-E 2. We explain how OpenAI innovates the training of diffusion models with better image...

www.youtube.com

0

2

7

@kalyan_kpl

Kalyan KS

7 months

🚀 Excellent demo of Online LLMs ➡️ Recently @perplexity_ai introduced Online LLMs, the first of its kind. ➡️ Drawbacks of existing LLMs - Freshness: LLMs often struggle to share up-to-date information. - Hallucinations: LLMs can also output inaccurate statements. ➡️

Tweet media one

0

0

6

@kalyan_kpl

Kalyan KS

7 months

@cenyk1230 @subhobrata1 Interesting work.

0

0

5

@kalyan_kpl

Kalyan KS

6 months

⚡️ OpenAI GPT Store Set to Launch Next Week OpenAI plans to launch a store for GPTs, custom apps based on its text-generating AI models (e.g. GPT-4) The GPT Store was announced last year during OpenAI’s first annual developer conference, DevDay. GPTs don’t require coding

Tweet media one

1

1

5

@kalyan_kpl

Kalyan KS

8 months

@SharonYixuanLi The main reason for this race is the commercial benefits of these large language models. -> 2013 - word2vec, 2014-Glove, 2017- FastText (slow and steady progress)

0

0

5

@kalyan_kpl

Kalyan KS

7 months

🚀 MedLM - a family of foundation models fine-tuned for the healthcare industry ✅ MedLM models are built on the top of MedPaLM-2. ✅ There are two models under MedLM. ➡️ The first MedLM model is larger, designed for complex tasks. ➡️ The second is a medium model, able to be

Tweet media one

0

0

6

@kalyan_kpl

Kalyan KS

6 months

The rise of multiple open-source LLMs like Llama2, Falcon, @llm360 , Mistral etc. supports @ylecun claims. Many of these open-source LLMs already outperformed the proprietary GPT-3.5 model on multiple benchmarks. 2024 will surely witness more advanced open-source LLMs which may

Tweet media one

0

1

6

@kalyan_kpl

Kalyan KS

1 year

Koala - new chatbot model approaching ChatGPT quality. Koala is initialized from LLaMA-13B and then trained over dialogue data scraped from the web and public datasets Link:

Tweet media one

0

0

6

@kalyan_kpl

Kalyan KS

6 months

LLM Life Cycle LLM Life Cycle involves four important stages - Data Collection - Pretraining - Meta Training (instruction tuning or RLHF) - Model Serving Picture Credit: "Training and Serving System of Foundation Models: A Comprehensive Survey" #llms #opensource #generativeai

Tweet media one

1

0

5

@kalyan_kpl

Kalyan KS

4 years

Biomedical Language Understanding and Reasoning Benchmark. #NLProc #bionlp @BioNLProc Paper link:

Tweet card media

Domain-Specific Language Model Pretraining for Biomedical Natural...

Pretraining large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. However, most pretraining efforts focus on general domain...

0

0

5

@kalyan_kpl

Kalyan KS

7 months

🚀LLM API Pricing Calculator 🚀 ✅Large language models are powerful artificial intelligence systems that have the ability to analyze and generate human-like text. ✅LLMs gained a lot of popularity with the release of models like ChatGPT and GPT-4. ✅As these models are

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

7 months

♨️ Build with Gemini (Pro and Pro Vision) 1️⃣ The first version of Gemini Pro and Gemini Pro Vision are now accessible via the Gemini API. 2️⃣ Gemini API comes with a range of features - function calling, - embeddings, - semantic retrieval - custom knowledge grounding, - chat

1

1

3

@kalyan_kpl

Kalyan KS

3 years

Comprehensive list of benchmarks in NLP #nlproc #nlp #biomedicalnlp #clinicalnlp @omarsar0 @seb_ruder @philipvollet @nlpnoah @allen_ai Link:

Tweet media one

1

1

5

@kalyan_kpl

Kalyan KS

6 months

Google Gemini to Open AI Q* Survey This survey paper covers - evolving landscape of generative AI, with a focus on MoE, multimodal learning, and AGI. - impact of innovations like Google's Gemini and OpenAI's Q* project on research and applications. - computational challenges,

Tweet media one

0

1

5

@kalyan_kpl

Kalyan KS

6 months

@Sentdex It's absolutely fine to promote a good book. @Sentdex

0

0

4

@kalyan_kpl

Kalyan KS

1 year

BloombergGPT - 50B parameter language model for Finance domain. - Mixed dataset training leads to good performance on finance tasks without sacrificing performance on general NLP tasks. @business @TechAtBloomberg - Paper link:

Tweet media one

0

0

5

@kalyan_kpl

Kalyan KS

5 months

🚀 Finance with LLMs: An Overview of Applications and Insights 1️⃣ LLMs like GPT-4 are becoming increasingly advanced and versatile. 2️⃣ LLMs are useful for various tasks in the financial sector like: - Automating report generation. - Forecasting market trends. - Analyzing

Tweet media one

0

2

5

@kalyan_kpl

Kalyan KS

3 years

@philipvollet This is a comprehensive survey paper on pretrained NLP models. Please share it in twitter so that it will reach more people.

