daiwk's repositories
collections
https://www.daiwk.net/
build-nanogpt
Video+code lecture on building nanoGPT from scratch
Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
DeepEP
DeepEP: an efficient expert-parallel communication library
DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
gemma.cpp
lightweight, standalone C++ inference engine for Google's Gemma models.
generative-recommenders
Repository hosting code used to reproduce results in "Actions Speak Louder than Words Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
HLLM
HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling
Langchain-Chatchat
Langchain-Chatchat๏ผๅLangchain-ChatGLM๏ผๅบไบ Langchain ไธ ChatGLM ็ญ่ฏญ่จๆจกๅ็ๆฌๅฐ็ฅ่ฏๅบ้ฎ็ญ | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain
llama3
The official Meta Llama 3 GitHub site
llama3-from-scratch
llama3 implementation one matrix multiplication at a time
llm-twin-course
๐ค ๐๐ฒ๐ฎ๐ฟ๐ป for ๐ณ๐ฟ๐ฒ๐ฒ how to ๐ฏ๐๐ถ๐น๐ฑ an end-to-end ๐ฝ๐ฟ๐ผ๐ฑ๐๐ฐ๐๐ถ๐ผ๐ป-๐ฟ๐ฒ๐ฎ๐ฑ๐ ๐๐๐ & ๐ฅ๐๐ ๐๐๐๐๐ฒ๐บ using ๐๐๐ ๐ข๐ฝ๐ best practices: ~ ๐ด๐ฐ๐ถ๐ณ๐ค๐ฆ ๐ค๐ฐ๐ฅ๐ฆ + 12 ๐ฉ๐ข๐ฏ๐ฅ๐ด-๐ฐ๐ฏ ๐ญ๐ฆ๐ด๐ด๐ฐ๐ฏ๐ด
LLM101n
LLM101n: Let's build a Storyteller
LLMs-from-scratch-CN
LLMs-from-scratch้กน็ฎไธญๆ็ฟป่ฏ
mistral-src
Reference implementation of Mistral AI 7B v0.1 model.
open-r1
Fully open reproduction of DeepSeek-R1
recommenders-addons
Additional utils and helpers to extend TensorFlow when build recommendation systems, contributed and maintained by SIG Recommenders.
s1
s1: Simple test-time scaling
sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
SSLRec
[WSDM'2024 Oral] "SSLRec: A Self-Supervised Learning Framework for Recommendation"
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.
transformers
๐ค Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
trlx_new
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)