predibase / llm_distillation_playbookLinks
Best practices for distilling large language models.
☆577Updated 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:
- Automatically evaluate your LLMs in Google Colab☆661Updated last year
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,514Updated 8 months ago
- Easily embed, cluster and semantically label text datasets☆578Updated last year
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,973Updated last week
- An Open Source Toolkit For LLM Distillation☆732Updated 2 months ago
- LLM Workshop by Sourab Mangrulkar☆395Updated last year
- Official repository for ORPO☆464Updated last year
- ☆541Updated 10 months ago
- awesome synthetic (text) datasets☆297Updated 3 months ago
- Generative Representational Instruction Tuning☆674Updated 3 months ago
- Evaluate your LLM's response with Prometheus and GPT4 💯☆996Updated 5 months ago
- Starter pack for NeurIPS LLM Efficiency Challenge 2023.☆127Updated 2 years ago
- ☆1,034Updated 9 months ago
- A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.☆358Updated 2 months ago
- ☆682Updated 5 months ago
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆1,062Updated 8 months ago
- Automated Evaluation of RAG Systems☆658Updated 6 months ago
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.☆536Updated 3 weeks ago
- Recipes to scale inference-time compute of open models☆1,109Updated 4 months ago
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆289Updated 7 months ago
- Automatic evals for LLMs☆539Updated 3 months ago
- A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.☆793Updated 2 months ago
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆492Updated last year
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆816Updated 2 months ago
- Train Models Contrastively in Pytorch☆750Updated 6 months ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆720Updated last year
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆888Updated last week
- Minimalistic large language model 3D-parallelism training☆2,239Updated last month
- A reading list on LLM based Synthetic Data Generation 🔥☆1,423Updated 4 months ago
- System 2 Reasoning Link Collection☆853Updated 6 months ago