GFNOrg / gfn-lm-tuning
☆125Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for gfn-lm-tuning
- ☆73Updated 4 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆95Updated 2 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆77Updated 2 weeks ago
- ☆75Updated 9 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆83Updated 7 months ago
- ☆102Updated last month
- Understand and test language model architectures on synthetic tasks.☆161Updated 6 months ago
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging☆96Updated last year
- ☆96Updated 3 months ago
- Language models scale reliably with over-training and on downstream tasks☆94Updated 7 months ago
- ☆50Updated 5 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆95Updated 6 months ago
- A library for efficient patching and automatic circuit discovery.☆30Updated last month
- ☆89Updated 4 months ago
- ☆70Updated last year
- ☆78Updated last year
- Can Language Models Solve Olympiad Programming?☆100Updated 3 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆102Updated 7 months ago
- ☆99Updated this week
- ☆75Updated last month
- Function Vectors in Large Language Models (ICLR 2024)☆116Updated 3 weeks ago
- NanoGPT-like codebase for LLM training☆73Updated this week
- ☆43Updated 4 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆176Updated 5 months ago
- ☆35Updated 9 months ago
- ☆112Updated 3 months ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆46Updated 4 months ago
- ☆186Updated last month
- A repository for transformer critique learning and generation☆85Updated 11 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago