ayulockin.github.io Public

Personal website of Ayush Thakur

terminal-bench Public

A benchmark for LLMs on complicated tasks in the terminal

fastapi-chroma Public

Simple FastAPI server on top of ChromaDB

litellm Public

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

verifiers Public

Verifiers for LLM Reinforcement Learning

assignment1-basics Public

Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch

llama_index Public

LlamaIndex (GPT Index) is a data framework for your LLM applications

AIQToolkit Public

The NVIDIA Agent Intelligence Toolkit (AIQ Toolkit) is an open-source library for efficiently connecting and optimizing teams of AI agents.

ART Public

Agent Reinforcement Trainer for training multi-turn agents using GRPO

trl Public

Train transformer language models with reinforcement learning.

neurathon-finals Public

crewAI Public

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

ayulockin Public

Pawan Kumar Portfolio

llm_scratch Public

Exploring LLMs by implementing and understanding all the key components, perform experiments and optimize it.

workshops Public

Educational material for workshops

swe-agent Public

A simple SWE Agent for the SWE Benchmark

scratchpads Public

Random stuffs

SimpleBench Public

ragas Public

Supercharge Your LLM Application Evaluations

guardrails-genie Public

Guardrails-Genie is a tool that helps you implement guardrails in your LLM applications.

helm Public

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image ...

rpg-llm Public

A framework to play Divinity Original Sin 2

guardrails Public

Adding guardrails to large language models.

inspect_ai Public

Inspect: A framework for large language model evaluations

manim_projects Public

Fun manim based animations.

isic-24 Public

debugNNwithWandB Public

Concepts Explored in/with Pytorch

MixEval Public

The official evaluation suite and dynamic data release for MixEval.

llm_judge_llamaindex Public

Demo repository for llamaindex webinar (10/07/24)

automated-essay-scoring Public

For a Kaggle competition: Learning Agency Lab - Automated Essay Scoring 2.0