-
Salesforce Research
- Singapore
- https://allanj.github.io
Stars
Python tool for converting files and office documents to Markdown.
Build resilient language agents as graphs.
Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.
A bibliography and survey of the papers surrounding o1
ThinK: Thinner Key Cache by Query-Driven Pruning
veRL: Volcano Engine Reinforcement Learning for LLM
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
SGLang is a fast serving framework for large language models and vision language models.
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
llmstep: [L]LM proofstep suggestions in Lean 4.
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Lean Algorithmic Trading Engine by QuantConnect (Python, C#)
Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" (ICLR 2024)
ReFT: Representation Finetuning for Language Models
The official repository for the paper Multilingual Mathematical Autoformalization
RealSI: Open Benchmark for Simultaneous Interpretation in Real-world Scenarios
Build your own second brain with supermemory. It's a ChatGPT for your bookmarks. Import tweets or save websites and content using the chrome extension.
Doing simple retrieval from LLM models at various context lengths to measure accuracy
📖A curated list of Awesome LLM/VLM Inference Papers with codes, such as FlashAttention, PagedAttention, Parallelism, etc. 🎉🎉
A curated list for Efficient Large Language Models
Agentic components of the Llama Stack APIs
蜂鸟物联网平台是由Golang编写的超轻量级物联网平台,具有轻量级、快速、极低的内存占用等特性,特别适用于个人开发者或初创公司承接中小型物联网项目。
Simple frontend for LLMs built in react-native.
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…