DPO, but faster π
β52Dec 6, 2024Updated last year
Alternatives and similar repositories for dpo-prefix-sharing
Users that are interested in dpo-prefix-sharing are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- rabitq rust implementationβ11May 14, 2026Updated 2 weeks ago
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into oneβ26Aug 5, 2024Updated last year
- β16Jul 29, 2025Updated 10 months ago
- Training and evaluation code for the paper "Headless Language Models: Learning without Predicting with Contrastive Weight Tying" (https:/β¦β29Apr 17, 2024Updated 2 years ago
- See https://github.com/cuda-mode/triton-index/ instead!β11May 8, 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.
- Official implementation of "GPT or BERT: why not both?"β64Jul 28, 2025Updated 10 months ago
- Latent Large Language Modelsβ19Aug 24, 2024Updated last year
- NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessmentβ16Apr 13, 2022Updated 4 years ago
- Simple repository for training small reasoning modelsβ51Feb 17, 2026Updated 3 months ago
- This repository contains the joint use of CPO and SimPO method for better reference-free preference learning methods.β57Aug 13, 2024Updated last year
- β16Feb 6, 2024Updated 2 years ago
- Evaluating Reward Models in Multilingual Settings (ACL Main '25)β42May 16, 2025Updated last year
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]β32Jan 23, 2025Updated last year
- 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 last year
- Simple, predictable pricing with DigitalOcean hosting β’ AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Official implementation of ECCV24 paper: POAβ24Aug 8, 2024Updated last year
- β36Mar 12, 2025Updated last year
- β19Nov 4, 2025Updated 6 months ago
- [ICLR2025] Ξ³ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Modelsβ43Oct 28, 2025Updated 7 months ago
- Direct preference optimization with f-divergences.β16Nov 3, 2024Updated last year
- Curriculum training of instruction-following LLMs with Unslothβ14Dec 15, 2025Updated 5 months ago
- Blazingly fast neighborhood attentionβ14Nov 28, 2023Updated 2 years ago
- Efficient Infinite Context Transformers with Infini-attention Pytorch Implementation + QwenMoE Implementation + Training Script + 1M contβ¦β96May 9, 2024Updated 2 years ago
- Official implementation for "MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models"β20Oct 26, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits β’ AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Fast and memory-efficient exact attentionβ21Apr 10, 2026Updated last month
- β24Sep 2, 2022Updated 3 years ago
- Hugging Face RoBERTa with Flash Attention 2β24Sep 14, 2025Updated 8 months ago
- [ICLR 2025] Weighted-Reward Preference Optimization for Implicit Model Fusionβ14Mar 17, 2025Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inferenceβ299May 1, 2025Updated last year
- Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpeningβ73May 18, 2025Updated last year
- [NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generationβ78Sep 19, 2025Updated 8 months ago
- Codebase for Efficient yet simple Reinforcement Learning Research Frameworkβ28Jan 14, 2023Updated 3 years ago
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.β152Mar 31, 2026Updated last month
- End-to-end encrypted email - Proton Mail β’ AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encodersβ19May 23, 2025Updated last year
- β70Jul 8, 2025Updated 10 months ago
- [ICLR 2026] Tina: Tiny Reasoning Models via LoRAβ332Sep 23, 2025Updated 8 months ago
- [ICML 2025] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Modelsβ18Nov 4, 2025Updated 6 months ago
- Accepted to ICLR 2025. MetaMetrics is a calibrated meta-metric designed to evaluate generation tasks across different modalities aligned β¦β15Dec 30, 2024Updated last year
- A scalable automated alignment method for large language models. Resources for "Aligning Large Language Models via Self-Steering Optimizaβ¦β20Nov 21, 2024Updated last year
- β15May 15, 2021Updated 5 years ago