tzu-yen

arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

llm-decontaminator

Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

WizardLM-2-8x22B

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

EgoVLPv2

Code release for "EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone" [ICCV, 2023]

LaViLa

Code release for "Learning Video Representations from Large Language Models"

MovieChat

[CVPR 2024] 🎬💭 chat with over 10K frames of video!

awesome-llm-human-preference-datasets

A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.

Awesome-Code-LLM

A curated list of language modeling researches for code and related datasets.

orpo

Official repository for ORPO

Video-LLaVA

PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models

Awesome-LLMs-for-Video-Understanding

🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

trl

Train transformer language models with reinforcement learning.

notus

Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach

starcoder

Home of StarCoder: fine-tuning & inference!

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

codealpaca

dspy

DSPy: The framework for programming—not prompting—foundation models

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

text-generation-inference

Large Language Model Text Generation Inference

Megatron-LM

Ongoing research training transformer models at scale

TimeSformer

The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

open_clip

An open source implementation of CLIP.