Highlights
- Pro
Stars
Swallowプロジェクト 事後学習済み大規模言語モデル 評価フレームワーク
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
A holistic benchmark for LLM abstention
The agent that grows with you
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Rethinking the Trust Region in LLM Reinforcement Learning
AgentSociety 2 is a modern, LLM-native agent simulation platform designed for social science research and experimental design. It provides a flexible framework for creating and managing intelligent…
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
[COLM 2025] An Open Math Pre-trainng Dataset with 370B Tokens.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
RapidIn: Scalable Influence Estimation for Large Language Models (LLMs). The implementation for paper "Token-wise Influential Training Data Retrieval for Large Language Models" (Accepted on ACL 2024).
Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
A reading list on LLM based Synthetic Data Generation 🔥
Large Language Model Text Generation Inference
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.