Search Results for "process control kill"

PRM800K is a process supervision dataset accompanying the paper Let’s Verify Step by Step, providing 800,000 step-level correctness labels on model-generated solutions to problems from the MATH dataset. The repository releases the raw labels and the labeler instructions used in two project phases, enabling researchers to study how human raters graded intermediate reasoning.

...It uses pretrained weights converted for PyTorch rather than training the language model from scratch. Users can begin generation from a supplied prompt or request unconditional samples. Command-line options control sample count, batch size, output length, temperature, and top-k filtering. The repository includes a runnable Python script, dependency file, and Google Colab notebook for faster experimentation. It is best suited to studying an early Transformer language model and its sampling process rather than building a modern production system.