xyangk

xyangk's Stars

• meta-llama/llama-recipes

  Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

  Language:Jupyter Notebook11.6k1.6k

• 01-ai/Yi-1.5

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

  48327

• yaoxieyoulei/mytv-android

  使用Android原生开发的电视直播软件

  Language:Kotlin3.6k302

• casper-hansen/AutoAWQ

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

  Language:Python1.6k191

• OpenBMB/MiniCPM-V

  MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

  Language:Python11.8k834

• naklecha/llama3-from-scratch

  llama3 implementation one matrix multiplication at a time

  Language:Jupyter Notebook13.1k1k

• NousResearch/Hermes-Function-Calling

  Language:Jupyter Notebook63485

• cognitivecomputations/OpenChatML

  14410

• MinorJerry/WebVoyager

  Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"

  Language:Python23328

• ddupont808/GPT-4V-Act

  AI agent using GPT-4V(ision) capable of using a mouse/keyboard to interact with web UI

  Language:JavaScript95186

• web-arena-x/visualwebarena

  VisualWebArena is a benchmark for multimodal agents.

  Language:Python21137

• nlpxucan/WizardLM

  LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

  Language:Python9.2k713

• OFA-Sys/Chinese-CLIP

  Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

  Language:Python4.3k449

• karpathy/llm.c

  LLM training in simple, raw C/CUDA

  Language:Cuda23.3k2.6k

• karpathy/minbpe

  Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

  Language:Python9k830

• OpenBMB/MiniCPM

  MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

  Language:Python6.7k432

• shuxueslpi/chatGLM-6B-QLoRA

  使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。

  Language:Python34946

• ossu/computer-science

  🎓 Path to a free self-taught education in Computer Science!

  168k21.3k

• NVIDIA/Megatron-LM

  Ongoing research training transformer models at scale

  Language:Python9.9k2.2k

• NascentCore/llm-numbers-cn

  中文版 llm-numbers

  944

• OSU-NLP-Group/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).

  Language:Python58772

• triton-inference-server/tutorials

  This repository contains tutorials and examples for Triton Inference Server

  Language:Python52490

• NVIDIA/TensorRT-LLM

  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++8.2k905

• vllm-project/vllm

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

  Language:Python26.7k3.9k

• haotian-liu/LLaVA

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

  Language:Python19.3k2.1k

• Instruction-Tuning-with-GPT-4/GPT-4-LLM

  Instruction Tuning with GPT-4

  Language:HTML4.2k299

• mit-han-lab/llm-awq

  [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

  Language:Python2.3k177

• hiyouga/LLaMA-Factory

  Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

  Language:Python30.8k3.8k

• deepseek-ai/DeepSeek-Coder

  DeepSeek Coder: Let the Code Write Itself

  Language:Python6.5k460

• bitsandbytes-foundation/bitsandbytes

  Accessible large language models via k-bit quantization for PyTorch.

  Language:Python6k606