Large Model

We propose AdaInfer, a lightweight algorithm that adaptively stops LLM inference early based on statistical cues, cutting up to 43% of computation with <1% performance loss and no model modification.

We propose Few-Shot Detector (FSD), a novel AI-generated image detector that learns a metric space to recognize unseen fake images with only a few samples, achieving +11.6% higher accuracy and strong generalization without retraining.

As scaling laws underscore the potential of increasing model sizes, the academic community has intensified its investigations into LLMs with capacities exceeding 50 billion parameters. This technical report builds on our prior work with Tele-FLM (also known as FLM-2), a publicly available 52-billion-parameter model.

To lower the computional cost of training large model, we focus on speeding up pre-training by progressively growing from a small Transformer structure to a large one.

The FLM series of large models are a set of large models completed by the Cofe-AI team, including FLM-2, FLM-101B, and FreeLM. The core technology mainly consists of growth techniques, loss prediction technologies, and the FreeLM framework, among others.