A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.
☆388Jul 8, 2025Updated last year
Alternatives and similar repositories for logits-processor-zoo
Users that are interested in logits-processor-zoo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 1st Place Solution for Eedi - Mining Misconceptions in Mathematics Kaggle Competition☆59Dec 27, 2024Updated last year
- NVIDIA Kaggle Plugin gives agents end-to-end Kaggle competition workflows through a single skill, nvidia-kaggle-skill. It can gather comp…☆273Jul 10, 2026Updated 2 weeks ago
- Structured Generation Evals☆14Sep 25, 2024Updated last year
- GPU-accelerated algorithm for subsampling datasets while preserving diversity☆27Jan 12, 2024Updated 2 years ago
- ☆77Apr 20, 2026Updated 3 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- LLM KV cache compression made easy☆1,147Updated this week
- ☆57Nov 22, 2024Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆153Aug 9, 2024Updated last year
- Creating diff that supports wildcard produced by LLMs☆16Sep 18, 2024Updated last year
- Slides for my presentation☆19Nov 17, 2022Updated 3 years ago
- Official repository for ORPO☆480May 31, 2024Updated 2 years ago
- Kaggle AIMO2 solution with token-efficient reasoning LLM recipes☆50Aug 7, 2025Updated 11 months ago
- Latent Large Language Models☆19Aug 24, 2024Updated last year
- Tools for merging pretrained large language models.☆7,266Jun 17, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,501Jun 29, 2026Updated last month
- Load any clip model with a standardized interface☆22Oct 20, 2025Updated 9 months ago
- Efficient few-shot learning with Sentence Transformers☆2,777May 26, 2026Updated 2 months ago
- ☆103Jul 4, 2025Updated last year
- Code for the CHAMPS Predicting Molecular Properties Kaggle competition☆52Aug 31, 2019Updated 6 years ago
- Efficient Triton Kernels for LLM Training☆6,537Updated this week
- ☆57Apr 16, 2026Updated 3 months ago
- Applied AI experiments and examples for PyTorch☆322Aug 22, 2025Updated 11 months ago
- Minimalistic large language model 3D-parallelism training☆2,768May 26, 2026Updated 2 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Formatron empowers everyone to control the format of language models' output with minimal overhead.☆237Jun 7, 2025Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆181May 2, 2024Updated 2 years ago
- Easily embed, cluster and semantically label text datasets☆609Mar 28, 2024Updated 2 years ago
- Enforce the output format (JSON Schema, Regex etc) of a language model☆2,027Apr 4, 2026Updated 3 months ago
- implementation of https://arxiv.org/pdf/2312.09299☆21Jul 3, 2024Updated 2 years ago
- Training code for Sparse Autoencoders on Embedding models☆39Jul 11, 2026Updated 2 weeks ago
- ☆19Jul 26, 2024Updated 2 years ago
- PyTorch native post-training library☆5,790Updated this week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆3,237Jul 22, 2026Updated last week
- 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.
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆234Oct 31, 2024Updated last year
- Expand -> Retrieve -> Rerank - simple method with strong results on BRIGHT benchmark☆22Aug 22, 2025Updated 11 months ago
- ☆14May 3, 2022Updated 4 years ago
- Fast Multimodal Semantic Deduplication & Filtering☆954May 24, 2026Updated 2 months ago
- RSNA 2024 Lumbar Spine Degenerative Classification 4th place solution☆11Oct 10, 2024Updated last year
- ☆50Mar 14, 2024Updated 2 years ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆735Apr 10, 2024Updated 2 years ago