eshoyuan

GLM-4

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

mlx

MLX: An array framework for Apple silicon

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

Awesome-LLM-Inference

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

bolna

End-to-end platform for building voice first multimodal agents

awesome-llm-role-playing-with-persona

Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas

pipecat

Open Source framework for voice and multimodal conversational AI

Yi-1.5

Yi-1.5 is an upgraded version of Yi, delivering stronger performance in coding, math, reasoning, and instruction-following capability.

trl

Train transformer language models with reinforcement learning.

llama3-Chinese-chat

Llama3 中文仓库（聚合资料，各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

axolotl

Go ahead and axolotl questions

SpeculativeDecodingPapers

📰 Must-read papers and blogs on Speculative Decoding ⚡️

llama3

The official Meta Llama 3 GitHub site

Ouroboros

Ouroboros: Speculative Decoding with Large Model Enhanced Drafting

TriForce

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

torchtune

A Native-PyTorch Library for LLM Fine-tuning

cog

Containers for machine learning

insanely-fast-whisper

reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

wordcab-transcribe

💬 ASR FastAPI server using faster-whisper and Multi-Scale Auto-Tuning Spectral Clustering for diarization.

WhisperLive

A nearly-live implementation of OpenAI's Whisper.

spring2024-lectures

Ice

Powerful menu bar manager for macOS

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.

kubeflow

Machine Learning Toolkit for Kubernetes

RecommenderSystem

SearchEngine

搜索引擎原理

Qwen2

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

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.

SWE-bench

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?