noahwoo Goto Github PK

alpaca_eval

A validated automatic evaluator for instruction-following language models. High-quality, cheap, and fast.

autogpt-next-web

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.一键免费部署你的私人AutoGPT 网页应用

baichuan-7b

A large-scale 7B pretraining language model developed by Baichuan

cc_net

Tools to download and cleanup Common Crawl data

chatgpt-next-web

One-Click to deploy well-designed ChatGPT web UI on Vercel. 一键拥有你自己的 ChatGPT 网页服务。

chinese-llama-alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

clinearsvm

code for a simple implementation of linear svm

copilot-analysis

deepspeedexamples

Example models using DeepSpeed

dl4math

Resources of deep learning for mathematical reasoning (DL4MATH).

effective_transformer

Running BERT without Padding

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

flan

goat

a Fine-tuned LLaMA that is Good at Arithmetic Tasks

inno_agent

intro-to-llms

ita

introduction to algorithm

langchain

⚡ Building applications with LLMs through composability ⚡

language-programmes

llama_index

LlamaIndex (GPT Index) is a data framework for your LLM applications

llm-toolmaker

mc4seq

code based on CRF++(https://github.com/taku910/crfpp) with multi-class classifier as the base solver

md_r

r code for MD

noahwoo.github.io

觉印思

prm800k

800,000 step-level correctness labels on LLM solutions to MATH problems

psvm

parallel svm

rewoo

Decoupling Reasoning from Observations for Efficient Augmented Language Models

rl-sutton

reinforcement learning of sutton textbook based on https://github.com/dennybritz/reinforcement-learning

rl-sutton-exa

rwkv-lm

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.