This repository contains code for the paper "Better Estimation of the KL Divergence Between Language Models"
☆20May 30, 2025Updated last year
Alternatives and similar repositories for kl-rb
Users that are interested in kl-rb are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Sampling-Based Minimum Bayes-Risk Decoding for Neural Machine Translation☆16Oct 14, 2022Updated 4 years ago
- ☆21Apr 26, 2026Updated 6 months ago
- ☆24Aug 30, 2025Updated last year
- Path-SGD: Path-Normalized Optimization in Deep Neural Networks☆19Nov 26, 2018Updated 7 years ago
- Repo for Paper: Discovering Interpretable Algorithms by Decompiling Transformers to RASP☆16May 25, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Code for "On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding (ICML 2025)"☆10Jun 29, 2025Updated last year
- On-policy self-distillation using worked solutions from other problems.☆18Aug 28, 2026Updated 2 months ago
- Code for the paper "Verifying Chain-of-Thought Reasoning via its Computational Graph".☆33Dec 6, 2025Updated 10 months ago
- Code for "Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation"☆19Sep 1, 2026Updated 2 months ago
- (Nanochat based) Full-bandwidth transformer, feed LLM's own deep hidden states back to itself☆16Oct 3, 2026Updated 3 weeks ago
- Semantic Parser Localizer (SPL) code repository☆10Mar 15, 2021Updated 5 years ago
- Robust and safe deep reinforcement learning algorithms☆17Mar 27, 2024Updated 2 years ago
- [ICML 2026 Spotlight] Enhancing Reasoning For Diffusion LLMs via Distribution Matching Policy Optimization☆20Aug 31, 2026Updated 2 months ago
- High-performance backend for language model probabilistic programs☆17Oct 14, 2026Updated 2 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Sequential Monte Carlo Speculative Decoding☆54Aug 25, 2026Updated 2 months ago
- Code repository for "RL Grokking Recipe: How RL Unlocks and Transfers New Algorithms in LLMs""☆35Oct 12, 2025Updated last year
- Pipelined Self-Speculative Decoding for Looped Transformer☆22Sep 24, 2026Updated last month
- Rationales for Sequential Predictions☆39Mar 10, 2022Updated 4 years ago
- Natural Perturbation for Robust Question Answering☆12Apr 7, 2020Updated 6 years ago
- The OlymMATH dataset☆26Jun 1, 2025Updated last year
- ☆16Jul 21, 2025Updated last year
- CLIPPER: Compression enables long-context synthetic data generation [COLM '25]☆11Apr 16, 2025Updated last year
- ☆11Aug 30, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- An open source evaluation framework for developing NLP systems☆10Jan 16, 2020Updated 6 years ago
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆61Jun 3, 2024Updated 2 years ago
- Learning Based Java (LBJava)☆14Jul 1, 2022Updated 4 years ago
- ALBERT Persian Playground☆13Jun 12, 2023Updated 3 years ago
- qwen3-base family of models RL on gsm8k using verl, is there an RL power law on downstream tasks?☆28Oct 19, 2025Updated last year
- Scripts for training Qwen 2.5 VL with ms-swift and GRPO☆13Feb 27, 2025Updated last year
- Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.☆75Oct 23, 2026Updated last week
- ☆89Feb 25, 2025Updated last year
- Code for running forward and backward versions of GPT2☆10Nov 20, 2021Updated 4 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- 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.☆15Updated this week
- The official implementation of the paper "A Dual-Space Framework for General Knowledge Distillation of Large Language Models".☆17Jan 4, 2026Updated 9 months ago
- Awesome tools for interpreting, manipulating the internals of of deep neural networks.☆21Oct 13, 2026Updated 2 weeks ago
- Code and dataset for the paper ``Challenges to Open-Domain Constituency Parsing''☆11Sep 22, 2022Updated 4 years ago
- Normalized and modified version of Bijankhan corpus☆13Feb 21, 2023Updated 3 years ago
- [Code for paper] The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?☆11Oct 6, 2025Updated last year
- ☆37Feb 2, 2026Updated 9 months ago