Xidong Wang's repositories
Notes-and-Assigns-for-CS224N
Homework and Notes of CS224N
BLAS_testbench
Basic Linear Algebra Subprograms testbench
Optimized-LLM.cpp
Optimized LLM.cpp codes(LLaMa.cpp BLoomz.cpp Whisper.cpp) with Matrix Multiplication implemented by BLIS
acl-2023
Repository for the ACL 2023 conference website
DoLa
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
emnlp-2023
Repository containing the website for the EMNLP 2023 conference
EasyContext
Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.
Firefly
Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA),支持微调Baichuan2、CodeLlama、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya、Bloom等大模型
flash-attention
Fast and memory-efficient exact attention
llama-mistral
Inference code for Mistral and Mixtral hacked up into original Llama implementation
llama.cpp
Port of Facebook's LLaMA model in C/C++
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
LLMSFT_template
Various SFT acceleration framework scripts and codes
Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
Megatron-LLaMA
Best practice for training LLaMA models in Megatron-LM
neurips_llm_efficiency_challenge
NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day
opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets.
OpenRLHF
A Ray-based High-performance RLHF framework (for 7B on RTX4090 and 34B on A100)
PromethAI-Memory
Memory management for the AI Applications and AI Agents
TensorRT
NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.
UltraFastBERT
The repository for the code of the UltraFastBERT paper