Llama-3-SynE: A Significantly Enhanced Version of Llama-3 with Advanced Scientific Reasoning and Chinese Language Capabilities | 继续预训练提升 Llama-3 的科学推理和中文能力

TensorFlow Implementation of "Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation" in SIGIR'21

This is the repository for the Tool Learning survey.

A Go web framework for quickly building recommendation online services based on JSON configuration.

Making LLaVA Tiny via MoE-Knowledge Distillation

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

A modified version of Google's tool for pure text file

Label, clean and enrich text datasets with LLMs.

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or rejection sampling fine-tuning.

Code for Paper (Entropic Distribution Matching in Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity)

This is the code repo for our paper "Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents".

[EMNLP24] Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

使用W2NER模型进行命名实体识别

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

Aligning Query Representation with Rewritten Query and Relevance Judgments for Conversational Search. A code base for CIKM 2024 accepted paper.

Source code for "CoEdPilot: Recommending Code Edits with Learned Prior Edit Relevance, Project-wise Awareness, and Interactive Nature"

State-of-the-art Parameter-Efficient MoE Fine-tuning Method

Continuous learning to fine-tune a pre-trained generative transformer model with DPO from real examples and a knowledge retrieval system

Official Pytorch Implementation of Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling

Some methods to sampling data points from a given distribution.

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

Distill a Small Static Model from any Sentence Transformer