inclusionAI / Ring-V2Links
Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.
☆76Updated last month
Alternatives and similar repositories for Ring-V2
Users that are interested in Ring-V2 are comparing it to the libraries listed below
Sorting:
- ☆103Updated 2 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆66Updated 7 months ago
- ☆317Updated 2 weeks ago
- Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.☆106Updated 3 months ago
- SIFT: Grounding LLM Reasoning in Contexts via Stickers☆58Updated 8 months ago
- ☆85Updated 7 months ago
- Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.☆228Updated last month
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆186Updated 4 months ago
- The official github repo for "Diffusion Language Models are Super Data Learners".☆200Updated 2 weeks ago
- Defeating the Training-Inference Mismatch via FP16☆154Updated last week
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆202Updated 3 weeks ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆118Updated 6 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆40Updated last month
- SSRL: Self-Search Reinforcement Learning☆152Updated 3 months ago
- Esoteric Language Models☆106Updated last month
- ☆85Updated last week
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆35Updated 8 months ago
- ☆19Updated 10 months ago
- Geometric-Mean Policy Optimization☆92Updated this week
- ☆61Updated 4 months ago
- ☆55Updated 5 months ago
- QeRL enables RL for 32B LLMs on a single H100 GPU.☆441Updated last month
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆180Updated 4 months ago
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆105Updated 2 months ago
- ☆105Updated 5 months ago
- MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.☆93Updated 2 months ago
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆60Updated 3 months ago
- MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning☆107Updated this week
- ☆92Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆124Updated 4 months ago