A library for mechanistic interpretability of GPT-style language models

🦜💯 Flex those feathers!

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite with each task costs less than $0.7.

Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and representation of player Elo.

Repository for G-Retriever

Go ahead and axolotl questions

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Template job submissions using GPUs in CHTC

You like pytorch? You like micrograd? You love tinygrad! ❤️

This is a repository containing the list of company wise questions available on leetcode premium. Every pdf file in this repository corresponds to a list of questions on leetcode for a specific com…

The codebase for our ACL2023 paper: Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning

Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE benchmark with subquadratic complexity in length (or without…

Editing Models with Task Arithmetic

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry lead…

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

LLM as a Chatbot Service

Transformers at any scale

[ACL 2023] Few-shot Reranking for Multi-hop QA via Language Model Prompting

Build, evaluate, understand, and fix LLM-based apps

ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate

Translation models for 22 scheduled languages of India

General technology for enabling AI capabilities w/ LLMs and MLLMs

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

A (somewhat) minimal library for finetuning language models with PPO on human feedback.

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

EMNLP 2022: Generating Natural Language Proofs with Verifier-Guided Search https://arxiv.org/abs/2205.12443

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.