Popular repositoriesLoading

1. llm.scalallm.scalaPublic

   Extensible implementation of a Language Model (LLM) training framework in Scala.

   Scala 33 3

2. MegaScale-Infer-PrototypMegaScale-Infer-PrototypPublic

   Prototyp MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism

   Jupyter Notebook 26 2

3. MedAgentSim-PrototypeMedAgentSim-PrototypePublic

   MedAgentSim Prototype "Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions"

   Jupyter Notebook 10 2

4. iRoPE-tryiRoPE-tryPublic

   Jupyter Notebook 7 1

5. SuperTokenizerSuperTokenizerPublic

   A high-performance tokenizer built to rival GPT-4, trained on the C4 dataset.

   Jupyter Notebook 5

6. DeepSeek-V3.2-Exp-to-10MDeepSeek-V3.2-Exp-to-10MPublic

   Forked fromdeepseek-ai/DeepSeek-V3.2-Exp

   Pushing DeepSeek to 10M context window

   Python 5