allenai / open-instructLinks
AllenAI's post-training codebase
☆3,562Updated this week
Alternatives and similar repositories for open-instruct
Users that are interested in open-instruct are comparing it to the libraries listed below
Sorting:
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,293Updated 2 weeks ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,084Updated 2 weeks ago
- Minimalistic large language model 3D-parallelism training☆2,544Updated last month
- DataComp for Language Models☆1,413Updated 5 months ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,877Updated last week
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,940Updated 6 months ago
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,555Updated 3 weeks ago
- A library for advanced large language model reasoning☆2,328Updated 8 months ago
- Fully open data curation for reasoning models☆2,206Updated 2 months ago
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,657Updated last year
- Recipes to scale inference-time compute of open models☆1,124Updated 8 months ago
- Democratizing Reinforcement Learning for LLMs☆5,081Updated this week
- Reference implementation for DPO (Direct Preference Optimization)☆2,850Updated last year
- ☆1,345Updated 11 months ago
- Data and tools for generating and inspecting OLMo pre-training data.☆1,404Updated 3 months ago
- Scalable RL solution for advanced reasoning of language models☆1,803Updated 10 months ago
- O1 Replication Journey☆2,000Updated last year
- Tools for merging pretrained large language models.☆6,761Updated 2 weeks ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆2,167Updated last year
- Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"☆1,460Updated 11 months ago
- An Open Large Reasoning Model for Real-World Solutions☆1,533Updated last week
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆905Updated 4 months ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,668Updated last year
- Official Repo for Open-Reasoner-Zero☆2,087Updated 8 months ago
- Robust recipes to align language models with human and AI preferences☆5,489Updated 5 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,511Updated 2 weeks ago
- Training Large Language Model to Reason in a Continuous Latent Space☆1,496Updated 5 months ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,092Updated 2 years ago
- Bringing BERT into modernity via both architecture changes and scaling☆1,627Updated 7 months ago
- Modeling, training, eval, and inference code for OLMo☆6,305Updated 2 months ago