Pinned Loading

1. semantic-soft-bootstrapping semantic-soft-bootstrapping Public

   A self-distillation based training method for long context reasoning in a single LLM without reinforcement learning

   Python 10 1

2. MOTIF MOTIF Public

   MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs

   Python 16 1

3. distributed_moa distributed_moa Public

   Mixture-of-Agents Framework Implementation at Distributed Edge Devices with Theoretical Guarantee of Finite Average Latency

   Python 9 3

4. SOLOgenBench SOLOgenBench Public

   Forked from jd-3d/SOLOBench

   A generalized version of the original SOLO Bench (https://github.com/jd-3d/SOLOBench)

   Python 1