Pinned Repositories
adaptive-quantization-modules
Code for "Online Learned Continual Compression with Adaptive Quantization Modules"
BERT
modification of official bert for downstream task
cail22_xxcq
classifynet
text classification with various advanced modules and latest models such as leam, hard attention, multi-head attention
Conv_Bert
crust
[NeurIPS 2020] Coresets for Robust Training of Neural Networks against Noisy Labels
DeepNER
天池中药说明书实体识别挑战冠军方案；中文命名实体识别；NER; BERT-CRF & BERT-SPAN & BERT-MRC；Pytorch
deepspeech
deepspeech on tensorflow (1.x ) and supported for tpu, gpu
simnet
semantic similarity model
UPSA
yyht's Repositories
yyht/Agent-Pro
The Code Repo for Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization
yyht/AI-Security-and-Privacy-Events
A curated list of academic events on AI Security & Privacy
yyht/ArCHer
Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"
yyht/autogen-agi
AutoGen AGI: Advancing AI agents using AutoGen towards AGI capabilities. Explore cutting-edge enhancements in group chat dynamics, decision-making, and complex task proficiency. Join our journey in shaping AI's future!
yyht/Awesome-LLM-Safety
A curated list of security-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights into the security implications, challenges, and advancements surrounding these powerful models.
yyht/deep_training
deep learning
yyht/DeepSeek-Math
yyht/detect-secrets
An enterprise friendly way of detecting and preventing secrets in code.
yyht/evalplus
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023
yyht/GuoFeng-Webnovel
Multilingual Corpus of Web Fiction
yyht/HALOs
A library with extensible implementations of DPO, KTO, PPO, and other human-aware loss functions (HALOs).
yyht/HybridAGI
The Programmable Neuro-Symbolic AGI that lets you program its behavior using Graph-based Prompt Programming: for people who want AI to behave as expected
yyht/ICDPO
The official implementation of "ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization".
yyht/k-diffusion-inverse-problems
Implementation of diffusion-based posterior sampling methods for inverse problems
yyht/lingua-py
The most accurate natural language detection library for Python, suitable for short text and mixed-language text
yyht/llm-verified-with-monte-carlo-tree-search
LLM verified with Monte Carlo Tree Search
yyht/marker
Convert PDF to markdown quickly with high accuracy
yyht/Noise-Contrastive-Alignment
Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards"
yyht/OPO
yyht/orpo
yyht/REBEL
yyht/reflection-on-trees
yyht/ReNeLLM
The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily".
yyht/SAELens
Training Sparse Autoencoders on Language Models
yyht/searchformer
Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".
yyht/self-rewarding-lm-pytorch
Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
yyht/SemiReward
[ICLR 2024] SemiReward: A General Reward Model for Semi-supervised Learning
yyht/theorem-proving-reasoning
Code for the paper LeanReasoner: Boosting Complex Logical Reasoning with Lean: https://arxiv.org/pdf/2403.13312.pdf
yyht/unisim
UniSim is a package for efficient similarity computation, fuzzy matching, and clustering of data.
yyht/URS
URS Benchmark: Evaluating LLMs on User Reported Scenarios