uclaml / SPINLinks
The official implementation of Self-Play Fine-Tuning (SPIN)
☆1,172Updated last year
Alternatives and similar repositories for SPIN
Users that are interested in SPIN are comparing it to the libraries listed below
Sorting:
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,392Updated last year
- Code for Quiet-STaR☆735Updated 10 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆868Updated 2 weeks ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆908Updated 5 months ago
- Codebase for Merging Language Models (ICML 2024)☆842Updated last year
- ☆1,025Updated 6 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆735Updated 9 months ago
- Official repository for ORPO☆457Updated last year
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,575Updated 8 months ago
- ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting wit…☆1,077Updated last year
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,557Updated last year
- YaRN: Efficient Context Window Extension of Large Language Models☆1,511Updated last year
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆656Updated last year
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,495Updated 5 months ago
- Reaching LLaMA2 Performance with 0.1M Dollars☆984Updated 11 months ago
- RewardBench: the first evaluation tool for reward models.☆612Updated last month
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆728Updated 3 months ago
- Large Reasoning Models☆805Updated 7 months ago
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,800Updated 6 months ago
- ☆946Updated 5 months ago
- Generative Representational Instruction Tuning☆658Updated 3 weeks ago
- FuseAI Project☆578Updated 5 months ago
- ☆523Updated 7 months ago
- Recipes to scale inference-time compute of open models☆1,101Updated last month
- Representation Engineering: A Top-Down Approach to AI Transparency☆848Updated 11 months ago
- [ACL 2024] Progressive LLaMA with Block Expansion.☆505Updated last year
- A bibliography and survey of the papers surrounding o1☆1,205Updated 8 months ago
- ☆824Updated 2 weeks ago
- Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"☆1,225Updated 4 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆621Updated last year