deepseek-ai / ESFTLinks
Expert Specialized Fine-Tuning
☆690Updated 3 months ago
Alternatives and similar repositories for ESFT
Users that are interested in ESFT are comparing it to the libraries listed below
Sorting:
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,780Updated last year
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models☆2,871Updated last year
- ☆535Updated last year
- Muon is Scalable for LLM Training☆1,289Updated last month
- OLMoE: Open Mixture-of-Experts Language Models☆850Updated 5 months ago
- An Open Large Reasoning Model for Real-World Solutions☆1,516Updated 3 months ago
- [ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction☆546Updated 3 months ago
- A curated list of open-source projects related to DeepSeek Coder☆721Updated last year
- ☆812Updated 2 months ago
- Large Reasoning Models☆805Updated 9 months ago
- Scalable toolkit for efficient model reinforcement☆829Updated this week
- ☆636Updated this week
- ☆1,355Updated 9 months ago
- DeepSeek-VL: Towards Real-World Vision-Language Understanding☆3,950Updated last year
- A series of math-specific large language models of our Qwen2 series.☆997Updated 7 months ago
- Unleashing the Power of Reinforcement Learning for Math and Code Reasoners☆706Updated 2 months ago
- Analyze computation-communication overlap in V3/R1.☆1,096Updated 5 months ago
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,137Updated 7 months ago
- OpenSeek aims to unite the global open source community to drive collaborative innovation in algorithms, data and systems to develop next…☆222Updated this week
- [COLM 2025] LIMO: Less is More for Reasoning☆1,010Updated last month
- A project to improve skills of large language models☆538Updated this week
- Scalable RL solution for advanced reasoning of language models☆1,694Updated 5 months ago
- Official Repo for Open-Reasoner-Zero☆2,028Updated 3 months ago
- AllenAI's post-training codebase☆3,144Updated this week
- Seed-Coder is a family of lightweight open-source code LLMs comprising base, instruct and reasoning models, developed by ByteDance Seed.☆549Updated 2 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆435Updated 3 months ago
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,938Updated 11 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆346Updated 8 months ago
- Reaching LLaMA2 Performance with 0.1M Dollars☆988Updated last year
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆244Updated last year