lixsh6

LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

InfiniteBench

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

regmix

🧬 RegMix: Data Mixture as Regression for Language Model Pre-training

RAGChecker

RAGChecker: A Fine-grained Framework For Diagnosing RAG

LASP

Linear Attention Sequence Parallelism (LASP)

Husky-v1

Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and knowledge-based reasoning tasks.

VideoLLaMA2

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

ms-swift

Use PEFT or Full-parameter to finetune 300+ LLMs or 60+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

Megatron-Kwai

[USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Parallelism

ring-flash-attention

Ring attention implementation with flash attention

hh-rlhf

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Qwen-VL

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

MedicalGPT

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

claude-prompt-generator

UltraFeedback

A large-scale, fine-grained, diverse preference dataset (and models).

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

pipecat

Open Source framework for voice and multimodal conversational AI

ChatTTS

A generative speech model for daily dialogue.

LooGLE

ACL 2024 | LooGLE: Long Context Evaluation for Long-Context Language Models

long-context-attention

Sequence Parallel Attention for Long Context LLM Model Training and Inference

awesome-multi-modal-reinforcement-learning

A curated list of Multi-Modal Reinforcement Learning resources (continually updated)

ComplexBench

ChatEval

Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"

llm-autoeval

Automatically evaluate your LLMs in Google Colab

suri

Code for Suri: Multi-constraint instruction following for long-form text generation

Loong

[arxiv:2406.17419]Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA

persona-hub

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

AutoIF

MACM

MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems