s-smits / grpo-optunaLinks
Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
☆55Updated 7 months ago
Alternatives and similar repositories for grpo-optuna
Users that are interested in grpo-optuna are comparing it to the libraries listed below
Sorting:
- Simple GRPO scripts and configurations.☆59Updated 7 months ago
- ☆68Updated 3 months ago
- ☆54Updated 10 months ago
- Project code for training LLMs to write better unit tests + code☆21Updated 3 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 6 months ago
- Latent Large Language Models☆18Updated last year
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆48Updated 4 months ago
- ☆49Updated 7 months ago
- Train your own SOTA deductive reasoning model☆106Updated 6 months ago
- look how they massacred my boy☆64Updated 10 months ago
- ☆34Updated last month
- Lego for GRPO☆29Updated 3 months ago
- ☆39Updated last year
- NanoGPT (124M) quality in 2.67B tokens☆28Updated last month
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆96Updated last month
- Official repo for Learning to Reason for Long-Form Story Generation☆68Updated 4 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆88Updated 3 months ago
- ☆13Updated 4 months ago
- An introduction to LLM Sampling☆80Updated 8 months ago
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆116Updated last month
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆24Updated this week
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 7 months ago
- Nexusflow function call, tool use, and agent benchmarks.☆29Updated 9 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆92Updated this week
- ☆61Updated 2 months ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 9 months ago
- ☆67Updated last year
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆77Updated 5 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated 11 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 6 months ago