Alternatives and similar repositories for grpo-optuna:

Users that are interested in grpo-optuna are comparing it to the libraries listed below

• minosvasilias / simple_grpo
  Simple GRPO scripts and configurations.
  ☆58Updated 2 months ago
• axolotl-ai-cloud / grpo_code
  A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.
  ☆22Updated last week
• teknium1 / transformers-gptq-quant
  ☆48Updated last year
• enjalot / latent-data-modal
  Using modal.com to process FineWeb-edu data
  ☆20Updated last week
• kubernetes-bad / reward-composer
  Lego for GRPO
  ☆26Updated last week
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated 5 months ago
• xjdr-alt / muzero_sketch
  ☆38Updated 8 months ago
• AnswerDotAI / ModernBERT-Instruct-mini-cookbook
  ☆40Updated 2 months ago
• catid / lllm
  Latent Large Language Models
  ☆17Updated 7 months ago
• arcee-ai / DAM
  ☆48Updated 5 months ago
• AtakanTekparmak / agento
  Very minimal (and stateless) agent framework
  ☆42Updated 3 months ago
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆83Updated last month
• axeld5 / pali_reason
  Testing paligemma2 finetuning on reasoning dataset
  ☆18Updated 3 months ago
• leloykun / modded-nanogpt
  NanoGPT (124M) quality in 2.67B tokens
  ☆28Updated this week
• matthewrenze / jhu-concise-cot
  The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models
  ☆21Updated 4 months ago
• ElleLeonne / Lightning-ReLoRA
  A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.
  ☆33Updated last year
• SebastianBodza / EnsembleForecasting
  Using multiple LLMs for ensemble Forecasting
  ☆16Updated last year
• yueqis / API-Based-Agent
  ☆50Updated 4 months ago
• samchaineau / llm_slerp_generation
  Repo hosting codes and materials related to speeding LLMs' inference using token merging.
  ☆35Updated 11 months ago
• bipul1010 / agents_tutorial
  ☆19Updated 8 months ago
• goncalorafaria / qalign
  QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.
  ☆15Updated last week
• NathanGodey / qfilters
  Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)
  ☆28Updated last month
• ivanleomk / modal-grpo
  ☆18Updated 3 weeks ago
• EduardTalianu / EntropixLab
  entropix style sampling + GUI
  ☆25Updated 5 months ago
• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆95Updated last month
• philschmid / MixEval
  The official evaluation suite and dynamic data release for MixEval.
  ☆11Updated 6 months ago
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆60Updated 3 weeks ago
• JoshuaPurtell / SmallBench
  Small, simple agent task environments for training and evaluation
  ☆18Updated 5 months ago
• SinatrasC / entropix
  Entropy Based Sampling and Parallel CoT Decoding
  ☆17Updated 6 months ago
• gangiswag / infogent
  ☆20Updated last month