MEXMA: Token-level objectives improve sentence representations
☆44Jan 6, 2025Updated last year
Alternatives and similar repositories for mexma
Users that are interested in mexma are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆36Oct 1, 2026Updated last week
- ☆14Jul 7, 2024Updated 2 years ago
- This repository provides a comprehensive benchmark for evaluating the performance of neural watermarking techniques. The benchmark includ…☆25Jan 9, 2026Updated 9 months ago
- The training codes of Jasper-Token-Compression-600M☆22Nov 19, 2025Updated 10 months ago
- Training code for Sparse Autoencoders on Embedding models☆41Jul 11, 2026Updated 3 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.
- Code for the paper "Watermarking Makes Language Models Radioactive"☆25Oct 25, 2024Updated last year
- AutoRAG example about benchmarking Korean embeddings.☆46Oct 2, 2024Updated 2 years ago
- KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models☆25Aug 24, 2024Updated 2 years ago
- Draft grounded rebuttals to your paper's reviews, with the experiments actually run in your workspace☆17Jul 30, 2026Updated 2 months ago
- ☆11Jun 14, 2024Updated 2 years ago
- PreRanker: reranking tools before tool-use☆20Apr 9, 2025Updated last year
- ☆64Jan 26, 2025Updated last year
- ☆32Sep 27, 2026Updated 2 weeks ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆378Jul 20, 2026Updated 2 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆928Oct 28, 2024Updated last year
- Coord: A Unified Interface for All Models☆18Jun 19, 2026Updated 3 months ago
- Code for the paper "Multi-Field Adaptive Retrieval," a research project on a semi-structured document retrieval☆19Feb 13, 2026Updated 8 months ago
- Visualize expert firing frequencies across sentences in the Mixtral MoE model☆18Dec 22, 2023Updated 2 years ago
- Official code for "Evaluations of Machine Learning Privacy Defenses are Misleading" (https://arxiv.org/abs/2404.17399)☆13Apr 29, 2024Updated 2 years ago
- Mixture of Lora Experts☆11Apr 7, 2024Updated 2 years ago
- Load any clip model with a standardized interface☆23Oct 20, 2025Updated 11 months ago
- Official Repository for "Hypencoder: Hypernetworks for Information Retrieval"☆41Sep 20, 2025Updated last year
- Performs benchmarking on two Korean datasets with minimal time and effort.☆49Aug 6, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- bb25 is a fast, self-contained BM25 + Bayesian calibration implementation with a minimal Python API.☆151Mar 17, 2026Updated 6 months ago
- Identify which embedding model produced a vector using digit-level tokenization and a tiny transformer☆23Mar 7, 2026Updated 7 months ago
- ☆19May 16, 2024Updated 2 years ago
- A research project exploring fine-tuning BERT-style models for text generation☆43Nov 30, 2025Updated 10 months ago
- ☆16Mar 3, 2024Updated 2 years ago
- ☆18Apr 18, 2025Updated last year
- Codebase for generation-time and post-hoc text watermarking, as well as watermark radioactivity detection.☆72Updated this week
- huggingface에 있는 한국어 데이터 세트☆38Oct 10, 2024Updated 2 years ago
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,769Jul 18, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Proteus is an experimental platform that combines the power of Large Language Models with the Genesis physics engine☆25Dec 20, 2024Updated last year
- Code for paper "Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators"☆17Dec 4, 2024Updated last year
- Korean-MTEB☆106May 12, 2026Updated 5 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆386Dec 12, 2024Updated last year
- ☆16Jan 30, 2025Updated last year
- ☆34Feb 27, 2024Updated 2 years ago
- Official implementation of the paper "Watermarking Autoregressive Image Generation" (NeurIPS'25)☆70Jul 21, 2026Updated 2 months ago