Pinned Repositories
100-Days-Of-ML-Code
100 Days of ML Coding
Amazon-Intern-Questions
Most frequent questions for Amazon Internship
Artificial-Intelligence-Terminology
The English-Chinese paired terminologies in Artificial Intelligence Domain
attention-gym
Helpful tools and examples for working with flex-attention
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
LLM_Paper_Reading
This repo lists some interesting LLM related papers.
Research-Project-Title-Embedding
This project aims to improve the quality eBay product title embedding. Here are the slides and my master thesis. The source code is in company's repo and not able to release now.
Semantic-Differentials-for-Wikipedia-using-the-POLAR-Framework
RWTH ForschungPraktikum CSSH
LLM-paper
Biu
ichbinhandsome's Repositories
ichbinhandsome/attention-gym
Helpful tools and examples for working with flex-attention
ichbinhandsome/Research-Project-Title-Embedding
This project aims to improve the quality eBay product title embedding. Here are the slides and my master thesis. The source code is in company's repo and not able to release now.
ichbinhandsome/bilibot
A local chatbot fine-tuned by bilibili user comments.
ichbinhandsome/CodeAdvent2024
Advent of Code 2024
ichbinhandsome/composer
Supercharge Your Model Training
ichbinhandsome/dbrx
Code examples and resources for DBRX, a large language model developed by Databricks
ichbinhandsome/EffectiveModernCppChinese
《Effective Modern C++》- 完成翻译
ichbinhandsome/fms-fsdp
Demonstrate throughput of PyTorch FSDP
ichbinhandsome/gemma.cpp
lightweight, standalone C++ inference engine for Google's Gemma models.
ichbinhandsome/gemma_pytorch
The official PyTorch implementation of Google's Gemma models
ichbinhandsome/gpu.cpp
A lightweight library for portable low-level GPU computation using WebGPU.
ichbinhandsome/ichbinhandsome
ichbinhandsome/ichbinhandsome.github.io
my blog
ichbinhandsome/images
图床
ichbinhandsome/llama3-from-scratch
llama3 implementation one matrix multiplication at a time
ichbinhandsome/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
ichbinhandsome/llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
ichbinhandsome/LLM-fine-tuning
Code base about fine-tuning LLM
ichbinhandsome/llm.c
LLM training in simple, raw C/CUDA
ichbinhandsome/LLM101n
LLM101n: Let's build a Storyteller
ichbinhandsome/LLMs-from-scratch
Implementing a ChatGPT-like LLM from scratch, step by step
ichbinhandsome/lorax
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
ichbinhandsome/NeMo
NeMo: a toolkit for conversational AI
ichbinhandsome/NExT-GPT
Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model
ichbinhandsome/OLMo
Modeling, training, eval, and inference code for OLMo
ichbinhandsome/open_clip
An open source implementation of CLIP.
ichbinhandsome/open_flamingo
An open-source framework for training large multimodal models.
ichbinhandsome/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
ichbinhandsome/smoothquant
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
ichbinhandsome/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.