s-smits / grpo-optunaLinks
Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
☆53Updated 3 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.☆58Updated 3 months ago
- ☆57Updated last week
- Lego for GRPO☆28Updated last month
- Train your own SOTA deductive reasoning model☆92Updated 2 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆99Updated 2 months ago
- look how they massacred my boy☆63Updated 7 months ago
- A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.☆24Updated last month
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆38Updated 3 weeks ago
- Project code for training LLMs to write better unit tests + code☆20Updated last week
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 3 weeks ago
- ☆43Updated 3 months ago
- ☆38Updated 10 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆65Updated 2 months ago
- Testing paligemma2 finetuning on reasoning dataset☆18Updated 5 months ago
- ☆49Updated 6 months ago
- Verifiers for LLM Reinforcement Learning☆55Updated last month
- ☆48Updated last year
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆36Updated last year
- Official repo for Learning to Reason for Long-Form Story Generation☆58Updated last month
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 6 months ago
- Latent Large Language Models☆18Updated 9 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆67Updated last week
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆57Updated 9 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- ☆58Updated 2 weeks ago
- ☆16Updated 4 months ago
- Using modal.com to process FineWeb-edu data☆20Updated last month
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- ☆66Updated last year
- ☆9Updated last month