Starred repositories
📖 A curated list of resources dedicated to Natural Language Processing (NLP)
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
slime is an LLM post-training framework for RL Scaling.
Breakthrough Method for Agile Ai Driven Development
An extension that can help you to prepare for a Company specific interview
A curated list of awesome places to learn and/or practice algorithms.
On the Theoretical Limitations of Embedding-Based Retrieval
📑 PageIndex: Document Index for Reasoning-based RAG
SearchGPT / Perplexity clone, but personalised for you.
This repository contains a curated collection of 300+ case studies from over 80 companies, detailing practical applications and insights into machine learning (ML) system design. The contents are o…
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
Lists of company wise questions available on leetcode premium. Every csv file in the companies directory corresponds to a list of questions on leetcode for a specific company based on the leetcode …
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Multilingual Document Layout Parsing in a Single Vision-Language Model
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Agentic Web: Weaving the Next Web with AI Agents.
A framework for serving and evaluating LLM routers - save LLM costs without compromising quality
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
Kimi K2 is the large language model series developed by Moonshot AI team
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
Supercharge Your LLM with the Fastest KV Cache Layer
Inspect: A framework for large language model evaluations
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.