GitHub

Is there a minimum GPU architecture requirement for running this model

Run the Script: Run run_model_hf_chat_template.py or run_model_hf.py, and switch the dtype to FP16 if necessary. A quick note on memory: Please ensure your GPU has sufficient capacity. A 7B model ...
GitHub

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

We propose TraceRL, a trajectory-aware reinforcement learning method for diffusion language models, which demonstrates the best performance among RL approaches for DLMs. We also introduce a ...