shangshang-wang / TinaLinks
Tina: Tiny Reasoning Models via LoRA
☆314Updated 3 months ago
Alternatives and similar repositories for Tina
Users that are interested in Tina are comparing it to the libraries listed below
Sorting:
- Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"☆272Updated 3 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆370Updated last year
- Code for the paper: "Learning to Reason without External Rewards"☆385Updated 6 months ago
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).☆342Updated last month
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆179Updated 6 months ago
- ☆373Updated 2 months ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆358Updated 6 months ago
- minimal GRPO implementation from scratch☆102Updated 10 months ago
- A simplified implementation for experimenting with RLVR on GSM8K, This repository provides a starting point for exploring reasoning.☆156Updated 11 months ago
- [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example☆396Updated last month
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆618Updated 2 weeks ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆254Updated 8 months ago
- ☆227Updated 10 months ago
- ☆328Updated 7 months ago
- Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".☆280Updated 11 months ago
- A project to improve skills of large language models☆767Updated this week
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆227Updated 2 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆467Updated 8 months ago
- Minimal hackable GRPO implementation☆316Updated 11 months ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆276Updated 2 months ago
- Exploring Applications of GRPO☆252Updated 4 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆217Updated 7 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆352Updated 8 months ago
- A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning☆282Updated 3 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆175Updated last year
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆200Updated last month
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆141Updated 5 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆258Updated 8 months ago
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆181Updated 7 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆68Updated 9 months ago