TissueC

PaperMemory

Your browser's reference manager: automatic paper detection (Arxiv, OpenReview & more), publication venue matching and code repository discovery! Also enhances ArXiv: BibTex citation, Markdown link, direct download and more!

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

MAP-NEO

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

elasticsearch

Free and Open, Distributed, RESTful Search Engine

LLM-Extrapolation

Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"

DeepSeek-VL

DeepSeek-VL: Towards Real-World Vision-Language Understanding

mup

maximal update parametrization (µP)

fm-cheatsheet

Website for hosting the Open Foundation Models Cheat Sheet.

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

outlines

Structured Text Generation

OLMo

Modeling, training, eval, and inference code for OLMo

MiniCPM

MiniCPM-2B: An end-side LLM outperforming Llama2-13B.

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

InfoBench

DeepSeek-MoE

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

COIG-CQIA

FollowBench

Code for "FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models (ACL 2024)"

Pai-Megatron-Patch

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

CritiqueLLM

mergekit

Tools for merging pretrained large language models.

Yuan-2.0

Yuan 2.0 Large Language Model

tensor_parallel

Automatically split your PyTorch models on multiple GPUs for training & inference

BPO

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

LongQLoRA

LongQLoRA: Extent Context Length of LLMs Efficiently

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

Yi

A series of large language models trained from scratch by developers @01-ai

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

FasterTransformer

Transformer related optimization, including BERT, GPT