This repository contains the joint use of CPO and SimPO method for better reference-free preference learning methods.
β59Aug 13, 2024Updated 2 years ago
Alternatives and similar repositories for CPO_SIMPO
Users that are interested in CPO_SIMPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Control LLM generation format efficiently. A simple version of microsoft/aici in vllm and transformersβ14Jun 7, 2024Updated 2 years ago
- DPO, but faster πβ51Dec 6, 2024Updated last year
- β10Aug 7, 2026Updated 2 months ago
- Code of "Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model"β22Jun 28, 2024Updated 2 years ago
- WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction, to appear at ACL 2023 main conference.β12Apr 15, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways β’ AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [ICML 2025] Official code of "AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization"β32Jan 10, 2026Updated 9 months ago
- Testing the accelerate megatron integrationβ10Nov 8, 2022Updated 3 years ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"β41Sep 24, 2024Updated 2 years ago
- State-of-the-art LLM-based translation models.β593Apr 9, 2025Updated last year
- mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Modelsβ11Jan 19, 2024Updated 2 years ago
- β26Oct 22, 2022Updated 4 years ago
- β14Oct 11, 2023Updated 3 years ago
- Scalable, structured, dynamically-scheduled hyperparameter optimization.β19Oct 13, 2022Updated 4 years ago
- First explanation metric (diagnostic report) for text generation evaluationβ62Mar 3, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient β’ AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- This repository contains code for the paper Direct Preference Optimization with an Offset (ODPO).β21Feb 17, 2025Updated last year
- Official Code for "Token Distillation: Attention-aware Input Embeddings for New Tokens"β13Mar 11, 2026Updated 7 months ago
- Masking tokens to modify the predictions of a pretrained sentence classifierβ16Feb 4, 2020Updated 6 years ago
- Repository for Skill Set Optimizationβ14Jul 26, 2024Updated 2 years ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flβ¦β78Aug 17, 2024Updated 2 years ago
- The official implement of Freeze-Omni.β16Jul 10, 2025Updated last year
- Training SLMs for reasoning-intensive re-rankingβ11Jul 18, 2025Updated last year
- β13Sep 7, 2024Updated 2 years ago
- β16Feb 6, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient β’ AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- β18Jul 30, 2018Updated 8 years ago
- [NAACL 2024 Outstanding Paper] Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don'tβ¦β142Jul 10, 2024Updated 2 years ago
- MetricEval: A framework that conceptualizes and operationalizes four main components of metric evaluation, in terms of reliability and vaβ¦β13Nov 6, 2023Updated 2 years ago
- Multi-task modelling extensions for huggingface transformersβ21Mar 3, 2023Updated 3 years ago
- Mirror for Java and PHP libraries and text resources to facilitate the use of Inuktitut in its written form on computers and the webβ10Aug 2, 2015Updated 11 years ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"β75May 20, 2025Updated last year
- Constrained Decoding Projectβ20Nov 10, 2023Updated 2 years ago
- Accelerating GOT-OCRv2 with VLLMβ10Nov 15, 2024Updated last year
- [ICLR 2024] This is the official implementation for the paper: "Beyond imitation: Leveraging fine-grained quality signals for alignment"β11May 5, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean β’ AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- β49Oct 28, 2024Updated 2 years ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignmentβ55Jun 16, 2024Updated 2 years ago
- LLM-Training-API: Including Embeddings & ReRankers, mergekit, LaserRMTβ28Feb 18, 2024Updated 2 years ago
- ι³δΉη±»θ―ζηζεΎθ―ε«ε‘«ζ§½δ»₯ε槽εΌηΊ ι樑εβ19Mar 24, 2023Updated 3 years ago
- Code for paper γDrug-Drug Interaction Extraction via Recurrent Hybrid Convolutional Neural Networks with an Improved Focal Lossγβ14Mar 12, 2019Updated 7 years ago
- Regexp::Trie for Java7β11May 9, 2023Updated 3 years ago
- Hugging Face RoBERTa with Flash Attention 2β23Sep 14, 2025Updated last year