Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"
☆33Jun 5, 2025Updated last year
Alternatives and similar repositories for BLEUBERI
Users that are interested in BLEUBERI are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆63Sep 24, 2024Updated 2 years ago
- The dataset consists of public social media url pairs and the corresponding entailment label for an external conference (ACL 2021). Each …☆14Aug 16, 2021Updated 5 years ago
- ☆21Apr 3, 2026Updated 7 months ago
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆32Jun 13, 2024Updated 2 years ago
- Vocabulary Parallelism☆26Mar 10, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Reinforcing General Reasoning without Verifiers☆103Jun 24, 2025Updated last year
- ☆14Feb 12, 2026Updated 8 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆79Apr 19, 2025Updated last year
- ☆19Oct 6, 2026Updated 3 weeks ago
- Fully chunked KL-Loss kernel, that massively reduces VRAM usage☆20Aug 10, 2026Updated 2 months ago
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- ☆17Sep 9, 2026Updated last month
- Consistent dialogue generation☆16Oct 26, 2022Updated 4 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Danmuku dataset☆12Jul 7, 2023Updated 3 years ago
- Official repo for "Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs"☆12May 5, 2026Updated 5 months ago
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆52May 4, 2024Updated 2 years ago
- Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals☆11Jan 8, 2026Updated 9 months ago
- ☆12Apr 6, 2026Updated 6 months ago
- ☆15May 11, 2026Updated 5 months ago
- [ICML 2025] Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment (https://arxiv.org/abs/2410.02197)☆46Jun 15, 2026Updated 4 months ago
- ☆12Jun 5, 2024Updated 2 years ago
- ☆29Aug 31, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Scripts for training Qwen 2.5 VL with ms-swift and GRPO☆13Feb 27, 2025Updated last year
- An unofficial implementation of SOLAR-10.7B model and the newly proposed interlocked-DUS(iDUS) implementation and experiment details.☆14Mar 20, 2024Updated 2 years ago
- ☆32Dec 13, 2023Updated 2 years ago
- ☆12Jul 25, 2025Updated last year
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆674Jan 29, 2026Updated 9 months ago
- Set of scripts to finetune LLMs☆39Mar 30, 2024Updated 2 years ago
- Distributional Successor Features Enable Zero-Shot Policy Optimization☆15Apr 11, 2025Updated last year
- A miniature end-to-end reproduction of the Composer 2 training pipeline on a single NVIDIA GH200 480GB, using GLM-4-9B as the base model.☆15Oct 27, 2026Updated last week
- ☆25Dec 11, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- BFloat16 Fused Adam Operator for PyTorch☆20Nov 16, 2024Updated last year
- CascadER: Cross-Modal Cascading for Knowledge Graph Link Prediction (arXiv 22)☆14Jun 17, 2022Updated 4 years ago
- An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation☆27Jun 7, 2024Updated 2 years ago
- A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity☆20May 26, 2026Updated 5 months ago
- Self-Alignment with Principle-Following Reward Models☆171Oct 9, 2026Updated 3 weeks ago
- EMNLP 2025 "LLMs are Better Than You Think: Label-Guided In-Context Learning for Named Entity Recognition"☆16Nov 4, 2025Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆45Oct 1, 2025Updated last year