Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
☆60Oct 18, 2025Updated 8 months ago
Alternatives and similar repositories for grpo-optuna
Users that are interested in grpo-optuna are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Project code for training LLMs to write better unit tests + code☆22May 19, 2025Updated last year
- NanoGPT (124M) in 5 minutes☆15Feb 14, 2025Updated last year
- ☆15Apr 26, 2025Updated last year
- Tiny evaluation of leading LLMs on competitive programming problems☆14Apr 10, 2026Updated 2 months ago
- Using modal.com to process FineWeb-edu data☆20Apr 11, 2026Updated 2 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code for full fintuing Mochi model with FSDP (and CP)☆29Jul 15, 2025Updated 11 months ago
- ☆37May 5, 2025Updated last year
- ICML 2025 Spotlight, PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative AP…☆15Jun 27, 2025Updated last year
- Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)☆46May 20, 2026Updated last month
- This repository hosts the code to port NumPy model weights of BiT-ResNets to TensorFlow SavedModel format.☆14Dec 21, 2021Updated 4 years ago
- Collection of autoregressive model implementation☆84Jun 10, 2026Updated 3 weeks ago
- Various test models in WNNX format. It can view with `pip install wnetron && wnetron`☆12Jun 22, 2022Updated 4 years ago
- Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation☆14Jan 2, 2026Updated 6 months ago
- Implements RNNPool and SoftPool for CNNs.☆14Jan 29, 2021Updated 5 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Grokking on modular arithmetic in less than 150 epochs in MLX☆15Oct 24, 2024Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- Includes additional materials for the following keras.io blog post.☆12Jun 23, 2021Updated 5 years ago
- Submodule of evalverse forked from [google-research/instruction_following_eval](https://github.com/google-research/google-research/tree/m…☆15May 4, 2024Updated 2 years ago
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆80Feb 11, 2025Updated last year
- Simple GRPO scripts and configurations.☆59Feb 6, 2025Updated last year
- Autoregressive Image Generation☆31Jun 13, 2025Updated last year
- One click away from a locally downloaded, fine-tuned model, hosted on hugging face, with inference built in. In two hours.☆24Jul 1, 2026Updated last week
- Verifiers for LLM Reinforcement Learning☆81Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Very minimal (and stateless) agent framework☆44Jan 12, 2025Updated last year
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- official implementation of paper "Process Reward Model with Q-value Rankings"☆69Feb 5, 2025Updated last year
- Build your own visual reasoning model☆422Jan 13, 2026Updated 5 months ago
- ☆20Oct 25, 2025Updated 8 months ago
- Fine-tunes a student LLM using teacher feedback for improved reasoning and answer quality. Implements GRPO with teacher-provided evaluati…☆54May 7, 2025Updated last year
- ☆29Apr 29, 2024Updated 2 years ago
- ☆47Aug 29, 2024Updated last year
- various experiments for scaling inference time compute with small reasoning models☆17Jan 16, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Transfer Learning in Dialogue Benchmarking Toolkit☆14Mar 31, 2023Updated 3 years ago
- This project takes the arXiv dataset and builds an automatic tag classifier from the arXiv article/paper titles☆13Aug 18, 2021Updated 4 years ago
- ☆33Nov 21, 2025Updated 7 months ago
- ☆18Jan 16, 2024Updated 2 years ago
- ☆120Apr 7, 2026Updated 3 months ago
- ☆12Jun 2, 2023Updated 3 years ago
- ☆69May 23, 2025Updated last year