kubernetes-bad / reward-composerLinks
Lego for GRPO
☆30Updated 6 months ago
Alternatives and similar repositories for reward-composer
Users that are interested in reward-composer are comparing it to the libraries listed below
Sorting:
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated last month
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆108Updated 8 months ago
- look how they massacred my boy☆63Updated last year
- Train your own SOTA deductive reasoning model☆107Updated 8 months ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆68Updated last week
- ☆68Updated 6 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 7 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 10 months ago
- ☆36Updated 4 months ago
- ☆62Updated 4 months ago
- ☆40Updated last year
- ☆55Updated last year
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated last year
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆84Updated 3 months ago
- Simple GRPO scripts and configurations.☆59Updated 9 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated last year
- Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles☆60Updated 6 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆72Updated 7 months ago
- An introduction to LLM Sampling☆79Updated 11 months ago
- smolLM with Entropix sampler on pytorch☆149Updated last year
- ☆67Updated last year
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated last year
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 9 months ago
- ☆136Updated last year
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆106Updated this week
- EvaByte: Efficient Byte-level Language Models at Scale☆111Updated 7 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆112Updated last month
- Latent Large Language Models☆19Updated last year
- entropix style sampling + GUI☆27Updated last year
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆99Updated 6 months ago