uclaml / SPIN
The official implementation of Self-Play Fine-Tuning (SPIN)
☆1,034Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for SPIN
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,333Updated 6 months ago
- Code for Quiet-STaR☆639Updated 2 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆738Updated last week
- Codebase for Merging Language Models (ICML 2024)☆765Updated 6 months ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆701Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆642Updated last month
- Generative Representational Instruction Tuning☆562Updated this week
- ☆1,263Updated this week
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,426Updated last week
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆610Updated 5 months ago
- Reaching LLaMA2 Performance with 0.1M Dollars☆960Updated 3 months ago
- ☆445Updated last week
- ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting wit…☆971Updated 8 months ago
- Official repository for ORPO☆420Updated 5 months ago
- Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality s…☆476Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,143Updated 3 weeks ago
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆586Updated 3 months ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,339Updated 6 months ago
- ReFT: Representation Finetuning for Language Models☆1,145Updated this week
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆435Updated 7 months ago
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,000Updated 9 months ago
- [ACL 2024] Progressive LLaMA with Block Expansion.☆479Updated 5 months ago
- Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"☆868Updated last month
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,385Updated 8 months ago
- Train Models Contrastively in Pytorch☆543Updated 2 weeks ago
- RewardBench: the first evaluation tool for reward models.☆424Updated 2 weeks ago
- Large Reasoning Models☆457Updated this week
- Training LLMs with QLoRA + FSDP☆1,418Updated this week
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆667Updated 6 months ago
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models☆824Updated 6 months ago