hkproj / rlhf-ppo
Notes and commented code for RLHF (PPO)
☆29Updated 6 months ago
Related projects: ⓘ
- The official evaluation suite and dynamic data release for MixEval.☆200Updated last week
- ☆239Updated 10 months ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆182Updated last month
- ☆105Updated this week
- A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)☆116Updated last week
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆123Updated 6 months ago
- Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind☆161Updated last week
- A pipeline to improve skills of large language models☆149Updated this week
- Small and Efficient Mathematical Reasoning LLMs☆69Updated 7 months ago
- X-LoRA: Mixture of LoRA Experts☆152Updated last month
- ☆179Updated this week
- An Analytical Evaluation Board of Multi-turn LLM Agents☆227Updated 4 months ago
- Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper☆119Updated 2 months ago
- Family of LLMs for mathematical reasoning.☆208Updated 3 months ago
- ☆87Updated 2 months ago
- Implementation of the ICML 2024 paper "Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning" pr…☆57Updated 7 months ago
- BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.☆139Updated 3 weeks ago
- Prune transformer layers☆60Updated 3 months ago
- Unofficial Implementation of Evolutionary Model Merging☆33Updated 5 months ago
- RewardBench: the first evaluation tool for reward models.☆352Updated last week
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆195Updated 4 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆333Updated last month
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search☆91Updated 3 months ago
- Chain-of-Hindsight, A Scalable RLHF Method☆213Updated 11 months ago
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆72Updated 8 months ago
- Code and example data for the paper: Rule Based Rewards for Language Model Safety☆131Updated 2 months ago
- A large-scale, fine-grained, diverse preference dataset (and models).☆299Updated 8 months ago
- augmented LLM with self reflection☆80Updated 9 months ago
- ☆98Updated 2 months ago
- RLHF implementation details of OAI's 2019 codebase☆144Updated 8 months ago