§ models · storyline
ByteDance's "iLLaDA" is a diffusion language model that keeps up with Qwen2.5
ByteDance and Renmin University release iLLaDA, an 8B diffusion language model that matches Qwen2.5 base performance but lags after fine-tuning.
Researchers from Renmin University and ByteDance have released iLLaDA, an 8B language model that generates text differently than ChatGPT. It matches Qwen2.5 at the base level but falls behind after fine-tuning.
The article ByteDance's "iLLaDA" is a diffusion language model that keeps up with Qwen2.5 appeared first on The Decoder.
§ sources1 publication · timeline below