OLMoE: Open Mixture-of-Experts Language Models

🙌 OpenHands: Code Less, Make More

[NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623

BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

Data for the MTEB leaderboard

Code for the MTEB leaderboard

🧬 RegMix: Data Mixture as Regression for Language Model Pre-training

DataComp for Language Models

Code for the MTEB Arena

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

BigCodeBench: Benchmarking Code Generation Towards AGI

Home of StarCoder: fine-tuning & inference!

Home of StarCoder2!

Language models scale reliably with over-training and on downstream tasks

A Survey on Data Selection for Language Models

Generative Representational Instruction Tuning

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Evaluation of BLOOM on the HumanEval benchmark

A Scandinavian Benchmark for sentence embeddings

Astraios: Parameter-Efficient Instruction Tuning Code Language Models

A framework for few-shot evaluation of language models.

Modeling, training, eval, and inference code for OLMo

Data and tools for generating and inspecting OLMo pre-training data.

A framework for the evaluation of autoregressive code generation language models.

Retrieval and Retrieval-augmented LLMs

🐙 OctoPack: Instruction Tuning Code Large Language Models

Scaling Data-Constrained Language Models

BLOOM+1: Adapting BLOOM model to support a new unseen language

Crosslingual Generalization through Multitask Finetuning