cgftinc / benchmaxLinks
Framework-Agnostic RL Environments for LLM Fine-Tuning
☆42Updated last week
Alternatives and similar repositories for benchmax
Users that are interested in benchmax 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 3 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆112Updated 8 months ago
- Data recipes and robust infrastructure for training AI agents☆94Updated this week
- Aana SDK is a powerful framework for building AI enabled multimodal applications.☆56Updated 5 months ago
- Train your own SOTA deductive reasoning model☆107Updated 11 months ago
- ☆67Updated 8 months ago
- Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles☆61Updated 9 months ago
- II-Thought-RL is our initial attempt at developing a large-scale, multi-domain Reinforcement Learning (RL) dataset☆31Updated 10 months ago
- Lego for GRPO☆30Updated 8 months ago
- ☆24Updated last year
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆261Updated last week
- ☆39Updated 6 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆65Updated 9 months ago
- ☆56Updated last year
- Streamline on-policy/off-policy distillation workflows in a few lines of code☆95Updated this week
- Simple examples using Argilla tools to build AI☆57Updated last year
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated last year
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆35Updated 9 months ago
- ☆137Updated 10 months ago
- Nexusflow function call, tool use, and agent benchmarks.☆30Updated last year
- Pivotal Token Search☆144Updated last month
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆90Updated 10 months ago
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆125Updated 6 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆189Updated 11 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆26Updated last month
- Verifiers for LLM Reinforcement Learning☆80Updated 9 months ago
- Latent Large Language Models☆19Updated last year
- Data preparation code for CrystalCoder 7B LLM☆45Updated last year
- GPT-4 Level Conversational QA Trained In a Few Hours☆65Updated last year
- EXO Gym is an open-source Python toolkit that facilitates distributed AI research.☆96Updated 2 months ago