FreedomIntelligence / TinyDeepSeekLinks
Reproduction of the complete process of DeepSeek-R1 on small-scale models, including Pre-training, SFT, and RL.
☆27Updated 5 months ago
Alternatives and similar repositories for TinyDeepSeek
Users that are interested in TinyDeepSeek are comparing it to the libraries listed below
Sorting:
- ☆114Updated 2 months ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆124Updated last month
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆82Updated 6 months ago
- Extrapolating RLVR to General Domains without Verifiers☆136Updated 2 weeks ago
- qwen-nsa☆71Updated 4 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆171Updated last month
- Due to the huge vocaburary size (151,936) of Qwen models, the Embedding and LM Head weights are excessively heavy. Therefore, this projec…☆24Updated 11 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆127Updated 3 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆160Updated this week
- ☆198Updated 4 months ago
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆41Updated 2 weeks ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆68Updated 4 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆271Updated 3 weeks ago
- This is a repo for showcasing using MCTS with LLMs to solve gsm8k problems☆86Updated 4 months ago
- ☆263Updated 2 months ago
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory☆167Updated 3 weeks ago
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆207Updated 2 weeks ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆77Updated last month
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆81Updated 2 months ago
- ☆25Updated 2 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆138Updated 4 months ago
- ☆96Updated 3 months ago
- Efficient Mixture of Experts for LLM Paper List☆90Updated 7 months ago
- ☆176Updated last month
- ☆65Updated 8 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆282Updated last month
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models☆148Updated 2 months ago
- [Preprint] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.☆59Updated this week
- Segment Policy Optimization: Improved Credit Assignment in Reinforcement Learning for LLMs☆29Updated 2 weeks ago
- Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"☆60Updated last year