0

2

5

@kalyan_kpl

Kalyan KS

6 months

🚀 RAG Survey Retrieval Augmented Generation (RAG) refers to the retrieval of relevant information from external knowledge bases before answering questions with LLMs. ❌ Challenges of LLMs: - Hallucinations (generating inaccurate information) - Slow knowledge updates - Lack

Tweet media one

0

1

4

@kalyan_kpl

Kalyan KS

2 years

TweetNLP - Cutting-Edge NLP library (9 tasks) for Social Media. Library: Good work from @Cardiff_NLP people in creating this library. For NLP transformers survey, refer #nlproc #nlp

1

4

4

@kalyan_kpl

Kalyan KS

5 months

🚀 Code Llama-70B (the latest Coding LLM from MetaAI) ✔️ Recently, MetaAI released Code Llama-70B, the largest model in the CodeLlama family. 🟦 This Code LLM is initialized from Llama 2 and then trained on large volumes of code data. ✔️ Code Llama-70B is available on Hugging

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

8 months

Satya Nadella, in his early days at Microsoft as Technical Marketing Manager ✔️Satya Nadella joined Microsoft in the early 1990's and then stayed in the same company. ✔️Satya Nadella quickly rose through the ranks at Microsoft and held leadership roles in both enterprise and

0

0

4

@kalyan_kpl

Kalyan KS

5 months

🎀 @PyTorch Deep Learning ✅ This playlist covers the following - Pytorch Deep Learning Series - Introduction - PyTorch Deep Learning, Section 2: Deep Dive into Basics (Part 1) - PyTorch Deep Learning, Section 2: Building Strong Foundations (Part 2) - PyTorch Deep Learning,

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

8 months

9th Workshop on Noisy and User-generated Text (W-NUT) @eaclmeeting 2024 ✅ If you are working on problems at the intersection of NLP and Social media, the WNUT workshop (organized along with EACL 2024) is a good venue to submit your research paper. ✅ WNUT workshop is

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

8 months

Sam Altman is No Longer the CEO of @OpenAI 📍 It's a big surprise that Sam Altman is sacked as the CEO of OpenAI. 📍This happened just a few days after OpenAI DevDay, where he revealed the plans for a more advanced model, GPT-5. 📍 Undoubtedly, Sam Altman contributed a lot

Tweet media one

0

2

4

@kalyan_kpl

Kalyan KS

2 years

Comprehensive list of Generative Pretrained Language Models Link: #nlproc #nlp #NAACL2022 #GPT3 #BLOOM

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

8 months

Scale-LLM Workshop 2024 ✅Workshop on the Scaling Behavior of Large Language Models (Scale-LLM Workshop @eaclmeeting 2024) ✅The workshop will provide focused discussions on multiple topics in the general field of Scaling behavior of Large Language Models. ✅ Scale-LLM

Tweet media one

0

1

4

@kalyan_kpl

Kalyan KS

2 years

@_willfalcon @PyTorchLightnin Huggingface Transformers library

0

0

4

@kalyan_kpl

Kalyan KS

5 months

🚀 DeepSeek-Coder - Open Source Code LLMs DeepSeek-Coder - Family of open-source code models with sizes from 1.3B to 33B. ☑️ These LLMs are pretrained from scratch on 2 trillion tokens. ☑️ DeepSeek-Coder outperforms closed-source LLMs like Codex and GPT-3.5. ✅ These models

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

1 year

PMC-LLaMA : LLaMA model for biomedical domain PMC-LLaMA achieves good results on biomedical QA datasets. Paper: Model:

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

1 year

GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo Github repository: #nlproc #nlp #chatbot #openai #gpt3

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

7 months

PEFT Methods (LoRA, QLoRA) Survey LLMs with billions of parameters have been successful in NLP tasks. Parameter Efficient Fine-Tuning (PEFT) reduces fine-tuning parameters and memory usage while maintaining performance. This survey paper reviews PEFT methods, discusses

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

3 years

@SwiggyCares @zinqshere MRP means Maximum Retail Price which is inclusive of all the taxes. Then how can you add taxes beyond MRP? Can you please clarify?

