goncalorafaria / qalignLinks
QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.
☆24Updated last month
Alternatives and similar repositories for qalign
Users that are interested in qalign are comparing it to the libraries listed below
Sorting:
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 3 months ago
- ☆49Updated 6 months ago
- Simple GRPO scripts and configurations.☆58Updated 3 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆57Updated 9 months ago
- Verifiers for LLM Reinforcement Learning☆55Updated last month
- Train your own SOTA deductive reasoning model☆92Updated 2 months ago
- ☆18Updated 8 months ago
- A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.☆24Updated last month
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆65Updated 2 months ago
- ☆50Updated 6 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆38Updated 3 weeks ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆59Updated last week
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆32Updated last month
- Official Code Release for "Training a Generally Curious Agent"☆20Updated last week
- ☆57Updated last week
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆111Updated last week
- ☆58Updated 2 weeks ago
- Lego for GRPO☆28Updated last month
- ☆33Updated 2 months ago
- Small, simple agent task environments for training and evaluation☆18Updated 7 months ago
- AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories☆15Updated 2 weeks ago
- Source code for the collaborative reasoner research project at Meta FAIR.☆83Updated last month
- Simple repository for training small reasoning models☆31Updated 3 months ago
- Training code for Sparse Autoencoders on Embedding models☆38Updated 3 months ago
- ☆27Updated 2 weeks ago
- ☆20Updated 3 weeks ago
- ☆29Updated 6 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆99Updated 2 months ago
- Aioli: A unified optimization framework for language model data mixing☆25Updated 4 months ago
- ☆23Updated last year