Nealcly

Werewolf

llm-reasoners

A library for advanced large language model reasoning

llama3

The official Meta Llama 3 GitHub site

drpo

Dateset Reset Policy Optimization

FewShotCalibration

TACS

Source code for Truth-Aware Context Selection: Mitigating the Hallucinations of Large Language Models Being Misled by Untruthful Contexts

transformer-debugger

HALOs

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

GSM-Plus

GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.

MORE

Code for paper - On Diversified Preferences of Large Language Model Alignment

TruthX

Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"

sort-google-scholar

Sorting Google Scholar search results based on the number of citations

awesome-mixture-of-experts

A collection of AWESOME things about mixture-of-experts

CLEX

[ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

inferflow

Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).

world-model-for-language-model

ICD

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"

weak-to-strong

OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

vec2text

utilities for decoding deep representations (like sentence embeddings) back to text

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

OpenMoE

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

ALCUNA

[EMNLP 2023] ALCUNA: Large Language Models Meet New Knowledge

speculative-decoding

Explorations into some recent techniques surrounding speculative decoding

CaRing

Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

BotChat

Evaluating LLMs' multi-round chatting capability via assessing conversations generated by two LLM instances.

CoEval

A collaborative LLM-human evaluation pipeline COEVAL.

Selective_Context

Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.