2

1

3

@kalyan_kpl

Kalyan KS

2 years

"AMMU: A survey of transformer-based biomedical pretrained language models". Final Accepted Version (can be accessed freely)

1

1

3

@kalyan_kpl

Kalyan KS

2 years

My survey paper on pretrained language models received 50 citations. #nlproc #nlp #phdvoice #phdresearch #academicchatter #phdlife #phd

Tweet media one

0

0

3

@kalyan_kpl

Kalyan KS

4 years

Solving NLP Problems with BERT #NLProc

0

0

3

@kalyan_kpl

Kalyan KS

6 months

🚀 Build Gemini Chatbot using Streamlit ✅ Gemini is the latest and advanced Chatbot LLM introduced by Google AI. ☑️ Streamlit is a Python library to create ML and chatbot apps in just a few lines of codes. ✅ Build Gemini Chatbot using Streamlit involves the following steps

Tweet media one

0

0

3

@kalyan_kpl

Kalyan KS

2 years

GPT3 for data labeling Link: #GPT3 #ChatGPT #datalabeling #nlproc #nlp #ai #datascience

Tweet media one

0

3

3

@kalyan_kpl

Kalyan KS

2 years

Apps similar to ChatGPT are @WriteSonic @perplexity_ai For detailed information, check #chatGPT #openai #chatsonic #perlexityai

Tweet media one

1

0

3

@kalyan_kpl

Kalyan KS

7 months

State of LLM Apps 2023 (by @streamlit ) Key takeaways - OpenAI is dominant (73% use GPT models) - The future is multi-agent (56% use orchestration) - Most apps bypass vector magic (Only 19% use vector retrieval) - Chatbots are on the rise (25% and growing are chatbots) State of

Tweet media one

0

0

4

@kalyan_kpl

Kalyan KS

6 months

Vanna - Chat with your SQL Database Vanna is an open-source Python library that allows you to generate SQL queries from natural language questions. It uses a Retrieval-Augmented Generation (RAG) framework to train a model on your data and then answer your questions. Vanna is

Tweet media one

0

1

3

@kalyan_kpl

Kalyan KS

7 months

🚀 LLMLingua - LLM Prompt Compressor ❌ Drawbacks with length prompts ❌ 1️⃣ Large language models (LLMs) have demonstrated remarkable capabilities. 2️⃣ Advancements techniques such as Chain-of-Thought (CoT), In-Context Learning (ICL), and Retrieval-Augmented Generation (RAG)

Tweet media one

1

1

3

@kalyan_kpl

Kalyan KS

6 months

⚡️ DeepSeek LLM - New Open Source LLM (outperforms GPT-3.5) ❌ Existing research on scaling LLMs presents contradictory findings, making further scaling unclear. ✅ This paper proposes - new scaling laws - introduces DeepSeek LLM, a new open-source LLM open-source language

Tweet media one

0

0

3

@kalyan_kpl

Kalyan KS

1 year

PandasAI is a Python library that adds Generative AI capabilities to the pandas library. - PandasAI uses @OpenAI models. - PandasAI tutorial: - PandasAI library:

Tweet media one

0

2

3

@kalyan_kpl

Kalyan KS

4 years

@omarsar0 SECNLP: A survey of embeddings in clinical natural language processing

0

1

3

@kalyan_kpl

Kalyan KS

8 months

@vishalcseiitg @GoogleDeepMind @Microsoft Same to you.

0

0

1

@kalyan_kpl

Kalyan KS

7 months

♨️ PromptBench: A Library for Evaluation of Large Language Models ➡️ PromptBench is a unified library for evaluating large language models (LLMs). ➡️ Provides several key components for easy use and extension: - Prompt construction - Prompt engineering (e.g., few-shot,

Tweet media one

0

2

3

@kalyan_kpl

Kalyan KS

7 months

🚀Fabricator - LLM Library for Labelled Data Generation ✔️ Most NLP tasks are modelled as supervised learning and thus require labelled training data to train effective models. ✔️ However, data labelling is an expensive, laborious and time-intensive process. ✔️FABRICATOR is an

Tweet media one

0

1

3

@kalyan_kpl

Kalyan KS

6 months

@YiFung10 Well-written survey paper on an interesting topic.

0

0

1

@kalyan_kpl

Kalyan KS

5 months

🚀 Knowledge Fusion Of LLMs Training LLMs from scratch is inefficient and expensive. Merging existing models is a compelling and cost-effective alternative. However, direct weight blending is impractical due to varied architectures. This paper proposes a novel approach called

Tweet media one

0

1

4

@kalyan_kpl

Kalyan KS

2 years

@YassineAlouini @omarsar0 You can use PyTorch lightning instead of PyTorch for multi-GPU training.

1

0

3

@kalyan_kpl

Kalyan KS

7 months

♨️ Retrieval-Augmented Generation (RAG) Survey RAG is a technique that combines large language models (LLMs) with external knowledge bases to improve answer accuracy and reduce model hallucinations, particularly for knowledge-intensive tasks. ☑️ RAG achieves this by: -

Tweet media one

0

0

3

@kalyan_kpl

Kalyan KS

5 years

A comprehensive survey of embeddings in clinical natural language processing #NLProc

0

1

3

@kalyan_kpl

Kalyan KS

6 months

🚀 TEXTMACHINA - Seamless Generation of Machine-Generated Text Datasets ❌ Challenges - Easy access to powerful Large Language Models (LLMs) leads to misuse and the need for robust detection/attribution tools. ❎ Existing solution - Datasets for training MGT-related models,

Tweet media one

0

1

3

@kalyan_kpl

Kalyan KS

6 months

💡 Large Language Models and The End of Programming ✅ Dr. Matt Welsh discusses the impact of AI models like ChatGPT on the future of computer science and programming. ☑️ He presents the argument that LLMs could fundamentally change how we build software, potentially leading to

Tweet media one

0

0

3

@kalyan_kpl

Kalyan KS

8 months

Prompting Framework" (PF) is the framework for managing, simplifying, and facilitating interaction with large language models (LLMs). ✅ Prompting Framework is the upper layer which enables LLMs to interact with the external world. ✅ Some of the popular LLM prompting

Tweet media one

0

0

2

@kalyan_kpl

Kalyan KS

3 years

@srchvrs Thanks for sharing my survey paper.

0

0

3

@kalyan_kpl

Kalyan KS

9 months

@dair_ai I'm really surprised that you have missed a top-class survey paper on GPT-3 family LLMs, which covers more than 350 papers. Paper link:

Tweet media one

0

0

3

@kalyan_kpl

Kalyan KS

6 months

🚀 @OpenAI GPT Store ✅ GPTs are custom versions of ChatGPT. ☑️ Over 3M GPTs have been created. ✅ GPT Store - find useful and popular custom versions of ChatGPT. ☑️ Key Points - Discover custom ChatGPT models created by OpenAI and the community. - Explore various

Tweet media one

0

1

3

@kalyan_kpl

Kalyan KS

4 years

Building tools and frameworks for large-scale social media mining (by Dr. Juan M. Banda) @drjmbanda @ramyatekumalla #NLProc

Tweet card media

Building tools and frameworks for large-scale social media mining (by...

◾ Title: Building tools and frameworks for large-scale social media mining: Creating data infrastructure for COVID-19 research.Slides: https://www.dropbox.co...

www.youtube.com

0

0

2

@kalyan_kpl

Kalyan KS

3 years

@labmlai @karpathy Nice work. You can add options to filter papers related to specific area like NLP/ CV etc...

0

0

2

@kalyan_kpl

Kalyan KS

3 years

LightSeq, a highly efficient inference library for models in the Transformer family. LightSeq has better inference speeds compared to @huggingface #nlproc #nlp @BytedanceTalk

Tweet card media

GitHub - bytedance/lightseq: LightSeq: A High Performance Library for Sequence Processing and...

LightSeq: A High Performance Library for Sequence Processing and Generation - bytedance/lightseq

0

1

2

@kalyan_kpl

Kalyan KS

4 years

Is the anonymity period applicable to workshop papers also? or Is it applicable only to main conference papers? @emnlp2020 @annargrs

1

0

2

@kalyan_kpl

Kalyan KS

9 months

@chenxi_jw @AlhamFikri @monojitchou Check out my survey paper (Section 7), which covers LLM-powered in detail. Paper link:

Tweet media one

1

0

2

@kalyan_kpl

Kalyan KS

6 months

LangServe - Deploy LangChain Apps This video provides a step-by-step guide on how to deploy LangChain applications to (i) Google Cloud and (ii) LangServe hosted deployments. Video tutorial: #langchain #llms #generativeai #nlproc #deeplearning

Tweet media one

0

0

2

@kalyan_kpl

Kalyan KS

3 years

@mrm8488 @huggingface Good work. If you provide some details regarding model training in model card, it will be useful for others also.

1

0

2

@kalyan_kpl

Kalyan KS

2 years

ferret - A python package for benchmarking interpretability techniques for NLP Link: @hima_lakkaraju #nlproc #nlp #xai

Tweet media one

0

0

2

@kalyan_kpl

Kalyan KS

4 years

@AACL_SRW I want to register for AACL-IJCNLP conference. Is paper id and submission number are same?

1

0

2

@kalyan_kpl

Kalyan KS

4 years

Comprehensive survey on embeddings in clinical nlp @UK_healtex

0

0

2

@kalyan_kpl

Kalyan KS

4 years

#NLProc

@AACL_SRW

AACL SRW

4 years

Our 2nd Call for Papers is out! Submission deadline: September 25, Anywhere on Earth (🌎,🌍 and🌏) For more details:

Tweet media one

0

3

7

0

1

2