predibase / llm_distillation_playbook
Best practices for distilling large language models.
☆523Updated 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
- Official repository for ORPO☆448Updated 10 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,438Updated last week
- An Open Source Toolkit For LLM Distillation☆579Updated 3 months ago
- ☆515Updated 5 months ago
- Generative Representational Instruction Tuning☆620Updated last month
- Easily embed, cluster and semantically label text datasets☆526Updated last year
- awesome synthetic (text) datasets☆272Updated 5 months ago
- A reading list on LLM based Synthetic Data Generation 🔥☆1,246Updated 2 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆833Updated last week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,642Updated last week
- ☆1,015Updated 4 months ago
- Automatic evals for LLMs☆373Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆715Updated 6 months ago
- Automated Evaluation of RAG Systems☆579Updated 3 weeks ago
- Automatically evaluate your LLMs in Google Colab☆615Updated 11 months ago
- Minimalistic large language model 3D-parallelism training☆1,793Updated this week
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆459Updated last year
- A repository for research on medium sized language models.☆494Updated last week
- Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard a…☆1,143Updated 3 months ago
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆681Updated last month
- ☆1,161Updated last month
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,463Updated 2 months ago
- Evaluate your LLM's response with Prometheus and GPT4 💯☆911Updated last month
- Recipes to scale inference-time compute of open models☆1,058Updated 2 months ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,360Updated last week
- Data and tools for generating and inspecting OLMo pre-training data.☆1,198Updated last week
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆274Updated last month
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,251Updated this week
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆1,391Updated 3 weeks ago
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.☆436Updated this week