scorpio-nova's Stars
allenai/ScienceWorld
ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
SJ001/AI-Feynman
dvlab-research/Mr-Ben
This is the repo for our paper "Mr-Ben: A Comprehensive Meta-Reasoning Benchmark for Large Language Models"
jlko/semantic_uncertainty
Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).
ENSTA-U2IS-AI/awesome-uncertainty-deeplearning
This repository contains a collection of surveys, datasets, papers, and codes, for predictive uncertainty estimation in deep learning models.
ContextualAI/gritlm
Generative Representational Instruction Tuning
duskmoon314/THU_AMA
我的应用近世代数笔记
MiaoXiong2320/llm-uncertainty
code repo for ICLR 2024 paper "Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs"
jxzhangjhu/Awesome-LLM-Uncertainty-Reliability-Robustness
Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
WeixiangYAN/CodeScope
[ACL 2024] CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
AlignmentResearch/tuned-lens
Tools for understanding how transformer predictions are built layer-by-layer
TransformerLensOrg/TransformerLens
A library for mechanistic interpretability of GPT-style language models
RUCAIBox/HaluEval
This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.
ayaka14732/llama-2-jax
JAX implementation of the Llama 2 model
google/flax
Flax is a neural network library for JAX that is designed for flexibility.
luchris429/purejaxrl
Really Fast End-to-End Jax RL Implementations
UFund-Me/Qbot
[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant
BlinkDL/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.
xssstory/SeqCo
Code for "Sequence Level Contrastive Learning for Text Summarization"
openai/prm800k
800,000 step-level correctness labels on LLM solutions to MATH problems
guidance-ai/guidance
A guidance language for controlling large language models.
nuprl/MultiPL-E
A multi-programming language benchmark for LLMs
kaixindelele/ChatPaper
Use ChatGPT to summarize the arXiv papers. 全流程加速科研,利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
mlc-ai/web-llm
High-performance In-browser LLM Inference Engine
meta-llama/llama
Inference code for Llama models
openai/openai-cookbook
Examples and guides for using the OpenAI API
facebookresearch/segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
microsoft/JARVIS
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
datawhalechina/easy-rl
强化学习中文教程(蘑菇书🍄),在线阅读地址:https://datawhalechina.github.io/easy-rl/