predibase / llm_distillation_playbookLinks
Best practices for distilling large language models.
☆554Updated last year
Alternatives and similar repositories for llm_distillation_playbook
Users that are interested in llm_distillation_playbook are comparing it to the libraries listed below
Sorting:
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,641Updated this week
- ☆520Updated 7 months ago
- An Open Source Toolkit For LLM Distillation☆657Updated 3 weeks ago
- Official repository for ORPO☆455Updated last year
- Generative Representational Instruction Tuning☆654Updated 3 months ago
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,490Updated 4 months ago
- Easily embed, cluster and semantically label text datasets☆552Updated last year
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆859Updated 2 weeks ago
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆717Updated 3 months ago
- A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.☆780Updated 3 months ago
- Recipes to scale inference-time compute of open models☆1,097Updated last month
- ☆544Updated last year
- Evaluate your LLM's response with Prometheus and GPT4 💯☆952Updated 2 months ago
- Minimalistic large language model 3D-parallelism training☆1,942Updated this week
- ☆1,025Updated 6 months ago
- Train Models Contrastively in Pytorch☆723Updated 3 months ago
- A reading list on LLM based Synthetic Data Generation 🔥☆1,310Updated 3 weeks ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,773Updated this week
- ☆1,229Updated 4 months ago
- LLM Workshop by Sourab Mangrulkar☆383Updated last year
- Automatically evaluate your LLMs in Google Colab☆643Updated last year
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,426Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆732Updated 9 months ago
- awesome synthetic (text) datasets☆282Updated 7 months ago
- Automatic evals for LLMs☆437Updated 3 weeks ago
- Data and tools for generating and inspecting OLMo pre-training data.☆1,250Updated this week
- Automated Evaluation of RAG Systems☆613Updated 2 months ago
- ☆669Updated last month
- Code for Quiet-STaR☆734Updated 10 months ago
- Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard a…☆1,444Updated 5 months ago