Beast code in Giters

huangyf's starred repositories

persona-hub

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

Language:Python68900

llm_interview_note

主要记录大语言大模型（LLMs）算法（应用）工程师相关的知识及面试题

Language:HTML199100

FastFiD

[ACL 2024] Source code for ACL 2024 main coference paper "FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection"

Language:Python300

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Language:PythonApache-2.02122400

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo

Language:PythonNOASSERTION70500

VAR

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

Language:PythonMIT392500

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Language:PythonMIT614000

mergekit

Tools for merging pretrained large language models.

Language:PythonLGPL-3.0432400

awesome-hallucination-detection

List of papers on hallucination detection in LLMs.

Apache-2.052000

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonBSD-3-Clause545200

VisualCoT

Codebase for AAAI 2024 conference paper Visual Chain-of-Thought Prompting for Knowledge-based Visual Reasoning

Language:Python1100

LingoWhale-8B

LingoWhale-8B: Open Bilingual LLMs | 开源双语预训练大模型

Language:PythonNOASSERTION12900

flash-attention

Fast and memory-efficient exact attention

Language:PythonBSD-3-Clause1293300

fastmoe

A fast MoE impl for PyTorch

Language:PythonApache-2.0150100

CPM-Bee

百亿参数的中英文双语基座大模型

Language:Python267800

PythonProgrammingPuzzles

A Dataset of Python Challenges for AI Research

Language:PythonMIT96100

awesome-large-graph-model

Papers about large graph models.

MIT24100

CodeGen

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

Language:PythonApache-2.0486000

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Language:PythonApache-2.01123700

diplomacy_cicero

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

Language:PythonNOASSERTION126700

Stable-Alignment

Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

Language:PythonNOASSERTION33600

Megatron-LM

Ongoing research training transformer models at scale

Language:PythonNOASSERTION968400

DBKD-PLM

Codebase for ACL 2023 conference long paper Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models.

Language:Python600

chain-of-thought-hub

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

Language:Jupyter NotebookMIT247600

VisCPM

[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列

Language:Python105100

BMTrain

Efficient Training (including pre-training and fine-tuning) for Big Models

Language:PythonApache-2.054000

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Language:PythonMIT16576700

Multi-GPT

An experimental open-source attempt to make GPT-4 fully autonomous.

Language:PythonMIT54500

Awesome-LLM-Uncertainty-Reliability-Robustness

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

MIT59200

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Language:PythonApache-2.03614000