axeld5 / pali_reasonLinks
Testing paligemma2 finetuning on reasoning dataset
☆18Updated 7 months ago
Alternatives and similar repositories for pali_reason
Users that are interested in pali_reason are comparing it to the libraries listed below
Sorting:
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆45Updated 2 months ago
- ☆64Updated 2 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆72Updated 4 months ago
- An automated tool for discovering insights from research papaer corpora☆138Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 6 months ago
- ☆49Updated 5 months ago
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆117Updated 2 weeks ago
- Verifiers for LLM Reinforcement Learning☆68Updated 3 months ago
- Simple GRPO scripts and configurations.☆59Updated 5 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆91Updated 6 months ago
- ☆53Updated 8 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 6 months ago
- Small and Efficient Mathematical Reasoning LLMs☆71Updated last year
- ☆70Updated 2 weeks ago
- ☆87Updated last year
- Evaluating LLMs with CommonGen-Lite☆90Updated last year
- Just a bunch of benchmark logs for different LLMs☆119Updated last year
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆78Updated last week
- ☆86Updated 10 months ago
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆59Updated 7 months ago
- Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles☆53Updated 2 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated 11 months ago
- Train your own SOTA deductive reasoning model☆103Updated 4 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆23Updated 3 months ago
- Source code for the collaborative reasoner research project at Meta FAIR.☆99Updated 3 months ago
- Score LLM pretraining data with classifiers☆55Updated last year
- Small, simple agent task environments for training and evaluation☆18Updated 9 months ago
- ScreenSuite - The most comprehensive benchmarking suite for GUI Agents!☆99Updated last week
- The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆84Updated 2 weeks ago