SivilTaram

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

dspy

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

surya

OCR, layout analysis, reading order, line detection in 90+ languages

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

mergekit

Tools for merging pretrained large language models.

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.

InternLM-XComposer

InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) excelling in free-form text-image composition and comprehension.

starcoder2

Home of StarCoder2!

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

nanotron

Minimalistic large language model 3D-parallelism training

DeepSeek-Math

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

SeeAct

[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).

gritlm

Generative Representational Instruction Tuning

zero-bubble-pipeline-parallelism

Zero Bubble Pipeline Parallelism

AgentBoard

An Analytical Evaluation Board of Multi-turn LLM Agents

LongMamba

Some preliminary explorations of Mamba's context scaling.

visualwebarena

VisualWebArena is a benchmark for multimodal agents.

sewformer

gated_linear_attention

sailor-llm

Sailor: Open Language Models for South-East Asia

Agent-Smith

[ICML2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

astraios

Astraios: Parameter-Efficient Instruction Tuning Code Language Models

weak-to-strong

Weak-to-Strong Jailbreaking on Large Language Models

autofd

Automatic Functional Differentiation in JAX

arks

AnyDoor

AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models

youtube_subtitle_dataset

YT_subtitles - extracts subtitles from YouTube videos to raw text for Language Model training

SciTab

The project page for "SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables"

thaimaimee

Scrape, clean and explore ThaiME dataset

Bridge_for_Numerical_Reasoning