Name: DUSHYANT CHAUHAN
Type: User
Company: Indian Institute of Technology Patna
Bio: AI, NLP, CV, Conversational AI Chatbots, Interpretability and Explainability, Interactive code generation, MLLMs, Cognitive AI Systems, Robotics.
Twitter: GussailRaat
Location: Patna, Bihar, India
DUSHYANT CHAUHAN's Projects
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
Sentiment and Emotion help Sarcasm? A Multi-task Learning Framework for Multi-Modal Sarcasm, Sentiment and Emotion Analysis
A Deep Multi-task Contextual Attention Framework for Multi-modal Affect Analysis
33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
We develop benchmarks and analysis tools to evaluate the causal reasoning abilities of LLMs.
Inference code for CodeLlama models
Course scheduling of a Taiwanese elementary school with 994 courses, 66 teachers and 49 rooms
DeepSeek Coder: Let the Code Write Itself
DeepSeek LLM: Let there be answers
Easy Steps to write Devanagari (Hindi) Language in pdfLatex
Contextual Inter-modal Attention for Multi-modal Sentiment Analysis
Context-aware-Interactive-Attention-for-Multi-modal-Sentiment-and Emotion-Analysis
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
LangChain & Prompt Engineering tutorials on Large Language Models (LLMs) such as ChatGPT with custom data. Jupyter notebooks on loading and indexing data, creating prompt templates, CSV agents, and using retrieval QA chains to query the custom data. Projects for using a private LLM (Llama 2) for chat with PDF files, tweets sentiment analysis.
Code for the paper "Evaluating Large Language Models Trained on Code"
This repository contains the dataset and baselines explained in the paper: M2H2: A Multimodal Multiparty Hindi Dataset For HumorRecognition in Conversations
Multi-task Gated Contextual Cross-Modal Attention Framework for Sentiment and Emotion Analysis
InstructionGPT-4
🦜🔗 Build context-aware reasoning applications
A set of LangChain Tutorials from my youtube channel
Large Language Models: A large language model (LLM) is a specialized type of artificial intelligence (AI) that has been trained on vast amounts of text to understand existing content and generate original content.
Latte: Latent Diffusion Transformer for Video Generation.
LAVIS - A One-stop Library for Language-Vision Intelligence
🔗 LINC: Logical Inference via Neurosymbolic Computation [EMNLP2023]
Inference code for LLaMA models
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Examples and recipes for Llama 2 model