fe1ixxu / CPO_SIMPO
This repository contains the joint use of CPO and SimPO method for better reference-free preference learning methods.
☆53Updated 8 months ago
Alternatives and similar repositories for CPO_SIMPO:
Users that are interested in CPO_SIMPO are comparing it to the libraries listed below
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆74Updated 10 months ago
- Source code of "Reasons to Reject? Aligning Language Models with Judgments"☆58Updated last year
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆76Updated last year
- Reformatted Alignment☆115Updated 7 months ago
- Official implementation of the paper "From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large L…☆48Updated 10 months ago
- Official implementation for 'Extending LLMs ’ Context Window with 100 Samples'☆76Updated last year
- ☆98Updated 6 months ago
- Code implementation of synthetic continued pretraining☆104Updated 3 months ago
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆139Updated 5 months ago
- [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages☆45Updated 4 months ago
- Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment☆75Updated 10 months ago
- An Experiment on Dynamic NTK Scaling RoPE☆63Updated last year
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆47Updated 3 months ago
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆147Updated 7 months ago
- ☆35Updated last year
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆154Updated 10 months ago
- We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆61Updated 5 months ago
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆42Updated 2 months ago
- MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning☆90Updated last year
- Code for preprint "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"☆36Updated last month
- ☆69Updated last year
- Towards Systematic Measurement for Long Text Quality☆34Updated 7 months ago
- Suri: Multi-constraint instruction following for long-form text generation (EMNLP’24)☆22Updated 5 months ago
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆30Updated 10 months ago
- [ICML 2024] Selecting High-Quality Data for Training Language Models☆168Updated 10 months ago
- ☆49Updated last year
- LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models☆75Updated 6 months ago
- Counting-Stars (★)☆82Updated 7 months ago
- BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval☆99Updated last week
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆175Updated last month